{ "schema": "extended-run-catalog-v1", "sourceSha256": { "public-site/typesafe-repeats.json": "664b298af5a4780fa97ccf58bdd89ab9c12fcf4801319db9bfbd3d7136d8ed3e", "public-site/repeats.json": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "public-site/hosted-repeats.json": "15d6b725a2300a2c4f6b6a5984b2abac5fd9f08587a326eda64d1c41147cf458", "public-site/claude-repeats.json": "e2da6c5e3dc75b1673d1682a62b5c8a7bbe9fad87ab53e47412b4c4c3f368feb", "public-site/claude-roster-repeats.json": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "public-site/gemini-repeats.json": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "public-site/haiku-fresh-matched3.json": "6b49805ec97c55401b85eec2bd5ede5d18b8fe60ad63f7f7daa4fe4a922313f2", "public-site/laya-repeats.json": "a5e6f8b2faabb6db9bf6588cb1c3909a3694546297b7a6ebbac6c4bf12412ccf", "public-site/semif-repeats.json": "4bf539ce413e773bfec09c30fda8b502bd6300fe8b43cb85a41e922ca92c2e34", "public-site/semif-generated-repeats.json": "4e6b1b04ff427bc7ff970845b2138d06a79f9309fcb751dca40b90b9f30b07fc", "public-site/small-local-repeats.json": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "public-site/legacy-qwen-repeats.json": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "public-site/anyjev-raw-repeats.json": "8b729ad551a501aa71958df23fc26e8d491007d0af0361a08d6cd01798a36aa0", "public-site/anyjev-l0-repeats.json": "2bcf22675dadfc1b3e15cec27d68edfcdd4901fbbd405f0e595c2941708f3958", "public-site/anyjev-l1-repeats.json": "fed283e8e94f5cf1d7712bf48dfa7b3e9b5b2c03833a61df41265ce96d6ea94b", "public-site/anyjev-l2-repeats.json": "c9c2e610361628e9d67cb5c1c9246b61629be72f2c8915ef89ee77ed24021fd7", "public-site/anyjev-generated-repeats.json": "b4c5a867a5bb5916c24d99977451c83a1366dfd34f8bc0a3515b57b3a64e8d20", "public-site/alex-native-repeats.json": "9bb99cdc99bf6e54a57c69e6e0ee90b6c4a13008bc1ae15506edbb01a106c70e", "public-site/codex-fresh-repeats.json": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "public-site/deepseek-fresh-repeats.json": "df407ff4112b3e41e5c245579c6621a0ffdbcde966e6eb26d40ab6960278b6af", "public-site/additional-hosted-fresh-repeats.json": "cfd11bb576566097c6d351896e05578ffd6e1a35014011194d0d06fee0e85cf4", "public-site/qwen36-off-second-interruption-findings.json": "c6688ff8eb8a3cbc0c3a9c03c33e9121cbcf13d591518099c88e68f09e8712f0", "public-site/qwen27-final-descriptive-findings.json": "008fa43be645b4414a57e3e0783d6e5fc0bf428c09fa1bd5771fd064b93b1c42", "public-site/sonnet55-fresh-matched3.json": "ddcf0e523d49a5873285daa0c606d7e875251711670fc97ffb13d7d4c04b9f56", "public-site/openjev-native-repeats.json": "485a79dbab84a693a6ddfd53b2333ee394d095a4ea5a8e2989b17d546706c69e", "public-site/openjev-generated-repeats.json": "fa198837ea32f92556ed05a26023a632f3cf9b026970ed006d6370a537000562", "public-site/kev-native-repeats.json": "3f8b95ae790a8252fe2bb7a6823a8ee8196a245bf37bd4fb4f5944cb2b0e0fa9", "public-site/jev-native-prompt-findings.json": "464943a09a6bfe0f73c5d81d1427ec43fcb759167d2a79d7ff3ddaa7c1af23cc", "public-site/kev-native-prompt-findings.json": "0b860a96067bdd729c35bd131dd10a4495f7526ad7a01ee979077af36be52683", "public-site/clef-closed-repeat-findings.json": "72e9f99eb81979250f8c27805fe763423369edc9842565580ee9d711966ab082", "public-site/hosted-v2-repeats.json": "f385e8a5f969c1d0bea269e6a3279a84eaadd3e45f2dbe20a6d71f2bafaacceb", "public-site/gemma26-continuation-findings.json": "cce3d6d24e1708960ffe16158016017d8d28cbcdc2a5deb60e76e47b51cb32e7", "public-site/gemma26-second-continuation-findings.json": "f23d805f23117d39da1e1229d2bc2516eb667e1d17c355bc7ab5223c9bbb8ee0", "public-site/gemma26-p2-repeat-findings.json": "f595203141acf14ab9994e39d329ad177fdd79a429fa17844af553728c448fd9", "public-site/gemma26-fresh3-p0-checkpoint.json": "89cdf0bb3dcc82c4aa90662b4994067c8faa99b7c16b9244ef07d14394bdd8bf", "public-site/gemma26-fresh3-p1-interrupted-checkpoint.json": "2dab60820ffde5c4e31b871bf95a31d975ca28663ec2a6ad0cc22eca4b770176", "public-site/clef-flash-p1-findings.json": "16a1f65cf9ca4721cac60977accaa32e4ba1a11499d657c978abf368a457885b", "public-site/clef-flash-p2-findings.json": "017f3beb60bf91915411642fdcea5904ee938cfcbe66b01b76b99f02c5c22a1e", "public-site/clef-p0-repeat-findings.json": "8bbe4ed0be59c922c72e90640b30a9dc4d90f4aa063a61d142424ae66e16ad61", "public-site/deepseek-high-remaining6-successor-findings.json": "85ba944ed1a3cf5e0b287b4680275852c472beaee2be000c32aa56472fd2e0a6", "public-site/e4b-interruption-findings.json": "8c6474ee4d672ff4e9fb435a9d138a6dd61b9e14e89b65045cdc44a8fb109835", "public-site/deepseek-low-fresh3-findings.json": "bb9db920f74443d7e4b25b6b1f66e14b3f8ee97d67e7fc3eb2d154032821c97c", "public-site/deepseek-low-p1-successor-findings.json": "21e9f369afbbd877021843c77b679c6e3c9898e82037cb3edc7b2b358e95b67e", "public-site/deepseek-low-remaining6-price-v2-findings.json": "e45c23c22e875fe5e12c6f8d3dfc9af32ca7f34243fdbdbdd49cfb9e7e17b088", "public-site/deepseek-low-final-suffix-findings.json": "ab856fca91fcff7aa3e81749c0bdeaef63f0cd9af20475fdefb0a6b0e691290b", "public-site/mistral119-fresh1-p0-findings.json": "12deeac00c9a044fe3a66b28399fb27a147ac153225eb3d02376c3d1d53052d2" }, "runs": [ { "id": "extended-alex-openjev08-native-p0-v1-fresh1-p0", "experimentId": "extended-alex-openjev08-native-p0-v1-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-alex-native-repeats-v1", "repeatPass": "fresh1", "model": "alex-openjev08-native-p0-v1", "effort": null, "provider": "Local native MPS", "surface": "Local native MPS", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 3, "sentiment": 39, "follow_up_needed": 37, "serious_concern_reported": 20, "testimonial_potential": 9 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/alex-native-repeats.json", "sourceRecordSha256": "9bb99cdc99bf6e54a57c69e6e0ee90b6c4a13008bc1ae15506edbb01a106c70e", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/alex-native-repeats.json", "sourceFamily": "alex-native-repeats", "sourceStage": "alex-openjev08-native-p0-v1/fresh1/P0" }, { "id": "extended-alex-openjev08-native-p0-v1-fresh2-p0", "experimentId": "extended-alex-openjev08-native-p0-v1-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-alex-native-repeats-v1", "repeatPass": "fresh2", "model": "alex-openjev08-native-p0-v1", "effort": null, "provider": "Local native MPS", "surface": "Local native MPS", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 3, "sentiment": 39, "follow_up_needed": 37, "serious_concern_reported": 20, "testimonial_potential": 9 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/alex-native-repeats.json", "sourceRecordSha256": "9bb99cdc99bf6e54a57c69e6e0ee90b6c4a13008bc1ae15506edbb01a106c70e", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/alex-native-repeats.json", "sourceFamily": "alex-native-repeats", "sourceStage": "alex-openjev08-native-p0-v1/fresh2/P0" }, { "id": "extended-alex-openjev08-native-p0-v1-fresh3-p0", "experimentId": "extended-alex-openjev08-native-p0-v1-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-alex-native-repeats-v1", "repeatPass": "fresh3", "model": "alex-openjev08-native-p0-v1", "effort": null, "provider": "Local native MPS", "surface": "Local native MPS", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 3, "sentiment": 39, "follow_up_needed": 37, "serious_concern_reported": 20, "testimonial_potential": 9 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/alex-native-repeats.json", "sourceRecordSha256": "9bb99cdc99bf6e54a57c69e6e0ee90b6c4a13008bc1ae15506edbb01a106c70e", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/alex-native-repeats.json", "sourceFamily": "alex-native-repeats", "sourceStage": "alex-openjev08-native-p0-v1/fresh3/P0" }, { "id": "extended-alex-openjev4b-native-p0-v1-fresh1-p0", "experimentId": "extended-alex-openjev4b-native-p0-v1-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-alex-native-repeats-v1", "repeatPass": "fresh1", "model": "alex-openjev4b-native-p0-v1", "effort": null, "provider": "Local native MPS", "surface": "Local native MPS", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 39, "sentiment": 49, "follow_up_needed": 57, "serious_concern_reported": 47, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/alex-native-repeats.json", "sourceRecordSha256": "9bb99cdc99bf6e54a57c69e6e0ee90b6c4a13008bc1ae15506edbb01a106c70e", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/alex-native-repeats.json", "sourceFamily": "alex-native-repeats", "sourceStage": "alex-openjev4b-native-p0-v1/fresh1/P0" }, { "id": "extended-alex-openjev4b-native-p0-v1-fresh2-p0", "experimentId": "extended-alex-openjev4b-native-p0-v1-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-alex-native-repeats-v1", "repeatPass": "fresh2", "model": "alex-openjev4b-native-p0-v1", "effort": null, "provider": "Local native MPS", "surface": "Local native MPS", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 39, "sentiment": 49, "follow_up_needed": 57, "serious_concern_reported": 47, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/alex-native-repeats.json", "sourceRecordSha256": "9bb99cdc99bf6e54a57c69e6e0ee90b6c4a13008bc1ae15506edbb01a106c70e", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/alex-native-repeats.json", "sourceFamily": "alex-native-repeats", "sourceStage": "alex-openjev4b-native-p0-v1/fresh2/P0" }, { "id": "extended-alex-openjev4b-native-p0-v1-fresh3-p0", "experimentId": "extended-alex-openjev4b-native-p0-v1-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-alex-native-repeats-v1", "repeatPass": "fresh3", "model": "alex-openjev4b-native-p0-v1", "effort": null, "provider": "Local native MPS", "surface": "Local native MPS", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 39, "sentiment": 49, "follow_up_needed": 57, "serious_concern_reported": 47, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/alex-native-repeats.json", "sourceRecordSha256": "9bb99cdc99bf6e54a57c69e6e0ee90b6c4a13008bc1ae15506edbb01a106c70e", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/alex-native-repeats.json", "sourceFamily": "alex-native-repeats", "sourceStage": "alex-openjev4b-native-p0-v1/fresh3/P0" }, { "id": "extended-anyjev-qwen06-generated-fresh-three-fresh1-p0", "experimentId": "extended-anyjev-qwen06-generated-fresh-three-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-anyjev-generated-repeats-v1", "repeatPass": "fresh1", "model": "Qwen/Qwen3-0.6B", "effort": null, "provider": "Local native MPS", "surface": "Local native MPS", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 0, "metrics": { "all_four": 0, "sentiment": 0, "follow_up_needed": 0, "serious_concern_reported": 0, "testimonial_potential": 0 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 155.9247132546152, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 94350, "output": 2726, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-generated-repeats.json", "sourceRecordSha256": "b4c5a867a5bb5916c24d99977451c83a1366dfd34f8bc0a3515b57b3a64e8d20", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-generated-repeats.json", "sourceFamily": "anyjev-generated-repeats", "sourceStage": "anyjev-qwen06-generated-fresh-three/fresh1/P0" }, { "id": "extended-anyjev-qwen06-generated-fresh-three-fresh1-p1", "experimentId": "extended-anyjev-qwen06-generated-fresh-three-fresh1-p0", "parentBaselineId": "extended-anyjev-qwen06-generated-fresh-three-fresh1-p0", "protocolId": "report-only-anyjev-generated-repeats-v1", "repeatPass": "fresh1", "model": "Qwen/Qwen3-0.6B", "effort": null, "provider": "Local native MPS", "surface": "Local native MPS", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 0, "metrics": { "all_four": 0, "sentiment": 0, "follow_up_needed": 0, "serious_concern_reported": 0, "testimonial_potential": 0 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 172.89547520916676, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 104850, "output": 2734, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-generated-repeats.json", "sourceRecordSha256": "b4c5a867a5bb5916c24d99977451c83a1366dfd34f8bc0a3515b57b3a64e8d20", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-generated-repeats.json", "sourceFamily": "anyjev-generated-repeats", "sourceStage": "anyjev-qwen06-generated-fresh-three/fresh1/P1" }, { "id": "extended-anyjev-qwen06-generated-fresh-three-fresh1-p2", "experimentId": "extended-anyjev-qwen06-generated-fresh-three-fresh1-p0", "parentBaselineId": "extended-anyjev-qwen06-generated-fresh-three-fresh1-p0", "protocolId": "report-only-anyjev-generated-repeats-v1", "repeatPass": "fresh1", "model": "Qwen/Qwen3-0.6B", "effort": null, "provider": "Local native MPS", "surface": "Local native MPS", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 30, "metrics": { "all_four": 1, "sentiment": 23, "follow_up_needed": 20, "serious_concern_reported": 15, "testimonial_potential": 8 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 263.5809372899821, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 159150, "output": 2664, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-generated-repeats.json", "sourceRecordSha256": "b4c5a867a5bb5916c24d99977451c83a1366dfd34f8bc0a3515b57b3a64e8d20", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-generated-repeats.json", "sourceFamily": "anyjev-generated-repeats", "sourceStage": "anyjev-qwen06-generated-fresh-three/fresh1/P2" }, { "id": "extended-anyjev-qwen06-generated-fresh-three-fresh2-p0", "experimentId": "extended-anyjev-qwen06-generated-fresh-three-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-anyjev-generated-repeats-v1", "repeatPass": "fresh2", "model": "Qwen/Qwen3-0.6B", "effort": null, "provider": "Local native MPS", "surface": "Local native MPS", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 0, "metrics": { "all_four": 0, "sentiment": 0, "follow_up_needed": 0, "serious_concern_reported": 0, "testimonial_potential": 0 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 167.2106446250691, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 94350, "output": 2726, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-generated-repeats.json", "sourceRecordSha256": "b4c5a867a5bb5916c24d99977451c83a1366dfd34f8bc0a3515b57b3a64e8d20", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-generated-repeats.json", "sourceFamily": "anyjev-generated-repeats", "sourceStage": "anyjev-qwen06-generated-fresh-three/fresh2/P0" }, { "id": "extended-anyjev-qwen06-generated-fresh-three-fresh2-p1", "experimentId": "extended-anyjev-qwen06-generated-fresh-three-fresh2-p0", "parentBaselineId": "extended-anyjev-qwen06-generated-fresh-three-fresh2-p0", "protocolId": "report-only-anyjev-generated-repeats-v1", "repeatPass": "fresh2", "model": "Qwen/Qwen3-0.6B", "effort": null, "provider": "Local native MPS", "surface": "Local native MPS", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 0, "metrics": { "all_four": 0, "sentiment": 0, "follow_up_needed": 0, "serious_concern_reported": 0, "testimonial_potential": 0 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 179.776564621774, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 104850, "output": 2734, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-generated-repeats.json", "sourceRecordSha256": "b4c5a867a5bb5916c24d99977451c83a1366dfd34f8bc0a3515b57b3a64e8d20", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-generated-repeats.json", "sourceFamily": "anyjev-generated-repeats", "sourceStage": "anyjev-qwen06-generated-fresh-three/fresh2/P1" }, { "id": "extended-anyjev-qwen06-generated-fresh-three-fresh2-p2", "experimentId": "extended-anyjev-qwen06-generated-fresh-three-fresh2-p0", "parentBaselineId": "extended-anyjev-qwen06-generated-fresh-three-fresh2-p0", "protocolId": "report-only-anyjev-generated-repeats-v1", "repeatPass": "fresh2", "model": "Qwen/Qwen3-0.6B", "effort": null, "provider": "Local native MPS", "surface": "Local native MPS", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 30, "metrics": { "all_four": 1, "sentiment": 23, "follow_up_needed": 20, "serious_concern_reported": 15, "testimonial_potential": 8 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 278.1581933288835, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 159150, "output": 2664, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-generated-repeats.json", "sourceRecordSha256": "b4c5a867a5bb5916c24d99977451c83a1366dfd34f8bc0a3515b57b3a64e8d20", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-generated-repeats.json", "sourceFamily": "anyjev-generated-repeats", "sourceStage": "anyjev-qwen06-generated-fresh-three/fresh2/P2" }, { "id": "extended-anyjev-qwen06-generated-fresh-three-fresh3-p0", "experimentId": "extended-anyjev-qwen06-generated-fresh-three-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-anyjev-generated-repeats-v1", "repeatPass": "fresh3", "model": "Qwen/Qwen3-0.6B", "effort": null, "provider": "Local native MPS", "surface": "Local native MPS", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 0, "metrics": { "all_four": 0, "sentiment": 0, "follow_up_needed": 0, "serious_concern_reported": 0, "testimonial_potential": 0 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 156.15845812589396, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 94350, "output": 2726, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-generated-repeats.json", "sourceRecordSha256": "b4c5a867a5bb5916c24d99977451c83a1366dfd34f8bc0a3515b57b3a64e8d20", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-generated-repeats.json", "sourceFamily": "anyjev-generated-repeats", "sourceStage": "anyjev-qwen06-generated-fresh-three/fresh3/P0" }, { "id": "extended-anyjev-qwen06-generated-fresh-three-fresh3-p1", "experimentId": "extended-anyjev-qwen06-generated-fresh-three-fresh3-p0", "parentBaselineId": "extended-anyjev-qwen06-generated-fresh-three-fresh3-p0", "protocolId": "report-only-anyjev-generated-repeats-v1", "repeatPass": "fresh3", "model": "Qwen/Qwen3-0.6B", "effort": null, "provider": "Local native MPS", "surface": "Local native MPS", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 0, "metrics": { "all_four": 0, "sentiment": 0, "follow_up_needed": 0, "serious_concern_reported": 0, "testimonial_potential": 0 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 173.00069604074815, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 104850, "output": 2734, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-generated-repeats.json", "sourceRecordSha256": "b4c5a867a5bb5916c24d99977451c83a1366dfd34f8bc0a3515b57b3a64e8d20", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-generated-repeats.json", "sourceFamily": "anyjev-generated-repeats", "sourceStage": "anyjev-qwen06-generated-fresh-three/fresh3/P1" }, { "id": "extended-anyjev-qwen06-generated-fresh-three-fresh3-p2", "experimentId": "extended-anyjev-qwen06-generated-fresh-three-fresh3-p0", "parentBaselineId": "extended-anyjev-qwen06-generated-fresh-three-fresh3-p0", "protocolId": "report-only-anyjev-generated-repeats-v1", "repeatPass": "fresh3", "model": "Qwen/Qwen3-0.6B", "effort": null, "provider": "Local native MPS", "surface": "Local native MPS", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 30, "metrics": { "all_four": 1, "sentiment": 23, "follow_up_needed": 20, "serious_concern_reported": 15, "testimonial_potential": 8 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 262.9939998713089, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 159150, "output": 2664, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-generated-repeats.json", "sourceRecordSha256": "b4c5a867a5bb5916c24d99977451c83a1366dfd34f8bc0a3515b57b3a64e8d20", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-generated-repeats.json", "sourceFamily": "anyjev-generated-repeats", "sourceStage": "anyjev-qwen06-generated-fresh-three/fresh3/P2" }, { "id": "extended-anyjev-qwen06-l0-repeat2-p0", "experimentId": "extended-anyjev-qwen06-l0-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-anyjev-l0-repeats-v1", "repeatPass": "repeat2", "model": "Qwen/Qwen3-0.6B", "effort": null, "provider": "Local native MPS", "surface": "Local native MPS", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 4, "sentiment": 37, "follow_up_needed": 13, "serious_concern_reported": 34, "testimonial_potential": 44 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 5289.377210084931, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 5070194, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-l0-repeats.json", "sourceRecordSha256": "2bcf22675dadfc1b3e15cec27d68edfcdd4901fbbd405f0e595c2941708f3958", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-l0-repeats.json", "sourceFamily": "anyjev-l0-repeats", "sourceStage": "anyjev-qwen06-l0/repeat2/P0" }, { "id": "extended-anyjev-qwen06-l0-repeat3-p0", "experimentId": "extended-anyjev-qwen06-l0-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-anyjev-l0-repeats-v1", "repeatPass": "repeat3", "model": "Qwen/Qwen3-0.6B", "effort": null, "provider": "Local native MPS", "surface": "Local native MPS", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 4, "sentiment": 37, "follow_up_needed": 13, "serious_concern_reported": 34, "testimonial_potential": 44 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 3701.40697874903, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 5070194, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-l0-repeats.json", "sourceRecordSha256": "2bcf22675dadfc1b3e15cec27d68edfcdd4901fbbd405f0e595c2941708f3958", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-l0-repeats.json", "sourceFamily": "anyjev-l0-repeats", "sourceStage": "anyjev-qwen06-l0/repeat3/P0" }, { "id": "extended-anyjev-qwen06-l1-direct-native-cv5-fresh1-p0", "experimentId": "extended-anyjev-qwen06-l1-direct-native-cv5-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-anyjev-l1-repeats-v1", "repeatPass": "fresh1", "model": "Qwen/Qwen3-0.6B", "effort": null, "provider": "Local native MPS", "surface": "Local native MPS", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 6, "sentiment": 38, "follow_up_needed": 16, "serious_concern_reported": 31, "testimonial_potential": 49 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": 60, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-l1-repeats.json", "sourceRecordSha256": "fed283e8e94f5cf1d7712bf48dfa7b3e9b5b2c03833a61df41265ce96d6ea94b", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-l1-repeats.json", "sourceFamily": "anyjev-l1-repeats", "sourceStage": "anyjev-qwen06-l1-direct-native-cv5/fresh1/P0" }, { "id": "extended-anyjev-qwen06-l1-direct-native-cv5-fresh2-p0", "experimentId": "extended-anyjev-qwen06-l1-direct-native-cv5-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-anyjev-l1-repeats-v1", "repeatPass": "fresh2", "model": "Qwen/Qwen3-0.6B", "effort": null, "provider": "Local native MPS", "surface": "Local native MPS", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 6, "sentiment": 38, "follow_up_needed": 16, "serious_concern_reported": 31, "testimonial_potential": 49 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": 60, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-l1-repeats.json", "sourceRecordSha256": "fed283e8e94f5cf1d7712bf48dfa7b3e9b5b2c03833a61df41265ce96d6ea94b", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-l1-repeats.json", "sourceFamily": "anyjev-l1-repeats", "sourceStage": "anyjev-qwen06-l1-direct-native-cv5/fresh2/P0" }, { "id": "extended-anyjev-qwen06-l1-direct-native-cv5-fresh3-p0", "experimentId": "extended-anyjev-qwen06-l1-direct-native-cv5-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-anyjev-l1-repeats-v1", "repeatPass": "fresh3", "model": "Qwen/Qwen3-0.6B", "effort": null, "provider": "Local native MPS", "surface": "Local native MPS", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 6, "sentiment": 38, "follow_up_needed": 16, "serious_concern_reported": 31, "testimonial_potential": 49 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": 60, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-l1-repeats.json", "sourceRecordSha256": "fed283e8e94f5cf1d7712bf48dfa7b3e9b5b2c03833a61df41265ce96d6ea94b", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-l1-repeats.json", "sourceFamily": "anyjev-l1-repeats", "sourceStage": "anyjev-qwen06-l1-direct-native-cv5/fresh3/P0" }, { "id": "extended-anyjev-qwen06-native-l2-outer-cv5-hf517-adapter-v1-repeat2-p0", "experimentId": "extended-anyjev-qwen06-native-l2-outer-cv5-hf517-adapter-v1-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-anyjev-l2-repeats-v1", "repeatPass": "repeat2", "model": "anyjev-qwen06-native-l2-outer-cv5-hf517-adapter-v1", "effort": null, "provider": "Local native MPS", "surface": "Local native MPS", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 13, "sentiment": 33, "follow_up_needed": 43, "serious_concern_reported": 36, "testimonial_potential": 47 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 156.43749945788295, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": 60, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured; no token totals recorded." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-l2-repeats.json", "sourceRecordSha256": "c9c2e610361628e9d67cb5c1c9246b61629be72f2c8915ef89ee77ed24021fd7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-l2-repeats.json", "sourceFamily": "anyjev-l2-repeats", "sourceStage": "anyjev-qwen06-native-l2-outer-cv5-hf517-adapter-v1/repeat2/P0" }, { "id": "extended-anyjev-qwen06-native-l2-outer-cv5-hf517-adapter-v1-repeat3-p0", "experimentId": "extended-anyjev-qwen06-native-l2-outer-cv5-hf517-adapter-v1-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-anyjev-l2-repeats-v1", "repeatPass": "repeat3", "model": "anyjev-qwen06-native-l2-outer-cv5-hf517-adapter-v1", "effort": null, "provider": "Local native MPS", "surface": "Local native MPS", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 13, "sentiment": 33, "follow_up_needed": 43, "serious_concern_reported": 36, "testimonial_potential": 47 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 150.42132803212735, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": 60, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured; no token totals recorded." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-l2-repeats.json", "sourceRecordSha256": "c9c2e610361628e9d67cb5c1c9246b61629be72f2c8915ef89ee77ed24021fd7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-l2-repeats.json", "sourceFamily": "anyjev-l2-repeats", "sourceStage": "anyjev-qwen06-native-l2-outer-cv5-hf517-adapter-v1/repeat3/P0" }, { "id": "extended-anyjev-qwen06-raw-repeat2-p0", "experimentId": "extended-anyjev-qwen06-raw-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-anyjev-raw-repeats-v1", "repeatPass": "repeat2", "model": "Qwen/Qwen3-0.6B", "effort": null, "provider": "Local native MPS", "surface": "Local native MPS", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 0, "sentiment": 8, "follow_up_needed": 35, "serious_concern_reported": 25, "testimonial_potential": 33 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 474.62809087501955, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 367804, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-raw-repeats.json", "sourceRecordSha256": "8b729ad551a501aa71958df23fc26e8d491007d0af0361a08d6cd01798a36aa0", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-raw-repeats.json", "sourceFamily": "anyjev-raw-repeats", "sourceStage": "anyjev-qwen06-raw/repeat2/P0" }, { "id": "extended-anyjev-qwen06-raw-repeat3-p0", "experimentId": "extended-anyjev-qwen06-raw-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-anyjev-raw-repeats-v1", "repeatPass": "repeat3", "model": "Qwen/Qwen3-0.6B", "effort": null, "provider": "Local native MPS", "surface": "Local native MPS", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 0, "sentiment": 8, "follow_up_needed": 35, "serious_concern_reported": 25, "testimonial_potential": 33 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 498.67164642488933, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 367804, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-raw-repeats.json", "sourceRecordSha256": "8b729ad551a501aa71958df23fc26e8d491007d0af0361a08d6cd01798a36aa0", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/anyjev-raw-repeats.json", "sourceFamily": "anyjev-raw-repeats", "sourceStage": "anyjev-qwen06-raw/repeat3/P0" }, { "id": "extended-cloudflare-clef-direct-fresh1-p1", "experimentId": "extended-cloudflare-clef-direct-fresh1-p0", "parentBaselineId": "extended-cloudflare-clef-direct-fresh1-p0", "protocolId": "report-only-clef-closed-repeat-findings-v1", "repeatPass": "fresh1", "model": "clef", "effort": null, "provider": "Cloudflare", "surface": "Cloudflare connected app", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 52, "sentiment": 57, "follow_up_needed": 59, "serious_concern_reported": 55, "testimonial_potential": 57 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 144694, "output": 0, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": 0.94374, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/clef-closed-repeat-findings.json", "sourceRecordSha256": "72e9f99eb81979250f8c27805fe763423369edc9842565580ee9d711966ab082", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/clef-closed-repeat-findings.json", "sourceFamily": "clef-closed-repeat-findings", "sourceStage": "cloudflare-clef-direct/fresh1/P1" }, { "id": "extended-cloudflare-clef-direct-fresh1-p2", "experimentId": "extended-cloudflare-clef-direct-fresh1-p0", "parentBaselineId": "extended-cloudflare-clef-direct-fresh1-p0", "protocolId": "report-only-clef-closed-repeat-findings-v1", "repeatPass": "fresh1", "model": "clef", "effort": null, "provider": "Cloudflare", "surface": "Cloudflare connected app", "condition": "P2", "complete": false, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": null, "valid": 59, "metrics": { "all_four": 48, "sentiment": 54, "follow_up_needed": 57, "serious_concern_reported": 54, "testimonial_potential": 55 }, "pairedEligible": false, "resultStatus": "interrupted_composite", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 152364, "output": 0, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": 0.94374, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/clef-closed-repeat-findings.json", "sourceRecordSha256": "72e9f99eb81979250f8c27805fe763423369edc9842565580ee9d711966ab082", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/clef-closed-repeat-findings.json", "sourceFamily": "clef-closed-repeat-findings", "sourceStage": "cloudflare-clef-direct/fresh1/P2" }, { "id": "extended-cloudflare-clef-direct-fresh2-p0", "experimentId": "extended-cloudflare-clef-direct-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-clef-closed-repeat-findings-v1", "repeatPass": "fresh2", "model": "clef", "effort": null, "provider": "Cloudflare", "surface": "Cloudflare connected app", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 53, "sentiment": 55, "follow_up_needed": 59, "serious_concern_reported": 56, "testimonial_potential": 58 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 132694, "output": 0, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": 0.94374, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/clef-closed-repeat-findings.json", "sourceRecordSha256": "72e9f99eb81979250f8c27805fe763423369edc9842565580ee9d711966ab082", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/clef-closed-repeat-findings.json", "sourceFamily": "clef-closed-repeat-findings", "sourceStage": "cloudflare-clef-direct/fresh2/P0" }, { "id": "extended-cloudflare-clef-direct-fresh2-p1", "experimentId": "extended-cloudflare-clef-direct-fresh2-p0", "parentBaselineId": "extended-cloudflare-clef-direct-fresh2-p0", "protocolId": "report-only-clef-closed-repeat-findings-v1", "repeatPass": "fresh2", "model": "clef", "effort": null, "provider": "Cloudflare", "surface": "Cloudflare connected app", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 51, "sentiment": 57, "follow_up_needed": 58, "serious_concern_reported": 55, "testimonial_potential": 57 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 144694, "output": 0, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": 0.94374, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/clef-closed-repeat-findings.json", "sourceRecordSha256": "72e9f99eb81979250f8c27805fe763423369edc9842565580ee9d711966ab082", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/clef-closed-repeat-findings.json", "sourceFamily": "clef-closed-repeat-findings", "sourceStage": "cloudflare-clef-direct/fresh2/P1" }, { "id": "extended-cloudflare-clef-direct-fresh2-p2", "experimentId": "extended-cloudflare-clef-direct-fresh2-p0", "parentBaselineId": "extended-cloudflare-clef-direct-fresh2-p0", "protocolId": "report-only-clef-closed-repeat-findings-v1", "repeatPass": "fresh2", "model": "clef", "effort": null, "provider": "Cloudflare", "surface": "Cloudflare connected app", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 49, "sentiment": 55, "follow_up_needed": 58, "serious_concern_reported": 55, "testimonial_potential": 56 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 154954, "output": 0, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": 0.94374, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/clef-closed-repeat-findings.json", "sourceRecordSha256": "72e9f99eb81979250f8c27805fe763423369edc9842565580ee9d711966ab082", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/clef-closed-repeat-findings.json", "sourceFamily": "clef-closed-repeat-findings", "sourceStage": "cloudflare-clef-direct/fresh2/P2" }, { "id": "extended-cloudflare-clef-direct-fresh3-p0", "experimentId": "extended-cloudflare-clef-direct-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-clef-closed-repeat-findings-v1", "repeatPass": "fresh3", "model": "clef", "effort": null, "provider": "Cloudflare", "surface": "Cloudflare connected app", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 53, "sentiment": 55, "follow_up_needed": 59, "serious_concern_reported": 56, "testimonial_potential": 58 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 132694, "output": 0, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": 0.94374, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/clef-closed-repeat-findings.json", "sourceRecordSha256": "72e9f99eb81979250f8c27805fe763423369edc9842565580ee9d711966ab082", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/clef-closed-repeat-findings.json", "sourceFamily": "clef-closed-repeat-findings", "sourceStage": "cloudflare-clef-direct/fresh3/P0" }, { "id": "extended-cloudflare-clef-direct-fresh3-p1", "experimentId": "extended-cloudflare-clef-direct-fresh3-p0", "parentBaselineId": "extended-cloudflare-clef-direct-fresh3-p0", "protocolId": "report-only-clef-closed-repeat-findings-v1", "repeatPass": "fresh3", "model": "clef", "effort": null, "provider": "Cloudflare", "surface": "Cloudflare connected app", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 51, "sentiment": 57, "follow_up_needed": 58, "serious_concern_reported": 55, "testimonial_potential": 57 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 144694, "output": 0, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": 0.94374, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/clef-closed-repeat-findings.json", "sourceRecordSha256": "72e9f99eb81979250f8c27805fe763423369edc9842565580ee9d711966ab082", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/clef-closed-repeat-findings.json", "sourceFamily": "clef-closed-repeat-findings", "sourceStage": "cloudflare-clef-direct/fresh3/P1" }, { "id": "extended-cloudflare-clef-flash-direct-fresh1-p1", "experimentId": "extended-cloudflare-clef-flash-direct-fresh1-p0", "parentBaselineId": "extended-cloudflare-clef-flash-direct-fresh1-p0", "protocolId": "report-only-clef-flash-p1-findings-v1", "repeatPass": "fresh1", "model": "@cf/cloudflare/clef-flash", "effort": null, "provider": "Cloudflare connected app", "surface": "Cloudflare connected app", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 47, "sentiment": 52, "follow_up_needed": 57, "serious_concern_reported": 56, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/clef-flash-p1-findings.json", "sourceRecordSha256": "16a1f65cf9ca4721cac60977accaa32e4ba1a11499d657c978abf368a457885b", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/clef-flash-p1-findings.json", "sourceFamily": "clef-flash-p1-findings", "sourceStage": "cloudflare-clef-flash-direct/fresh1/P1" }, { "id": "extended-cloudflare-clef-flash-direct-fresh1-p2", "experimentId": "extended-cloudflare-clef-flash-direct-fresh1-p0", "parentBaselineId": "extended-cloudflare-clef-flash-direct-fresh1-p0", "protocolId": "report-only-clef-flash-p2-findings-v1", "repeatPass": "fresh1", "model": "@cf/cloudflare/clef-flash", "effort": null, "provider": "Cloudflare connected app", "surface": "Cloudflare connected app", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 46, "sentiment": 50, "follow_up_needed": 57, "serious_concern_reported": 56, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/clef-flash-p2-findings.json", "sourceRecordSha256": "017f3beb60bf91915411642fdcea5904ee938cfcbe66b01b76b99f02c5c22a1e", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/clef-flash-p2-findings.json", "sourceFamily": "clef-flash-p2-findings", "sourceStage": "cloudflare-clef-flash-direct/fresh1/P2" }, { "id": "extended-cloudflare-clef-flash-direct-fresh2-p0", "experimentId": "extended-cloudflare-clef-flash-direct-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-clef-p0-repeat-findings-v1", "repeatPass": "fresh2", "model": "@cf/cloudflare/clef-flash", "effort": null, "provider": "Cloudflare connected app", "surface": "Cloudflare connected app", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 45, "sentiment": 50, "follow_up_needed": 57, "serious_concern_reported": 56, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 258.680956, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 132694, "output": 0, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.01194246, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/clef-p0-repeat-findings.json", "sourceRecordSha256": "8bbe4ed0be59c922c72e90640b30a9dc4d90f4aa063a61d142424ae66e16ad61", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/clef-p0-repeat-findings.json", "sourceFamily": "clef-p0-repeat-findings", "sourceStage": "cloudflare-clef-flash-direct/fresh2/P0" }, { "id": "extended-cloudflare-clef-flash-direct-fresh2-p1", "experimentId": "extended-cloudflare-clef-flash-direct-fresh2-p0", "parentBaselineId": "extended-cloudflare-clef-flash-direct-fresh2-p0", "protocolId": "report-only-clef-flash-p1-findings-v1", "repeatPass": "fresh2", "model": "@cf/cloudflare/clef-flash", "effort": null, "provider": "Cloudflare connected app", "surface": "Cloudflare connected app", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 47, "sentiment": 52, "follow_up_needed": 57, "serious_concern_reported": 56, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/clef-flash-p1-findings.json", "sourceRecordSha256": "16a1f65cf9ca4721cac60977accaa32e4ba1a11499d657c978abf368a457885b", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/clef-flash-p1-findings.json", "sourceFamily": "clef-flash-p1-findings", "sourceStage": "cloudflare-clef-flash-direct/fresh2/P1" }, { "id": "extended-cloudflare-clef-flash-direct-fresh2-p2", "experimentId": "extended-cloudflare-clef-flash-direct-fresh2-p0", "parentBaselineId": "extended-cloudflare-clef-flash-direct-fresh2-p0", "protocolId": "report-only-clef-flash-p2-findings-v1", "repeatPass": "fresh2", "model": "@cf/cloudflare/clef-flash", "effort": null, "provider": "Cloudflare connected app", "surface": "Cloudflare connected app", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 46, "sentiment": 50, "follow_up_needed": 57, "serious_concern_reported": 56, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/clef-flash-p2-findings.json", "sourceRecordSha256": "017f3beb60bf91915411642fdcea5904ee938cfcbe66b01b76b99f02c5c22a1e", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/clef-flash-p2-findings.json", "sourceFamily": "clef-flash-p2-findings", "sourceStage": "cloudflare-clef-flash-direct/fresh2/P2" }, { "id": "extended-cloudflare-clef-flash-direct-fresh3-p1", "experimentId": "extended-cloudflare-clef-flash-direct-fresh3-p0", "parentBaselineId": "extended-cloudflare-clef-flash-direct-fresh3-p0", "protocolId": "report-only-clef-flash-p1-findings-v1", "repeatPass": "fresh3", "model": "@cf/cloudflare/clef-flash", "effort": null, "provider": "Cloudflare connected app", "surface": "Cloudflare connected app", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 47, "sentiment": 52, "follow_up_needed": 57, "serious_concern_reported": 56, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/clef-flash-p1-findings.json", "sourceRecordSha256": "16a1f65cf9ca4721cac60977accaa32e4ba1a11499d657c978abf368a457885b", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/clef-flash-p1-findings.json", "sourceFamily": "clef-flash-p1-findings", "sourceStage": "cloudflare-clef-flash-direct/fresh3/P1" }, { "id": "extended-cloudflare-clef-flash-direct-fresh3-p2", "experimentId": "extended-cloudflare-clef-flash-direct-fresh3-p0", "parentBaselineId": "extended-cloudflare-clef-flash-direct-fresh3-p0", "protocolId": "report-only-clef-flash-p2-findings-v1", "repeatPass": "fresh3", "model": "@cf/cloudflare/clef-flash", "effort": null, "provider": "Cloudflare connected app", "surface": "Cloudflare connected app", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 46, "sentiment": 50, "follow_up_needed": 57, "serious_concern_reported": 56, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/clef-flash-p2-findings.json", "sourceRecordSha256": "017f3beb60bf91915411642fdcea5904ee938cfcbe66b01b76b99f02c5c22a1e", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/clef-flash-p2-findings.json", "sourceFamily": "clef-flash-p2-findings", "sourceStage": "cloudflare-clef-flash-direct/fresh3/P2" }, { "id": "extended-codex-gpt-5.6-luna-high-repeat2-p0", "experimentId": "extended-codex-gpt-5.6-luna-high-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-5.6-luna", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 59, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 189.52906475096825, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 50579, "output": 5574, "cachedInput": 0, "cacheWrite": 0, "reasoning": 3532, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-luna-high/repeat2/P0" }, { "id": "extended-codex-gpt-5.6-luna-high-repeat2-p1", "experimentId": "extended-codex-gpt-5.6-luna-high-repeat2-p0", "parentBaselineId": "extended-codex-gpt-5.6-luna-high-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-5.6-luna", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 59, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 168.30352816695813, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 51617, "output": 4656, "cachedInput": 0, "cacheWrite": 0, "reasoning": 2614, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-luna-high/repeat2/P1" }, { "id": "extended-codex-gpt-5.6-luna-high-repeat2-p2", "experimentId": "extended-codex-gpt-5.6-luna-high-repeat2-p0", "parentBaselineId": "extended-codex-gpt-5.6-luna-high-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-5.6-luna", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 57, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 200.1530243739835, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 57025, "output": 5743, "cachedInput": 0, "cacheWrite": 0, "reasoning": 3705, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-luna-high/repeat2/P2" }, { "id": "extended-codex-gpt-5.6-luna-high-repeat3-p0", "experimentId": "extended-codex-gpt-5.6-luna-high-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-5.6-luna", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 226.82269937498495, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 50587, "output": 6259, "cachedInput": 4864, "cacheWrite": 0, "reasoning": 4217, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-luna-high/repeat3/P0" }, { "id": "extended-codex-gpt-5.6-luna-high-repeat3-p1", "experimentId": "extended-codex-gpt-5.6-luna-high-repeat3-p0", "parentBaselineId": "extended-codex-gpt-5.6-luna-high-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-5.6-luna", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 60, "sentiment": 60, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 183.88422016601544, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 51621, "output": 5400, "cachedInput": 4864, "cacheWrite": 0, "reasoning": 3358, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-luna-high/repeat3/P1" }, { "id": "extended-codex-gpt-5.6-luna-high-repeat3-p2", "experimentId": "extended-codex-gpt-5.6-luna-high-repeat3-p0", "parentBaselineId": "extended-codex-gpt-5.6-luna-high-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-5.6-luna", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 187.61148470800254, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 57027, "output": 5124, "cachedInput": 4864, "cacheWrite": 0, "reasoning": 3084, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-luna-high/repeat3/P2" }, { "id": "extended-codex-gpt-5.6-luna-low-phase2-batch10-p0-repeat2-p0", "experimentId": "extended-codex-gpt-5.6-luna-low-phase2-batch10-p0-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-5.6-luna", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 54, "sentiment": 56, "follow_up_needed": 59, "serious_concern_reported": 60, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 157.83119737400557, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 50583, "output": 3463, "cachedInput": 4864, "cacheWrite": 0, "reasoning": 1417, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-luna-low-phase2-batch10-p0/repeat2/P0" }, { "id": "extended-codex-gpt-5.6-luna-low-phase2-batch10-p0-repeat2-p1", "experimentId": "extended-codex-gpt-5.6-luna-low-phase2-batch10-p0-repeat2-p0", "parentBaselineId": "extended-codex-gpt-5.6-luna-low-phase2-batch10-p0-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-5.6-luna", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 153.42508250000537, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 51615, "output": 3678, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1636, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-luna-low-phase2-batch10-p0/repeat2/P1" }, { "id": "extended-codex-gpt-5.6-luna-low-phase2-batch10-p0-repeat2-p2", "experimentId": "extended-codex-gpt-5.6-luna-low-phase2-batch10-p0-repeat2-p0", "parentBaselineId": "extended-codex-gpt-5.6-luna-low-phase2-batch10-p0-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-5.6-luna", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 54, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 150.53700895802467, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 57035, "output": 3307, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1267, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-luna-low-phase2-batch10-p0/repeat2/P2" }, { "id": "extended-codex-gpt-5.6-luna-low-phase2-batch10-p0-repeat3-p0", "experimentId": "extended-codex-gpt-5.6-luna-low-phase2-batch10-p0-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-5.6-luna", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 55, "sentiment": 57, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 150.6137602510571, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 50583, "output": 3578, "cachedInput": 4864, "cacheWrite": 0, "reasoning": 1532, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-luna-low-phase2-batch10-p0/repeat3/P0" }, { "id": "extended-codex-gpt-5.6-luna-low-phase2-batch10-p0-repeat3-p1", "experimentId": "extended-codex-gpt-5.6-luna-low-phase2-batch10-p0-repeat3-p0", "parentBaselineId": "extended-codex-gpt-5.6-luna-low-phase2-batch10-p0-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-5.6-luna", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 57, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 149.56906716703088, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 51619, "output": 3496, "cachedInput": 4864, "cacheWrite": 0, "reasoning": 1452, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-luna-low-phase2-batch10-p0/repeat3/P1" }, { "id": "extended-codex-gpt-5.6-luna-low-phase2-batch10-p0-repeat3-p2", "experimentId": "extended-codex-gpt-5.6-luna-low-phase2-batch10-p0-repeat3-p0", "parentBaselineId": "extended-codex-gpt-5.6-luna-low-phase2-batch10-p0-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-5.6-luna", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 163.01812466600677, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 57037, "output": 3318, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1278, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-luna-low-phase2-batch10-p0/repeat3/P2" }, { "id": "extended-codex-gpt-5.6-luna-medium-repeat2-p0", "experimentId": "extended-codex-gpt-5.6-luna-medium-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-5.6-luna", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 60, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 162.94844712596387, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 50587, "output": 4048, "cachedInput": 0, "cacheWrite": 0, "reasoning": 2002, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-luna-medium/repeat2/P0" }, { "id": "extended-codex-gpt-5.6-luna-medium-repeat2-p1", "experimentId": "extended-codex-gpt-5.6-luna-medium-repeat2-p0", "parentBaselineId": "extended-codex-gpt-5.6-luna-medium-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-5.6-luna", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 57, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 157.01141300002928, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 51619, "output": 3755, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1711, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-luna-medium/repeat2/P1" }, { "id": "extended-codex-gpt-5.6-luna-medium-repeat2-p2", "experimentId": "extended-codex-gpt-5.6-luna-medium-repeat2-p0", "parentBaselineId": "extended-codex-gpt-5.6-luna-medium-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-5.6-luna", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 159.18557091700495, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 57031, "output": 3936, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1896, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-luna-medium/repeat2/P2" }, { "id": "extended-codex-gpt-5.6-luna-medium-repeat3-p0", "experimentId": "extended-codex-gpt-5.6-luna-medium-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-5.6-luna", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 55, "sentiment": 56, "follow_up_needed": 58, "serious_concern_reported": 60, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 166.82048108396702, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 52261, "output": 4283, "cachedInput": 4864, "cacheWrite": 0, "reasoning": 2229, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-luna-medium/repeat3/P0" }, { "id": "extended-codex-gpt-5.6-luna-medium-repeat3-p1", "experimentId": "extended-codex-gpt-5.6-luna-medium-repeat3-p0", "parentBaselineId": "extended-codex-gpt-5.6-luna-medium-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-5.6-luna", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 55, "sentiment": 56, "follow_up_needed": 59, "serious_concern_reported": 60, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 159.3275662481028, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 53297, "output": 4112, "cachedInput": 0, "cacheWrite": 0, "reasoning": 2066, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-luna-medium/repeat3/P1" }, { "id": "extended-codex-gpt-5.6-luna-medium-repeat3-p2", "experimentId": "extended-codex-gpt-5.6-luna-medium-repeat3-p0", "parentBaselineId": "extended-codex-gpt-5.6-luna-medium-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-5.6-luna", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 162.70658875105437, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 58145, "output": 4112, "cachedInput": 4864, "cacheWrite": 0, "reasoning": 2070, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-luna-medium/repeat3/P2" }, { "id": "extended-codex-gpt-5.6-luna-xhigh-fresh1-p0", "experimentId": "extended-codex-gpt-5.6-luna-xhigh-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh1", "model": "gpt-5.6-luna", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 476.9495899989852, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 52267, "output": 6629, "cachedInput": 0, "cacheWrite": 0, "reasoning": 4589, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-5.6-luna-xhigh/fresh1/P0" }, { "id": "extended-codex-gpt-5.6-luna-xhigh-fresh1-p1", "experimentId": "extended-codex-gpt-5.6-luna-xhigh-fresh1-p0", "parentBaselineId": "extended-codex-gpt-5.6-luna-xhigh-fresh1-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh1", "model": "gpt-5.6-luna", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 440.1176343750558, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 53295, "output": 6018, "cachedInput": 4864, "cacheWrite": 0, "reasoning": 3980, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-5.6-luna-xhigh/fresh1/P1" }, { "id": "extended-codex-gpt-5.6-luna-xhigh-fresh1-p2", "experimentId": "extended-codex-gpt-5.6-luna-xhigh-fresh1-p0", "parentBaselineId": "extended-codex-gpt-5.6-luna-xhigh-fresh1-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh1", "model": "gpt-5.6-luna", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 493.4979712910135, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 58701, "output": 5947, "cachedInput": 4864, "cacheWrite": 0, "reasoning": 3907, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-5.6-luna-xhigh/fresh1/P2" }, { "id": "extended-codex-gpt-5.6-luna-xhigh-fresh2-p0", "experimentId": "extended-codex-gpt-5.6-luna-xhigh-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh2", "model": "gpt-5.6-luna", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 387.07459366801777, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 52259, "output": 7658, "cachedInput": 0, "cacheWrite": 0, "reasoning": 5204, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-5.6-luna-xhigh/fresh2/P0" }, { "id": "extended-codex-gpt-5.6-luna-xhigh-fresh2-p1", "experimentId": "extended-codex-gpt-5.6-luna-xhigh-fresh2-p0", "parentBaselineId": "extended-codex-gpt-5.6-luna-xhigh-fresh2-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh2", "model": "gpt-5.6-luna", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 59, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 307.3891937089793, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 53289, "output": 6236, "cachedInput": 4864, "cacheWrite": 0, "reasoning": 4196, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-5.6-luna-xhigh/fresh2/P1" }, { "id": "extended-codex-gpt-5.6-luna-xhigh-fresh2-p2", "experimentId": "extended-codex-gpt-5.6-luna-xhigh-fresh2-p0", "parentBaselineId": "extended-codex-gpt-5.6-luna-xhigh-fresh2-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh2", "model": "gpt-5.6-luna", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 462.82342929099104, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 58707, "output": 6213, "cachedInput": 0, "cacheWrite": 0, "reasoning": 4175, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-5.6-luna-xhigh/fresh2/P2" }, { "id": "extended-codex-gpt-5.6-luna-xhigh-fresh3-p0", "experimentId": "extended-codex-gpt-5.6-luna-xhigh-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh3", "model": "gpt-5.6-luna", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 55, "sentiment": 58, "follow_up_needed": 57, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 453.16299479297595, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 52275, "output": 5579, "cachedInput": 11520, "cacheWrite": 0, "reasoning": 3537, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-5.6-luna-xhigh/fresh3/P0" }, { "id": "extended-codex-gpt-5.6-luna-xhigh-fresh3-p1", "experimentId": "extended-codex-gpt-5.6-luna-xhigh-fresh3-p0", "parentBaselineId": "extended-codex-gpt-5.6-luna-xhigh-fresh3-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh3", "model": "gpt-5.6-luna", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 368.28982737398474, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 53305, "output": 6829, "cachedInput": 4864, "cacheWrite": 0, "reasoning": 4789, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-5.6-luna-xhigh/fresh3/P1" }, { "id": "extended-codex-gpt-5.6-luna-xhigh-fresh3-p2", "experimentId": "extended-codex-gpt-5.6-luna-xhigh-fresh3-p0", "parentBaselineId": "extended-codex-gpt-5.6-luna-xhigh-fresh3-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh3", "model": "gpt-5.6-luna", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 59, "sentiment": 60, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 434.869322582992, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 58707, "output": 6200, "cachedInput": 6656, "cacheWrite": 0, "reasoning": 4160, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-5.6-luna-xhigh/fresh3/P2" }, { "id": "extended-codex-gpt-5.6-sol-high-repeat2-p0", "experimentId": "extended-codex-gpt-5.6-sol-high-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-5.6-sol", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 162.44650016599917, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 59643, "output": 4071, "cachedInput": 0, "cacheWrite": 0, "reasoning": 2029, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-sol-high/repeat2/P0" }, { "id": "extended-codex-gpt-5.6-sol-high-repeat2-p1", "experimentId": "extended-codex-gpt-5.6-sol-high-repeat2-p0", "parentBaselineId": "extended-codex-gpt-5.6-sol-high-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-5.6-sol", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 159.75130995706422, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 60679, "output": 3944, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1902, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-sol-high/repeat2/P1" }, { "id": "extended-codex-gpt-5.6-sol-high-repeat2-p2", "experimentId": "extended-codex-gpt-5.6-sol-high-repeat2-p0", "parentBaselineId": "extended-codex-gpt-5.6-sol-high-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-5.6-sol", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 162.55086937497254, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 66093, "output": 3794, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1756, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-sol-high/repeat2/P2" }, { "id": "extended-codex-gpt-5.6-sol-high-repeat3-p0", "experimentId": "extended-codex-gpt-5.6-sol-high-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-5.6-sol", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 164.1757174579543, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 61315, "output": 4071, "cachedInput": 6656, "cacheWrite": 0, "reasoning": 2031, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-sol-high/repeat3/P0" }, { "id": "extended-codex-gpt-5.6-sol-high-repeat3-p1", "experimentId": "extended-codex-gpt-5.6-sol-high-repeat3-p0", "parentBaselineId": "extended-codex-gpt-5.6-sol-high-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-5.6-sol", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 158.90681237500394, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 62349, "output": 3846, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1806, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-sol-high/repeat3/P1" }, { "id": "extended-codex-gpt-5.6-sol-high-repeat3-p2", "experimentId": "extended-codex-gpt-5.6-sol-high-repeat3-p0", "parentBaselineId": "extended-codex-gpt-5.6-sol-high-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-5.6-sol", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 157.54965870798333, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 67755, "output": 3756, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1714, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-sol-high/repeat3/P2" }, { "id": "extended-codex-gpt-5.6-sol-low-repeat2-p0", "experimentId": "extended-codex-gpt-5.6-sol-low-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-5.6-sol", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 160.84239258200978, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 61309, "output": 3168, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1128, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-sol-low/repeat2/P0" }, { "id": "extended-codex-gpt-5.6-sol-low-repeat2-p1", "experimentId": "extended-codex-gpt-5.6-sol-low-repeat2-p0", "parentBaselineId": "extended-codex-gpt-5.6-sol-low-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-5.6-sol", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 144.94833808398107, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 62345, "output": 2917, "cachedInput": 0, "cacheWrite": 0, "reasoning": 877, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-sol-low/repeat2/P1" }, { "id": "extended-codex-gpt-5.6-sol-low-repeat2-p2", "experimentId": "extended-codex-gpt-5.6-sol-low-repeat2-p0", "parentBaselineId": "extended-codex-gpt-5.6-sol-low-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-5.6-sol", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 157.15091362598469, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 67755, "output": 3001, "cachedInput": 6656, "cacheWrite": 0, "reasoning": 959, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-sol-low/repeat2/P2" }, { "id": "extended-codex-gpt-5.6-sol-low-repeat3-p0", "experimentId": "extended-codex-gpt-5.6-sol-low-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-5.6-sol", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 145.2070288329851, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 61313, "output": 3093, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1053, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-sol-low/repeat3/P0" }, { "id": "extended-codex-gpt-5.6-sol-low-repeat3-p1", "experimentId": "extended-codex-gpt-5.6-sol-low-repeat3-p0", "parentBaselineId": "extended-codex-gpt-5.6-sol-low-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-5.6-sol", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 154.03993408300448, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 62347, "output": 3099, "cachedInput": 19968, "cacheWrite": 0, "reasoning": 1057, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-sol-low/repeat3/P1" }, { "id": "extended-codex-gpt-5.6-sol-low-repeat3-p2", "experimentId": "extended-codex-gpt-5.6-sol-low-repeat3-p0", "parentBaselineId": "extended-codex-gpt-5.6-sol-low-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-5.6-sol", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 228.9457975840196, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 67759, "output": 3050, "cachedInput": 6656, "cacheWrite": 0, "reasoning": 1010, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-sol-low/repeat3/P2" }, { "id": "extended-codex-gpt-5.6-sol-medium-repeat2-p0", "experimentId": "extended-codex-gpt-5.6-sol-medium-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-5.6-sol", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 212.8577965000004, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 61313, "output": 3725, "cachedInput": 6656, "cacheWrite": 0, "reasoning": 1685, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-sol-medium/repeat2/P0" }, { "id": "extended-codex-gpt-5.6-sol-medium-repeat2-p1", "experimentId": "extended-codex-gpt-5.6-sol-medium-repeat2-p0", "parentBaselineId": "extended-codex-gpt-5.6-sol-medium-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-5.6-sol", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 160.53791012402507, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 62353, "output": 3603, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1563, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-sol-medium/repeat2/P1" }, { "id": "extended-codex-gpt-5.6-sol-medium-repeat2-p2", "experimentId": "extended-codex-gpt-5.6-sol-medium-repeat2-p0", "parentBaselineId": "extended-codex-gpt-5.6-sol-medium-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-5.6-sol", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 158.237668457994, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 67761, "output": 3608, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1568, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-sol-medium/repeat2/P2" }, { "id": "extended-codex-gpt-5.6-sol-medium-repeat3-p0", "experimentId": "extended-codex-gpt-5.6-sol-medium-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-5.6-sol", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 153.62794287598808, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 61311, "output": 3274, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1234, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-sol-medium/repeat3/P0" }, { "id": "extended-codex-gpt-5.6-sol-medium-repeat3-p1", "experimentId": "extended-codex-gpt-5.6-sol-medium-repeat3-p0", "parentBaselineId": "extended-codex-gpt-5.6-sol-medium-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-5.6-sol", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 184.92769962595776, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 62339, "output": 3605, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1563, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-sol-medium/repeat3/P1" }, { "id": "extended-codex-gpt-5.6-sol-medium-repeat3-p2", "experimentId": "extended-codex-gpt-5.6-sol-medium-repeat3-p0", "parentBaselineId": "extended-codex-gpt-5.6-sol-medium-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-5.6-sol", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 150.42418762500165, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 67755, "output": 3397, "cachedInput": 13312, "cacheWrite": 0, "reasoning": 1359, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-sol-medium/repeat3/P2" }, { "id": "extended-codex-gpt-5.6-sol-xhigh-repeat2-p0", "experimentId": "extended-codex-gpt-5.6-sol-xhigh-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-5.6-sol", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 300.75788870904944, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 61305, "output": 4175, "cachedInput": 0, "cacheWrite": 0, "reasoning": 2135, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-sol-xhigh/repeat2/P0" }, { "id": "extended-codex-gpt-5.6-sol-xhigh-repeat2-p1", "experimentId": "extended-codex-gpt-5.6-sol-xhigh-repeat2-p0", "parentBaselineId": "extended-codex-gpt-5.6-sol-xhigh-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-5.6-sol", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 170.8748967499996, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 62341, "output": 4249, "cachedInput": 0, "cacheWrite": 0, "reasoning": 2207, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-sol-xhigh/repeat2/P1" }, { "id": "extended-codex-gpt-5.6-sol-xhigh-repeat2-p2", "experimentId": "extended-codex-gpt-5.6-sol-xhigh-repeat2-p0", "parentBaselineId": "extended-codex-gpt-5.6-sol-xhigh-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-5.6-sol", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 181.66454808495473, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 67753, "output": 4820, "cachedInput": 0, "cacheWrite": 0, "reasoning": 2780, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-sol-xhigh/repeat2/P2" }, { "id": "extended-codex-gpt-5.6-sol-xhigh-repeat3-p0", "experimentId": "extended-codex-gpt-5.6-sol-xhigh-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-5.6-sol", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 180.8317953319929, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 61309, "output": 4334, "cachedInput": 0, "cacheWrite": 0, "reasoning": 2294, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-sol-xhigh/repeat3/P0" }, { "id": "extended-codex-gpt-5.6-sol-xhigh-repeat3-p1", "experimentId": "extended-codex-gpt-5.6-sol-xhigh-repeat3-p0", "parentBaselineId": "extended-codex-gpt-5.6-sol-xhigh-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-5.6-sol", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 172.41860937396996, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 62347, "output": 4338, "cachedInput": 13312, "cacheWrite": 0, "reasoning": 2298, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-sol-xhigh/repeat3/P1" }, { "id": "extended-codex-gpt-5.6-sol-xhigh-repeat3-p2", "experimentId": "extended-codex-gpt-5.6-sol-xhigh-repeat3-p0", "parentBaselineId": "extended-codex-gpt-5.6-sol-xhigh-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-5.6-sol", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 57, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 179.12559129096917, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 67757, "output": 4470, "cachedInput": 0, "cacheWrite": 0, "reasoning": 2432, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-sol-xhigh/repeat3/P2" }, { "id": "extended-codex-gpt-5.6-terra-high-repeat2-p0", "experimentId": "extended-codex-gpt-5.6-terra-high-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-5.6-terra", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 262.8698302929697, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 61315, "output": 3821, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1779, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-terra-high/repeat2/P0" }, { "id": "extended-codex-gpt-5.6-terra-high-repeat2-p1", "experimentId": "extended-codex-gpt-5.6-terra-high-repeat2-p0", "parentBaselineId": "extended-codex-gpt-5.6-terra-high-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-5.6-terra", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 57, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 168.49197587301023, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 62337, "output": 3946, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1902, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-terra-high/repeat2/P1" }, { "id": "extended-codex-gpt-5.6-terra-high-repeat2-p2", "experimentId": "extended-codex-gpt-5.6-terra-high-repeat2-p0", "parentBaselineId": "extended-codex-gpt-5.6-terra-high-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-5.6-terra", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 57, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 158.0072867909912, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 67755, "output": 3849, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1813, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-terra-high/repeat2/P2" }, { "id": "extended-codex-gpt-5.6-terra-high-repeat3-p0", "experimentId": "extended-codex-gpt-5.6-terra-high-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-5.6-terra", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 166.52378141597728, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 61313, "output": 4251, "cachedInput": 11776, "cacheWrite": 0, "reasoning": 2213, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-terra-high/repeat3/P0" }, { "id": "extended-codex-gpt-5.6-terra-high-repeat3-p1", "experimentId": "extended-codex-gpt-5.6-terra-high-repeat3-p0", "parentBaselineId": "extended-codex-gpt-5.6-terra-high-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-5.6-terra", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 60, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 159.92441712497384, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 62341, "output": 3738, "cachedInput": 23552, "cacheWrite": 0, "reasoning": 1700, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-terra-high/repeat3/P1" }, { "id": "extended-codex-gpt-5.6-terra-high-repeat3-p2", "experimentId": "extended-codex-gpt-5.6-terra-high-repeat3-p0", "parentBaselineId": "extended-codex-gpt-5.6-terra-high-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-5.6-terra", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 60, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 161.2869924159604, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 67757, "output": 3755, "cachedInput": 11776, "cacheWrite": 0, "reasoning": 1715, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-terra-high/repeat3/P2" }, { "id": "extended-codex-gpt-5.6-terra-low-fresh1-p0", "experimentId": "extended-codex-gpt-5.6-terra-low-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh1", "model": "gpt-5.6-terra", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 440.1393037069938, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 61177, "output": 3263, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1225, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-5.6-terra-low/fresh1/P0" }, { "id": "extended-codex-gpt-5.6-terra-low-fresh1-p1", "experimentId": "extended-codex-gpt-5.6-terra-low-fresh1-p0", "parentBaselineId": "extended-codex-gpt-5.6-terra-low-fresh1-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh1", "model": "gpt-5.6-terra", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 366.46075670799473, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 62211, "output": 3184, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1144, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-5.6-terra-low/fresh1/P1" }, { "id": "extended-codex-gpt-5.6-terra-low-fresh1-p2", "experimentId": "extended-codex-gpt-5.6-terra-low-fresh1-p0", "parentBaselineId": "extended-codex-gpt-5.6-terra-low-fresh1-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh1", "model": "gpt-5.6-terra", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 414.9048534980102, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 67617, "output": 3083, "cachedInput": 5888, "cacheWrite": 0, "reasoning": 1043, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-5.6-terra-low/fresh1/P2" }, { "id": "extended-codex-gpt-5.6-terra-low-fresh2-p0", "experimentId": "extended-codex-gpt-5.6-terra-low-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh2", "model": "gpt-5.6-terra", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 57, "follow_up_needed": 59, "serious_concern_reported": 60, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 448.24124487501103, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 61175, "output": 3503, "cachedInput": 11776, "cacheWrite": 0, "reasoning": 1457, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-5.6-terra-low/fresh2/P0" }, { "id": "extended-codex-gpt-5.6-terra-low-fresh2-p1", "experimentId": "extended-codex-gpt-5.6-terra-low-fresh2-p0", "parentBaselineId": "extended-codex-gpt-5.6-terra-low-fresh2-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh2", "model": "gpt-5.6-terra", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 275.66691220903886, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 62213, "output": 3250, "cachedInput": 17664, "cacheWrite": 0, "reasoning": 1212, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-5.6-terra-low/fresh2/P1" }, { "id": "extended-codex-gpt-5.6-terra-low-fresh2-p2", "experimentId": "extended-codex-gpt-5.6-terra-low-fresh2-p0", "parentBaselineId": "extended-codex-gpt-5.6-terra-low-fresh2-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh2", "model": "gpt-5.6-terra", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 57, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 424.7754243759846, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 67627, "output": 3274, "cachedInput": 11776, "cacheWrite": 0, "reasoning": 1238, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-5.6-terra-low/fresh2/P2" }, { "id": "extended-codex-gpt-5.6-terra-low-fresh3-p0", "experimentId": "extended-codex-gpt-5.6-terra-low-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh3", "model": "gpt-5.6-terra", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 398.1034922519757, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 61179, "output": 3308, "cachedInput": 23552, "cacheWrite": 0, "reasoning": 1270, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-5.6-terra-low/fresh3/P0" }, { "id": "extended-codex-gpt-5.6-terra-low-fresh3-p1", "experimentId": "extended-codex-gpt-5.6-terra-low-fresh3-p0", "parentBaselineId": "extended-codex-gpt-5.6-terra-low-fresh3-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh3", "model": "gpt-5.6-terra", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 57, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 340.2302165830333, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 62207, "output": 3606, "cachedInput": 23552, "cacheWrite": 0, "reasoning": 1570, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-5.6-terra-low/fresh3/P1" }, { "id": "extended-codex-gpt-5.6-terra-low-fresh3-p2", "experimentId": "extended-codex-gpt-5.6-terra-low-fresh3-p0", "parentBaselineId": "extended-codex-gpt-5.6-terra-low-fresh3-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh3", "model": "gpt-5.6-terra", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 390.97751491802046, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 67619, "output": 3256, "cachedInput": 17664, "cacheWrite": 0, "reasoning": 1218, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-5.6-terra-low/fresh3/P2" }, { "id": "extended-codex-gpt-5.6-terra-medium-fresh1-p0", "experimentId": "extended-codex-gpt-5.6-terra-medium-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh1", "model": "gpt-5.6-terra", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 457.5251157100429, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 61175, "output": 3655, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1615, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-5.6-terra-medium/fresh1/P0" }, { "id": "extended-codex-gpt-5.6-terra-medium-fresh1-p1", "experimentId": "extended-codex-gpt-5.6-terra-medium-fresh1-p0", "parentBaselineId": "extended-codex-gpt-5.6-terra-medium-fresh1-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh1", "model": "gpt-5.6-terra", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 420.7185164160037, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 62213, "output": 3682, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1642, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-5.6-terra-medium/fresh1/P1" }, { "id": "extended-codex-gpt-5.6-terra-medium-fresh1-p2", "experimentId": "extended-codex-gpt-5.6-terra-medium-fresh1-p0", "parentBaselineId": "extended-codex-gpt-5.6-terra-medium-fresh1-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh1", "model": "gpt-5.6-terra", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 435.89999816700583, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 67623, "output": 3423, "cachedInput": 5888, "cacheWrite": 0, "reasoning": 1383, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-5.6-terra-medium/fresh1/P2" }, { "id": "extended-codex-gpt-5.6-terra-medium-fresh2-p0", "experimentId": "extended-codex-gpt-5.6-terra-medium-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh2", "model": "gpt-5.6-terra", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 57, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 445.2665434589726, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 61169, "output": 3610, "cachedInput": 17664, "cacheWrite": 0, "reasoning": 1572, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-5.6-terra-medium/fresh2/P0" }, { "id": "extended-codex-gpt-5.6-terra-medium-fresh2-p1", "experimentId": "extended-codex-gpt-5.6-terra-medium-fresh2-p0", "parentBaselineId": "extended-codex-gpt-5.6-terra-medium-fresh2-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh2", "model": "gpt-5.6-terra", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 250.11489533403073, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 62213, "output": 3442, "cachedInput": 5888, "cacheWrite": 0, "reasoning": 1404, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-5.6-terra-medium/fresh2/P1" }, { "id": "extended-codex-gpt-5.6-terra-medium-fresh2-p2", "experimentId": "extended-codex-gpt-5.6-terra-medium-fresh2-p0", "parentBaselineId": "extended-codex-gpt-5.6-terra-medium-fresh2-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh2", "model": "gpt-5.6-terra", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 55, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 57, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 413.8208096239832, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 67621, "output": 3374, "cachedInput": 11776, "cacheWrite": 0, "reasoning": 1338, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-5.6-terra-medium/fresh2/P2" }, { "id": "extended-codex-gpt-5.6-terra-medium-fresh3-p0", "experimentId": "extended-codex-gpt-5.6-terra-medium-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh3", "model": "gpt-5.6-terra", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 431.3412961670547, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 61177, "output": 3576, "cachedInput": 29440, "cacheWrite": 0, "reasoning": 1534, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-5.6-terra-medium/fresh3/P0" }, { "id": "extended-codex-gpt-5.6-terra-medium-fresh3-p1", "experimentId": "extended-codex-gpt-5.6-terra-medium-fresh3-p0", "parentBaselineId": "extended-codex-gpt-5.6-terra-medium-fresh3-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh3", "model": "gpt-5.6-terra", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 57, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 333.2961011239677, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 62219, "output": 3802, "cachedInput": 23552, "cacheWrite": 0, "reasoning": 1760, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-5.6-terra-medium/fresh3/P1" }, { "id": "extended-codex-gpt-5.6-terra-medium-fresh3-p2", "experimentId": "extended-codex-gpt-5.6-terra-medium-fresh3-p0", "parentBaselineId": "extended-codex-gpt-5.6-terra-medium-fresh3-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh3", "model": "gpt-5.6-terra", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 57, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 403.1398742069723, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 67623, "output": 3581, "cachedInput": 17664, "cacheWrite": 0, "reasoning": 1539, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-5.6-terra-medium/fresh3/P2" }, { "id": "extended-codex-gpt-5.6-terra-xhigh-repeat2-p0", "experimentId": "extended-codex-gpt-5.6-terra-xhigh-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-5.6-terra", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 170.70239216904156, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 61307, "output": 4769, "cachedInput": 23552, "cacheWrite": 0, "reasoning": 2731, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-terra-xhigh/repeat2/P0" }, { "id": "extended-codex-gpt-5.6-terra-xhigh-repeat2-p1", "experimentId": "extended-codex-gpt-5.6-terra-xhigh-repeat2-p0", "parentBaselineId": "extended-codex-gpt-5.6-terra-xhigh-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-5.6-terra", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 171.52629333295044, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 62341, "output": 4825, "cachedInput": 0, "cacheWrite": 0, "reasoning": 2785, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-terra-xhigh/repeat2/P1" }, { "id": "extended-codex-gpt-5.6-terra-xhigh-repeat2-p2", "experimentId": "extended-codex-gpt-5.6-terra-xhigh-repeat2-p0", "parentBaselineId": "extended-codex-gpt-5.6-terra-xhigh-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-5.6-terra", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 60, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 177.10256775000016, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 67751, "output": 4870, "cachedInput": 0, "cacheWrite": 0, "reasoning": 2830, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-terra-xhigh/repeat2/P2" }, { "id": "extended-codex-gpt-5.6-terra-xhigh-repeat3-p0", "experimentId": "extended-codex-gpt-5.6-terra-xhigh-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-5.6-terra", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 431.29162062497926, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 61311, "output": 4864, "cachedInput": 5888, "cacheWrite": 0, "reasoning": 2824, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-terra-xhigh/repeat3/P0" }, { "id": "extended-codex-gpt-5.6-terra-xhigh-repeat3-p1", "experimentId": "extended-codex-gpt-5.6-terra-xhigh-repeat3-p0", "parentBaselineId": "extended-codex-gpt-5.6-terra-xhigh-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-5.6-terra", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 276.24327129201265, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 62335, "output": 4815, "cachedInput": 11776, "cacheWrite": 0, "reasoning": 2775, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-terra-xhigh/repeat3/P1" }, { "id": "extended-codex-gpt-5.6-terra-xhigh-repeat3-p2", "experimentId": "extended-codex-gpt-5.6-terra-xhigh-repeat3-p0", "parentBaselineId": "extended-codex-gpt-5.6-terra-xhigh-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-5.6-terra", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 840.3216630420065, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 67753, "output": 4602, "cachedInput": 17664, "cacheWrite": 0, "reasoning": 2562, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-5.6-terra-xhigh/repeat3/P2" }, { "id": "extended-codex-gpt-6-astra-high-repeat2-p0", "experimentId": "extended-codex-gpt-6-astra-high-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-6-astra", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 235.63891558299656, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 68077, "output": 2707, "cachedInput": 7680, "cacheWrite": 0, "reasoning": 665, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-astra-high/repeat2/P0" }, { "id": "extended-codex-gpt-6-astra-high-repeat2-p1", "experimentId": "extended-codex-gpt-6-astra-high-repeat2-p0", "parentBaselineId": "extended-codex-gpt-6-astra-high-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-6-astra", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 175.4518256240117, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 69109, "output": 2670, "cachedInput": 0, "cacheWrite": 0, "reasoning": 628, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-astra-high/repeat2/P1" }, { "id": "extended-codex-gpt-6-astra-high-repeat2-p2", "experimentId": "extended-codex-gpt-6-astra-high-repeat2-p0", "parentBaselineId": "extended-codex-gpt-6-astra-high-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-6-astra", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 171.37719237501733, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 74513, "output": 2701, "cachedInput": 0, "cacheWrite": 0, "reasoning": 659, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-astra-high/repeat2/P2" }, { "id": "extended-codex-gpt-6-astra-high-repeat3-p0", "experimentId": "extended-codex-gpt-6-astra-high-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-6-astra", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 434.2044812499953, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 68083, "output": 2749, "cachedInput": 0, "cacheWrite": 0, "reasoning": 707, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-astra-high/repeat3/P0" }, { "id": "extended-codex-gpt-6-astra-high-repeat3-p1", "experimentId": "extended-codex-gpt-6-astra-high-repeat3-p0", "parentBaselineId": "extended-codex-gpt-6-astra-high-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-6-astra", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 602.2201317089493, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 69099, "output": 2703, "cachedInput": 0, "cacheWrite": 0, "reasoning": 663, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-astra-high/repeat3/P1" }, { "id": "extended-codex-gpt-6-astra-high-repeat3-p2", "experimentId": "extended-codex-gpt-6-astra-high-repeat3-p0", "parentBaselineId": "extended-codex-gpt-6-astra-high-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-6-astra", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 259.3655267500435, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 74525, "output": 2630, "cachedInput": 7680, "cacheWrite": 0, "reasoning": 588, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-astra-high/repeat3/P2" }, { "id": "extended-codex-gpt-6-astra-low-phase2-batch10-p0-repeat2-p0", "experimentId": "extended-codex-gpt-6-astra-low-phase2-batch10-p0-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-6-astra", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 185.8891820840072, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 68077, "output": 2310, "cachedInput": 7680, "cacheWrite": 0, "reasoning": 272, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-astra-low-phase2-batch10-p0/repeat2/P0" }, { "id": "extended-codex-gpt-6-astra-low-phase2-batch10-p0-repeat2-p1", "experimentId": "extended-codex-gpt-6-astra-low-phase2-batch10-p0-repeat2-p0", "parentBaselineId": "extended-codex-gpt-6-astra-low-phase2-batch10-p0-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-6-astra", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 156.89359254096053, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 69109, "output": 2189, "cachedInput": 0, "cacheWrite": 0, "reasoning": 153, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-astra-low-phase2-batch10-p0/repeat2/P1" }, { "id": "extended-codex-gpt-6-astra-low-phase2-batch10-p0-repeat2-p2", "experimentId": "extended-codex-gpt-6-astra-low-phase2-batch10-p0-repeat2-p0", "parentBaselineId": "extended-codex-gpt-6-astra-low-phase2-batch10-p0-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-6-astra", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 162.08898491799482, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 74521, "output": 2154, "cachedInput": 0, "cacheWrite": 0, "reasoning": 118, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-astra-low-phase2-batch10-p0/repeat2/P2" }, { "id": "extended-codex-gpt-6-astra-low-phase2-batch10-p0-repeat3-p0", "experimentId": "extended-codex-gpt-6-astra-low-phase2-batch10-p0-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-6-astra", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 540.6672697490139, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 68073, "output": 2246, "cachedInput": 0, "cacheWrite": 0, "reasoning": 208, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-astra-low-phase2-batch10-p0/repeat3/P0" }, { "id": "extended-codex-gpt-6-astra-low-phase2-batch10-p0-repeat3-p1", "experimentId": "extended-codex-gpt-6-astra-low-phase2-batch10-p0-repeat3-p0", "parentBaselineId": "extended-codex-gpt-6-astra-low-phase2-batch10-p0-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-6-astra", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 235.44995033196756, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 69111, "output": 2155, "cachedInput": 0, "cacheWrite": 0, "reasoning": 121, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-astra-low-phase2-batch10-p0/repeat3/P1" }, { "id": "extended-codex-gpt-6-astra-low-phase2-batch10-p0-repeat3-p2", "experimentId": "extended-codex-gpt-6-astra-low-phase2-batch10-p0-repeat3-p0", "parentBaselineId": "extended-codex-gpt-6-astra-low-phase2-batch10-p0-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-6-astra", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 825.4445405420265, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 74511, "output": 2254, "cachedInput": 0, "cacheWrite": 0, "reasoning": 216, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-astra-low-phase2-batch10-p0/repeat3/P2" }, { "id": "extended-codex-gpt-6-astra-medium-fresh1-p0", "experimentId": "extended-codex-gpt-6-astra-medium-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh1", "model": "gpt-6-astra", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 460.652820082003, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 67979, "output": 2282, "cachedInput": 0, "cacheWrite": 0, "reasoning": 244, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-6-astra-medium/fresh1/P0" }, { "id": "extended-codex-gpt-6-astra-medium-fresh1-p1", "experimentId": "extended-codex-gpt-6-astra-medium-fresh1-p0", "parentBaselineId": "extended-codex-gpt-6-astra-medium-fresh1-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh1", "model": "gpt-6-astra", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 428.2994336670381, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 69005, "output": 2260, "cachedInput": 0, "cacheWrite": 0, "reasoning": 224, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-6-astra-medium/fresh1/P1" }, { "id": "extended-codex-gpt-6-astra-medium-fresh1-p2", "experimentId": "extended-codex-gpt-6-astra-medium-fresh1-p0", "parentBaselineId": "extended-codex-gpt-6-astra-medium-fresh1-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh1", "model": "gpt-6-astra", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 435.43282258399995, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 74387, "output": 2256, "cachedInput": 0, "cacheWrite": 0, "reasoning": 218, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-6-astra-medium/fresh1/P2" }, { "id": "extended-codex-gpt-6-astra-medium-fresh2-p0", "experimentId": "extended-codex-gpt-6-astra-medium-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh2", "model": "gpt-6-astra", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 449.4959667910007, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 67935, "output": 2217, "cachedInput": 7680, "cacheWrite": 0, "reasoning": 179, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-6-astra-medium/fresh2/P0" }, { "id": "extended-codex-gpt-6-astra-medium-fresh2-p1", "experimentId": "extended-codex-gpt-6-astra-medium-fresh2-p0", "parentBaselineId": "extended-codex-gpt-6-astra-medium-fresh2-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh2", "model": "gpt-6-astra", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 270.76320033401134, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 69011, "output": 2277, "cachedInput": 0, "cacheWrite": 0, "reasoning": 239, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-6-astra-medium/fresh2/P1" }, { "id": "extended-codex-gpt-6-astra-medium-fresh2-p2", "experimentId": "extended-codex-gpt-6-astra-medium-fresh2-p0", "parentBaselineId": "extended-codex-gpt-6-astra-medium-fresh2-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh2", "model": "gpt-6-astra", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 440.30675512499874, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 74375, "output": 2218, "cachedInput": 15360, "cacheWrite": 0, "reasoning": 180, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-6-astra-medium/fresh2/P2" }, { "id": "extended-codex-gpt-6-astra-medium-fresh3-p0", "experimentId": "extended-codex-gpt-6-astra-medium-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh3", "model": "gpt-6-astra", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 377.25817220899626, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 67935, "output": 2321, "cachedInput": 7680, "cacheWrite": 0, "reasoning": 283, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-6-astra-medium/fresh3/P0" }, { "id": "extended-codex-gpt-6-astra-medium-fresh3-p1", "experimentId": "extended-codex-gpt-6-astra-medium-fresh3-p0", "parentBaselineId": "extended-codex-gpt-6-astra-medium-fresh3-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh3", "model": "gpt-6-astra", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 341.8804662929906, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 68969, "output": 2302, "cachedInput": 0, "cacheWrite": 0, "reasoning": 264, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-6-astra-medium/fresh3/P1" }, { "id": "extended-codex-gpt-6-astra-medium-fresh3-p2", "experimentId": "extended-codex-gpt-6-astra-medium-fresh3-p0", "parentBaselineId": "extended-codex-gpt-6-astra-medium-fresh3-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh3", "model": "gpt-6-astra", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 422.34469483300927, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 74421, "output": 2327, "cachedInput": 0, "cacheWrite": 0, "reasoning": 287, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-6-astra-medium/fresh3/P2" }, { "id": "extended-codex-gpt-6-astra-xhigh-repeat2-p0", "experimentId": "extended-codex-gpt-6-astra-xhigh-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-6-astra", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 335.46733924996806, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 68077, "output": 4034, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1992, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-astra-xhigh/repeat2/P0" }, { "id": "extended-codex-gpt-6-astra-xhigh-repeat2-p1", "experimentId": "extended-codex-gpt-6-astra-xhigh-repeat2-p0", "parentBaselineId": "extended-codex-gpt-6-astra-xhigh-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-6-astra", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 216.51607945901924, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 69111, "output": 4162, "cachedInput": 0, "cacheWrite": 0, "reasoning": 2120, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-astra-xhigh/repeat2/P1" }, { "id": "extended-codex-gpt-6-astra-xhigh-repeat2-p2", "experimentId": "extended-codex-gpt-6-astra-xhigh-repeat2-p0", "parentBaselineId": "extended-codex-gpt-6-astra-xhigh-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-6-astra", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 220.77551095900708, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 74521, "output": 4027, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1985, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-astra-xhigh/repeat2/P2" }, { "id": "extended-codex-gpt-6-astra-xhigh-repeat3-p0", "experimentId": "extended-codex-gpt-6-astra-xhigh-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-6-astra", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 875.6492657079652, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 68075, "output": 4316, "cachedInput": 0, "cacheWrite": 0, "reasoning": 2274, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-astra-xhigh/repeat3/P0" }, { "id": "extended-codex-gpt-6-astra-xhigh-repeat3-p1", "experimentId": "extended-codex-gpt-6-astra-xhigh-repeat3-p0", "parentBaselineId": "extended-codex-gpt-6-astra-xhigh-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-6-astra", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 486.61900504201185, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 69107, "output": 3964, "cachedInput": 7680, "cacheWrite": 0, "reasoning": 1922, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-astra-xhigh/repeat3/P1" }, { "id": "extended-codex-gpt-6-astra-xhigh-repeat3-p2", "experimentId": "extended-codex-gpt-6-astra-xhigh-repeat3-p0", "parentBaselineId": "extended-codex-gpt-6-astra-xhigh-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-6-astra", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 686.9382786249917, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 74513, "output": 3714, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1672, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-astra-xhigh/repeat3/P2" }, { "id": "extended-codex-gpt-6-luna-high-batch10-repeat2-p0", "experimentId": "extended-codex-gpt-6-luna-high-batch10-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-6-luna", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 59, "sentiment": 60, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 395.75773795801797, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 64307, "output": 4500, "cachedInput": 6912, "cacheWrite": 0, "reasoning": 2460, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-luna-high-batch10/repeat2/P0" }, { "id": "extended-codex-gpt-6-luna-high-batch10-repeat2-p1", "experimentId": "extended-codex-gpt-6-luna-high-batch10-repeat2-p0", "parentBaselineId": "extended-codex-gpt-6-luna-high-batch10-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-6-luna", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 832.7191629169974, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 65339, "output": 4248, "cachedInput": 0, "cacheWrite": 0, "reasoning": 2208, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-luna-high-batch10/repeat2/P1" }, { "id": "extended-codex-gpt-6-luna-high-batch10-repeat2-p2", "experimentId": "extended-codex-gpt-6-luna-high-batch10-repeat2-p0", "parentBaselineId": "extended-codex-gpt-6-luna-high-batch10-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-6-luna", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 685.1804017490358, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 70749, "output": 4365, "cachedInput": 0, "cacheWrite": 0, "reasoning": 2325, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-luna-high-batch10/repeat2/P2" }, { "id": "extended-codex-gpt-6-luna-high-batch10-repeat3-p0", "experimentId": "extended-codex-gpt-6-luna-high-batch10-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-6-luna", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 1330.5672351270332, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 64313, "output": 4358, "cachedInput": 27648, "cacheWrite": 0, "reasoning": 2318, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-luna-high-batch10/repeat3/P0" }, { "id": "extended-codex-gpt-6-luna-high-batch10-repeat3-p1", "experimentId": "extended-codex-gpt-6-luna-high-batch10-repeat3-p0", "parentBaselineId": "extended-codex-gpt-6-luna-high-batch10-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-6-luna", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 59, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 642.9888259600848, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 65333, "output": 4261, "cachedInput": 0, "cacheWrite": 0, "reasoning": 2221, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-luna-high-batch10/repeat3/P1" }, { "id": "extended-codex-gpt-6-luna-high-batch10-repeat3-p2", "experimentId": "extended-codex-gpt-6-luna-high-batch10-repeat3-p0", "parentBaselineId": "extended-codex-gpt-6-luna-high-batch10-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-6-luna", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 349.54595045695896, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 70747, "output": 4409, "cachedInput": 0, "cacheWrite": 0, "reasoning": 2369, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-luna-high-batch10/repeat3/P2" }, { "id": "extended-codex-gpt-6-luna-low-batch10-fresh1-p0", "experimentId": "extended-codex-gpt-6-luna-low-batch10-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh1", "model": "gpt-6-luna", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 53, "sentiment": 58, "follow_up_needed": 57, "serious_concern_reported": 59, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 323.59442683291854, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 64183, "output": 2030, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-6-luna-low-batch10/fresh1/P0" }, { "id": "extended-codex-gpt-6-luna-low-batch10-fresh1-p1", "experimentId": "extended-codex-gpt-6-luna-low-batch10-fresh1-p0", "parentBaselineId": "extended-codex-gpt-6-luna-low-batch10-fresh1-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh1", "model": "gpt-6-luna", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 51, "sentiment": 57, "follow_up_needed": 58, "serious_concern_reported": 59, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 346.99720200093, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 65223, "output": 2030, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-6-luna-low-batch10/fresh1/P1" }, { "id": "extended-codex-gpt-6-luna-low-batch10-fresh1-p2", "experimentId": "extended-codex-gpt-6-luna-low-batch10-fresh1-p0", "parentBaselineId": "extended-codex-gpt-6-luna-low-batch10-fresh1-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh1", "model": "gpt-6-luna", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 50, "sentiment": 56, "follow_up_needed": 58, "serious_concern_reported": 59, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 375.8174480830203, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 70621, "output": 2030, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-6-luna-low-batch10/fresh1/P2" }, { "id": "extended-codex-gpt-6-luna-low-batch10-fresh2-p0", "experimentId": "extended-codex-gpt-6-luna-low-batch10-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh2", "model": "gpt-6-luna", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 53, "sentiment": 57, "follow_up_needed": 57, "serious_concern_reported": 58, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 360.27273141700425, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 64171, "output": 2028, "cachedInput": 2816, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-6-luna-low-batch10/fresh2/P0" }, { "id": "extended-codex-gpt-6-luna-low-batch10-fresh2-p1", "experimentId": "extended-codex-gpt-6-luna-low-batch10-fresh2-p0", "parentBaselineId": "extended-codex-gpt-6-luna-low-batch10-fresh2-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh2", "model": "gpt-6-luna", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 53, "sentiment": 56, "follow_up_needed": 58, "serious_concern_reported": 58, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 222.13405658400734, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 65201, "output": 2028, "cachedInput": 2816, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-6-luna-low-batch10/fresh2/P1" }, { "id": "extended-codex-gpt-6-luna-low-batch10-fresh2-p2", "experimentId": "extended-codex-gpt-6-luna-low-batch10-fresh2-p0", "parentBaselineId": "extended-codex-gpt-6-luna-low-batch10-fresh2-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh2", "model": "gpt-6-luna", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 51, "sentiment": 58, "follow_up_needed": 58, "serious_concern_reported": 58, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 306.8763638329692, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 70627, "output": 2028, "cachedInput": 6912, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-6-luna-low-batch10/fresh2/P2" }, { "id": "extended-codex-gpt-6-luna-low-batch10-fresh3-p0", "experimentId": "extended-codex-gpt-6-luna-low-batch10-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh3", "model": "gpt-6-luna", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 52, "sentiment": 55, "follow_up_needed": 58, "serious_concern_reported": 59, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 308.04146412498085, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 64177, "output": 2030, "cachedInput": 6912, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-6-luna-low-batch10/fresh3/P0" }, { "id": "extended-codex-gpt-6-luna-low-batch10-fresh3-p1", "experimentId": "extended-codex-gpt-6-luna-low-batch10-fresh3-p0", "parentBaselineId": "extended-codex-gpt-6-luna-low-batch10-fresh3-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh3", "model": "gpt-6-luna", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 55, "sentiment": 57, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 362.66645320801763, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 65205, "output": 2028, "cachedInput": 13824, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-6-luna-low-batch10/fresh3/P1" }, { "id": "extended-codex-gpt-6-luna-low-batch10-fresh3-p2", "experimentId": "extended-codex-gpt-6-luna-low-batch10-fresh3-p0", "parentBaselineId": "extended-codex-gpt-6-luna-low-batch10-fresh3-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh3", "model": "gpt-6-luna", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 50, "sentiment": 58, "follow_up_needed": 57, "serious_concern_reported": 59, "testimonial_potential": 56 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 359.5687124179967, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 70625, "output": 2030, "cachedInput": 9728, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-6-luna-low-batch10/fresh3/P2" }, { "id": "extended-codex-gpt-6-luna-medium-batch10-repeat2-p0", "experimentId": "extended-codex-gpt-6-luna-medium-batch10-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-6-luna", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 54, "sentiment": 57, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 133.44643004098907, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 62631, "output": 2028, "cachedInput": 6912, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-luna-medium-batch10/repeat2/P0" }, { "id": "extended-codex-gpt-6-luna-medium-batch10-repeat2-p1", "experimentId": "extended-codex-gpt-6-luna-medium-batch10-repeat2-p0", "parentBaselineId": "extended-codex-gpt-6-luna-medium-batch10-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-6-luna", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 52, "sentiment": 55, "follow_up_needed": 59, "serious_concern_reported": 60, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 117.65723462500318, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 63667, "output": 2032, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-luna-medium-batch10/repeat2/P1" }, { "id": "extended-codex-gpt-6-luna-medium-batch10-repeat2-p2", "experimentId": "extended-codex-gpt-6-luna-medium-batch10-repeat2-p0", "parentBaselineId": "extended-codex-gpt-6-luna-medium-batch10-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-6-luna", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 53, "sentiment": 57, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 56 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 119.4819463329768, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 69079, "output": 2028, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-luna-medium-batch10/repeat2/P2" }, { "id": "extended-codex-gpt-6-luna-medium-batch10-repeat3-p0", "experimentId": "extended-codex-gpt-6-luna-medium-batch10-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-6-luna", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 51, "sentiment": 53, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 128.13191045699932, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 62623, "output": 2030, "cachedInput": 13824, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-luna-medium-batch10/repeat3/P0" }, { "id": "extended-codex-gpt-6-luna-medium-batch10-repeat3-p1", "experimentId": "extended-codex-gpt-6-luna-medium-batch10-repeat3-p0", "parentBaselineId": "extended-codex-gpt-6-luna-medium-batch10-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-6-luna", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 53, "sentiment": 56, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 116.81949270797486, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 63661, "output": 2030, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-luna-medium-batch10/repeat3/P1" }, { "id": "extended-codex-gpt-6-luna-medium-batch10-repeat3-p2", "experimentId": "extended-codex-gpt-6-luna-medium-batch10-repeat3-p0", "parentBaselineId": "extended-codex-gpt-6-luna-medium-batch10-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-6-luna", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 51, "sentiment": 55, "follow_up_needed": 59, "serious_concern_reported": 60, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 113.90285770899209, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 69075, "output": 2032, "cachedInput": 13824, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-luna-medium-batch10/repeat3/P2" }, { "id": "extended-codex-gpt-6-luna-xhigh-batch10-repeat2-p0", "experimentId": "extended-codex-gpt-6-luna-xhigh-batch10-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-6-luna", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 414.57683758297935, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 64311, "output": 6266, "cachedInput": 6912, "cacheWrite": 0, "reasoning": 4226, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-luna-xhigh-batch10/repeat2/P0" }, { "id": "extended-codex-gpt-6-luna-xhigh-batch10-repeat2-p1", "experimentId": "extended-codex-gpt-6-luna-xhigh-batch10-repeat2-p0", "parentBaselineId": "extended-codex-gpt-6-luna-xhigh-batch10-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-6-luna", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 60, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 702.1921408319904, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 65343, "output": 5842, "cachedInput": 0, "cacheWrite": 0, "reasoning": 3802, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-luna-xhigh-batch10/repeat2/P1" }, { "id": "extended-codex-gpt-6-luna-xhigh-batch10-repeat2-p2", "experimentId": "extended-codex-gpt-6-luna-xhigh-batch10-repeat2-p0", "parentBaselineId": "extended-codex-gpt-6-luna-xhigh-batch10-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-6-luna", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 870.9317855419649, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 70753, "output": 7021, "cachedInput": 0, "cacheWrite": 0, "reasoning": 4981, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-luna-xhigh-batch10/repeat2/P2" }, { "id": "extended-codex-gpt-6-luna-xhigh-batch10-repeat3-p0", "experimentId": "extended-codex-gpt-6-luna-xhigh-batch10-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-6-luna", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 1363.283458750986, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 64305, "output": 6324, "cachedInput": 13824, "cacheWrite": 0, "reasoning": 4284, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-luna-xhigh-batch10/repeat3/P0" }, { "id": "extended-codex-gpt-6-luna-xhigh-batch10-repeat3-p1", "experimentId": "extended-codex-gpt-6-luna-xhigh-batch10-repeat3-p0", "parentBaselineId": "extended-codex-gpt-6-luna-xhigh-batch10-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-6-luna", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 60, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 365.2938113340351, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 65335, "output": 5827, "cachedInput": 0, "cacheWrite": 0, "reasoning": 3787, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-luna-xhigh-batch10/repeat3/P1" }, { "id": "extended-codex-gpt-6-luna-xhigh-batch10-repeat3-p2", "experimentId": "extended-codex-gpt-6-luna-xhigh-batch10-repeat3-p0", "parentBaselineId": "extended-codex-gpt-6-luna-xhigh-batch10-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-6-luna", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 638.6333642910467, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 70755, "output": 5985, "cachedInput": 6912, "cacheWrite": 0, "reasoning": 3947, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-luna-xhigh-batch10/repeat3/P2" }, { "id": "extended-codex-gpt-6-sol-high-batch10-repeat2-p0", "experimentId": "extended-codex-gpt-6-sol-high-batch10-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-6-sol", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 145.12938929001393, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 63699, "output": 3567, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1527, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-sol-high-batch10/repeat2/P0" }, { "id": "extended-codex-gpt-6-sol-high-batch10-repeat2-p1", "experimentId": "extended-codex-gpt-6-sol-high-batch10-repeat2-p0", "parentBaselineId": "extended-codex-gpt-6-sol-high-batch10-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-6-sol", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 147.03782166801102, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 64743, "output": 3729, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1687, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-sol-high-batch10/repeat2/P1" }, { "id": "extended-codex-gpt-6-sol-high-batch10-repeat2-p2", "experimentId": "extended-codex-gpt-6-sol-high-batch10-repeat2-p0", "parentBaselineId": "extended-codex-gpt-6-sol-high-batch10-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-6-sol", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 139.24652428997797, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 70153, "output": 3155, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1117, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-sol-high-batch10/repeat2/P2" }, { "id": "extended-codex-gpt-6-sol-high-batch10-repeat3-p0", "experimentId": "extended-codex-gpt-6-sol-high-batch10-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-6-sol", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 148.03224833299464, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 63695, "output": 3553, "cachedInput": 21504, "cacheWrite": 0, "reasoning": 1513, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-sol-high-batch10/repeat3/P0" }, { "id": "extended-codex-gpt-6-sol-high-batch10-repeat3-p1", "experimentId": "extended-codex-gpt-6-sol-high-batch10-repeat3-p0", "parentBaselineId": "extended-codex-gpt-6-sol-high-batch10-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-6-sol", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 159.05100624902116, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 64733, "output": 3556, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1518, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-sol-high-batch10/repeat3/P1" }, { "id": "extended-codex-gpt-6-sol-high-batch10-repeat3-p2", "experimentId": "extended-codex-gpt-6-sol-high-batch10-repeat3-p0", "parentBaselineId": "extended-codex-gpt-6-sol-high-batch10-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-6-sol", "effort": "high", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 149.67460704299447, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 70155, "output": 3632, "cachedInput": 21504, "cacheWrite": 0, "reasoning": 1590, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-sol-high-batch10/repeat3/P2" }, { "id": "extended-codex-gpt-6-sol-low-batch10-fresh1-p0", "experimentId": "extended-codex-gpt-6-sol-low-batch10-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh1", "model": "gpt-6-sol", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 357.1956914579496, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 65253, "output": 2545, "cachedInput": 0, "cacheWrite": 0, "reasoning": 503, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-6-sol-low-batch10/fresh1/P0" }, { "id": "extended-codex-gpt-6-sol-low-batch10-fresh1-p1", "experimentId": "extended-codex-gpt-6-sol-low-batch10-fresh1-p0", "parentBaselineId": "extended-codex-gpt-6-sol-low-batch10-fresh1-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh1", "model": "gpt-6-sol", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 348.96601262604236, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 66297, "output": 2464, "cachedInput": 0, "cacheWrite": 0, "reasoning": 422, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-6-sol-low-batch10/fresh1/P1" }, { "id": "extended-codex-gpt-6-sol-low-batch10-fresh1-p2", "experimentId": "extended-codex-gpt-6-sol-low-batch10-fresh1-p0", "parentBaselineId": "extended-codex-gpt-6-sol-low-batch10-fresh1-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh1", "model": "gpt-6-sol", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 459.2679942919931, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 71693, "output": 2739, "cachedInput": 0, "cacheWrite": 0, "reasoning": 699, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-6-sol-low-batch10/fresh1/P2" }, { "id": "extended-codex-gpt-6-sol-low-batch10-fresh2-p0", "experimentId": "extended-codex-gpt-6-sol-low-batch10-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh2", "model": "gpt-6-sol", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 379.04127554106526, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 65239, "output": 2607, "cachedInput": 7168, "cacheWrite": 0, "reasoning": 569, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-6-sol-low-batch10/fresh2/P0" }, { "id": "extended-codex-gpt-6-sol-low-batch10-fresh2-p1", "experimentId": "extended-codex-gpt-6-sol-low-batch10-fresh2-p0", "parentBaselineId": "extended-codex-gpt-6-sol-low-batch10-fresh2-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh2", "model": "gpt-6-sol", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 57, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 253.99677908307058, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 66285, "output": 2463, "cachedInput": 0, "cacheWrite": 0, "reasoning": 423, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-6-sol-low-batch10/fresh2/P1" }, { "id": "extended-codex-gpt-6-sol-low-batch10-fresh2-p2", "experimentId": "extended-codex-gpt-6-sol-low-batch10-fresh2-p0", "parentBaselineId": "extended-codex-gpt-6-sol-low-batch10-fresh2-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh2", "model": "gpt-6-sol", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 57, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 366.071746667003, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 71685, "output": 2657, "cachedInput": 0, "cacheWrite": 0, "reasoning": 621, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-6-sol-low-batch10/fresh2/P2" }, { "id": "extended-codex-gpt-6-sol-low-batch10-fresh3-p0", "experimentId": "extended-codex-gpt-6-sol-low-batch10-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh3", "model": "gpt-6-sol", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 314.4008767900232, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 65249, "output": 2393, "cachedInput": 7168, "cacheWrite": 0, "reasoning": 355, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-6-sol-low-batch10/fresh3/P0" }, { "id": "extended-codex-gpt-6-sol-low-batch10-fresh3-p1", "experimentId": "extended-codex-gpt-6-sol-low-batch10-fresh3-p0", "parentBaselineId": "extended-codex-gpt-6-sol-low-batch10-fresh3-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh3", "model": "gpt-6-sol", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 380.8126332089596, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 66277, "output": 2531, "cachedInput": 14336, "cacheWrite": 0, "reasoning": 491, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-6-sol-low-batch10/fresh3/P1" }, { "id": "extended-codex-gpt-6-sol-low-batch10-fresh3-p2", "experimentId": "extended-codex-gpt-6-sol-low-batch10-fresh3-p0", "parentBaselineId": "extended-codex-gpt-6-sol-low-batch10-fresh3-p0", "protocolId": "report-only-codex-fresh-repeats-v1", "repeatPass": "fresh3", "model": "gpt-6-sol", "effort": "low", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 57, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_batch_duration_not_pure_inference", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 352.0880390430102, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 71689, "output": 2523, "cachedInput": 21504, "cacheWrite": 0, "reasoning": 487, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable monetary cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceRecordSha256": "335d7676d2d81e2a9eb258d34acdc808a428a3faff2adaedde904ccdcf5631dd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/codex-fresh-repeats.json", "sourceFamily": "codex-fresh-repeats", "sourceStage": "codex-gpt-6-sol-low-batch10/fresh3/P2" }, { "id": "extended-codex-gpt-6-sol-medium-batch10-repeat2-p0", "experimentId": "extended-codex-gpt-6-sol-medium-batch10-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-6-sol", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 289.85565858300833, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 63709, "output": 3216, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1174, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-sol-medium-batch10/repeat2/P0" }, { "id": "extended-codex-gpt-6-sol-medium-batch10-repeat2-p1", "experimentId": "extended-codex-gpt-6-sol-medium-batch10-repeat2-p0", "parentBaselineId": "extended-codex-gpt-6-sol-medium-batch10-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-6-sol", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 197.83112316500046, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 64735, "output": 3036, "cachedInput": 0, "cacheWrite": 0, "reasoning": 994, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-sol-medium-batch10/repeat2/P1" }, { "id": "extended-codex-gpt-6-sol-medium-batch10-repeat2-p2", "experimentId": "extended-codex-gpt-6-sol-medium-batch10-repeat2-p0", "parentBaselineId": "extended-codex-gpt-6-sol-medium-batch10-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-6-sol", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 221.26119179198577, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 70149, "output": 3053, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1011, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-sol-medium-batch10/repeat2/P2" }, { "id": "extended-codex-gpt-6-sol-medium-batch10-repeat3-p0", "experimentId": "extended-codex-gpt-6-sol-medium-batch10-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-6-sol", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 185.9765575420024, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 63709, "output": 3108, "cachedInput": 21504, "cacheWrite": 0, "reasoning": 1068, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-sol-medium-batch10/repeat3/P0" }, { "id": "extended-codex-gpt-6-sol-medium-batch10-repeat3-p1", "experimentId": "extended-codex-gpt-6-sol-medium-batch10-repeat3-p0", "parentBaselineId": "extended-codex-gpt-6-sol-medium-batch10-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-6-sol", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 398.4270443750138, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 64745, "output": 3273, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1231, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-sol-medium-batch10/repeat3/P1" }, { "id": "extended-codex-gpt-6-sol-medium-batch10-repeat3-p2", "experimentId": "extended-codex-gpt-6-sol-medium-batch10-repeat3-p0", "parentBaselineId": "extended-codex-gpt-6-sol-medium-batch10-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-6-sol", "effort": "medium", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 468.1708225399925, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 70234, "output": 2914, "cachedInput": 25856, "cacheWrite": 0, "reasoning": 878, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-sol-medium-batch10/repeat3/P2" }, { "id": "extended-codex-gpt-6-sol-xhigh-batch10-repeat2-p0", "experimentId": "extended-codex-gpt-6-sol-xhigh-batch10-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-6-sol", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 385.7532482500246, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 65381, "output": 4577, "cachedInput": 7168, "cacheWrite": 0, "reasoning": 2537, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-sol-xhigh-batch10/repeat2/P0" }, { "id": "extended-codex-gpt-6-sol-xhigh-batch10-repeat2-p1", "experimentId": "extended-codex-gpt-6-sol-xhigh-batch10-repeat2-p0", "parentBaselineId": "extended-codex-gpt-6-sol-xhigh-batch10-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-6-sol", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 687.1528055850358, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 66421, "output": 4494, "cachedInput": 0, "cacheWrite": 0, "reasoning": 2454, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-sol-xhigh-batch10/repeat2/P1" }, { "id": "extended-codex-gpt-6-sol-xhigh-batch10-repeat2-p2", "experimentId": "extended-codex-gpt-6-sol-xhigh-batch10-repeat2-p0", "parentBaselineId": "extended-codex-gpt-6-sol-xhigh-batch10-repeat2-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat2", "model": "gpt-6-sol", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 827.5147366249585, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 71827, "output": 4377, "cachedInput": 0, "cacheWrite": 0, "reasoning": 2337, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-sol-xhigh-batch10/repeat2/P2" }, { "id": "extended-codex-gpt-6-sol-xhigh-batch10-repeat3-p0", "experimentId": "extended-codex-gpt-6-sol-xhigh-batch10-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-6-sol", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 1329.8350172490464, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 65379, "output": 4510, "cachedInput": 0, "cacheWrite": 0, "reasoning": 2468, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-sol-xhigh-batch10/repeat3/P0" }, { "id": "extended-codex-gpt-6-sol-xhigh-batch10-repeat3-p1", "experimentId": "extended-codex-gpt-6-sol-xhigh-batch10-repeat3-p0", "parentBaselineId": "extended-codex-gpt-6-sol-xhigh-batch10-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-6-sol", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 337.26026216801256, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 66403, "output": 4333, "cachedInput": 0, "cacheWrite": 0, "reasoning": 2293, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-sol-xhigh-batch10/repeat3/P1" }, { "id": "extended-codex-gpt-6-sol-xhigh-batch10-repeat3-p2", "experimentId": "extended-codex-gpt-6-sol-xhigh-batch10-repeat3-p0", "parentBaselineId": "extended-codex-gpt-6-sol-xhigh-batch10-repeat3-p0", "protocolId": "report-only-repeats-v1", "repeatPass": "repeat3", "model": "gpt-6-sol", "effort": "xhigh", "provider": null, "surface": "Codex CLI subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "reported", "timing": { "kind": "unavailable", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 598.9204292919894, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 71825, "output": 4754, "cachedInput": 14336, "cacheWrite": 0, "reasoning": 2712, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "ChatGPT subscription; attributable request cost unavailable." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceRecordSha256": "e6acc3e09d4a2d59042e08d268c64ab9ff5a9949810513547802965d3f447c4a", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/repeats.json", "sourceFamily": "repeats", "sourceStage": "codex-gpt-6-sol-xhigh-batch10/repeat3/P2" }, { "id": "extended-fable51-high-phase2-batch10-p0-repeat2-p0", "experimentId": "extended-fable51-high-phase2-batch10-p0-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-fable-5-1", "effort": "high", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 60, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 105.52943854202749, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 9044, "cachedInput": 19680, "cacheWrite": 6406, "reasoning": 5292, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.58536, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "fable51-high-phase2-batch10-p0/repeat2/P0" }, { "id": "extended-fable51-high-phase2-batch10-p0-repeat2-p1", "experimentId": "extended-fable51-high-phase2-batch10-p0-repeat2-p0", "parentBaselineId": "extended-fable51-high-phase2-batch10-p0-repeat2-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-fable-5-1", "effort": "high", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 127.35441720904782, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 8636, "cachedInput": 21486, "cacheWrite": 6401, "reasoning": 4888, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.5653115000000001, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "fable51-high-phase2-batch10-p0/repeat2/P1" }, { "id": "extended-fable51-high-phase2-batch10-p0-repeat2-p2", "experimentId": "extended-fable51-high-phase2-batch10-p0-repeat2-p0", "parentBaselineId": "extended-fable51-high-phase2-batch10-p0-repeat2-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-fable-5-1", "effort": "high", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 110.8427773330477, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 8784, "cachedInput": 31698, "cacheWrite": 6403, "reasoning": 5037, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.5753045, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "fable51-high-phase2-batch10-p0/repeat2/P2" }, { "id": "extended-fable51-high-phase2-batch10-p0-repeat3-p0", "experimentId": "extended-fable51-high-phase2-batch10-p0-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-fable-5-1", "effort": "high", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 100.15250229096273, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 9035, "cachedInput": 19680, "cacheWrite": 6399, "reasoning": 5287, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.58477, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "fable51-high-phase2-batch10-p0/repeat3/P0" }, { "id": "extended-fable51-high-phase2-batch10-p0-repeat3-p1", "experimentId": "extended-fable51-high-phase2-batch10-p0-repeat3-p0", "parentBaselineId": "extended-fable51-high-phase2-batch10-p0-repeat3-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-fable-5-1", "effort": "high", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 104.13212829100667, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 9246, "cachedInput": 21486, "cacheWrite": 6402, "reasoning": 5499, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.5958315000000001, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "fable51-high-phase2-batch10-p0/repeat3/P1" }, { "id": "extended-fable51-high-phase2-batch10-p0-repeat3-p2", "experimentId": "extended-fable51-high-phase2-batch10-p0-repeat3-p0", "parentBaselineId": "extended-fable51-high-phase2-batch10-p0-repeat3-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-fable-5-1", "effort": "high", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 102.31089337405865, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 8872, "cachedInput": 31698, "cacheWrite": 6400, "reasoning": 5125, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.5796445, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "fable51-high-phase2-batch10-p0/repeat3/P2" }, { "id": "extended-fable51-low-phase2-batch10-p0-repeat2-p0", "experimentId": "extended-fable51-low-phase2-batch10-p0-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-fable-5-1", "effort": "low", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 60, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 83.8562019590463, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 7157, "cachedInput": 4884, "cacheWrite": 21203, "reasoning": 3404, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.783251, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "fable51-low-phase2-batch10-p0/repeat2/P0" }, { "id": "extended-fable51-low-phase2-batch10-p0-repeat2-p1", "experimentId": "extended-fable51-low-phase2-batch10-p0-repeat2-p0", "parentBaselineId": "extended-fable51-low-phase2-batch10-p0-repeat2-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-fable-5-1", "effort": "low", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 178.21372504299507, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 10, "output": 4655, "cachedInput": 17905, "cacheWrite": 5362, "reasoning": 1536, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.3974915, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "fable51-low-phase2-batch10-p0/repeat2/P1" }, { "id": "extended-fable51-low-phase2-batch10-p0-repeat2-p2", "experimentId": "extended-fable51-low-phase2-batch10-p0-repeat2-p0", "parentBaselineId": "extended-fable51-low-phase2-batch10-p0-repeat2-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-fable-5-1", "effort": "low", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 55, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 76.24614487597137, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 6480, "cachedInput": 0, "cacheWrite": 38097, "reasoning": 2740, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 1.08606, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "fable51-low-phase2-batch10-p0/repeat2/P2" }, { "id": "extended-fable51-low-phase2-batch10-p0-repeat3-p0", "experimentId": "extended-fable51-low-phase2-batch10-p0-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-fable-5-1", "effort": "low", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 78.527532084001, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 6554, "cachedInput": 19680, "cacheWrite": 6406, "reasoning": 2807, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.46086000000000005, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "fable51-low-phase2-batch10-p0/repeat3/P0" }, { "id": "extended-fable51-low-phase2-batch10-p0-repeat3-p1", "experimentId": "extended-fable51-low-phase2-batch10-p0-repeat3-p0", "parentBaselineId": "extended-fable51-low-phase2-batch10-p0-repeat3-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-fable-5-1", "effort": "low", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 75.29302012498374, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 6419, "cachedInput": 21486, "cacheWrite": 6403, "reasoning": 2673, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.4545015, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "fable51-low-phase2-batch10-p0/repeat3/P1" }, { "id": "extended-fable51-low-phase2-batch10-p0-repeat3-p2", "experimentId": "extended-fable51-low-phase2-batch10-p0-repeat3-p0", "parentBaselineId": "extended-fable51-low-phase2-batch10-p0-repeat3-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-fable-5-1", "effort": "low", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 145.65620470797876, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 6700, "cachedInput": 31698, "cacheWrite": 6396, "reasoning": 2955, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.4709645, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "fable51-low-phase2-batch10-p0/repeat3/P2" }, { "id": "extended-fable51-medium-phase2-batch10-p0-repeat2-p0", "experimentId": "extended-fable51-medium-phase2-batch10-p0-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-fable-5-1", "effort": "medium", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 93.74261645798106, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 8091, "cachedInput": 19680, "cacheWrite": 6407, "reasoning": 4343, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.53773, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "fable51-medium-phase2-batch10-p0/repeat2/P0" }, { "id": "extended-fable51-medium-phase2-batch10-p0-repeat2-p1", "experimentId": "extended-fable51-medium-phase2-batch10-p0-repeat2-p0", "parentBaselineId": "extended-fable51-medium-phase2-batch10-p0-repeat2-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-fable-5-1", "effort": "medium", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 60, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 95.63367495697457, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 7659, "cachedInput": 4884, "cacheWrite": 23002, "reasoning": 3907, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.844331, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "fable51-medium-phase2-batch10-p0/repeat2/P1" }, { "id": "extended-fable51-medium-phase2-batch10-p0-repeat2-p2", "experimentId": "extended-fable51-medium-phase2-batch10-p0-repeat2-p0", "parentBaselineId": "extended-fable51-medium-phase2-batch10-p0-repeat2-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-fable-5-1", "effort": "medium", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 104.33667304302799, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 8639, "cachedInput": 31698, "cacheWrite": 6400, "reasoning": 4891, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.5679945, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "fable51-medium-phase2-batch10-p0/repeat2/P2" }, { "id": "extended-fable51-medium-phase2-batch10-p0-repeat3-p0", "experimentId": "extended-fable51-medium-phase2-batch10-p0-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-fable-5-1", "effort": "medium", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 60, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 161.66721025001607, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 7744, "cachedInput": 19680, "cacheWrite": 6406, "reasoning": 3992, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.52036, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "fable51-medium-phase2-batch10-p0/repeat3/P0" }, { "id": "extended-fable51-medium-phase2-batch10-p0-repeat3-p1", "experimentId": "extended-fable51-medium-phase2-batch10-p0-repeat3-p0", "parentBaselineId": "extended-fable51-medium-phase2-batch10-p0-repeat3-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-fable-5-1", "effort": "medium", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 179.21269300102722, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 7959, "cachedInput": 21486, "cacheWrite": 6396, "reasoning": 4212, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.5313615, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "fable51-medium-phase2-batch10-p0/repeat3/P1" }, { "id": "extended-fable51-medium-phase2-batch10-p0-repeat3-p2", "experimentId": "extended-fable51-medium-phase2-batch10-p0-repeat3-p0", "parentBaselineId": "extended-fable51-medium-phase2-batch10-p0-repeat3-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-fable-5-1", "effort": "medium", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 100.64046974899247, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 8217, "cachedInput": 31698, "cacheWrite": 6398, "reasoning": 4468, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.5468545, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "fable51-medium-phase2-batch10-p0/repeat3/P2" }, { "id": "extended-fable51-xhigh-phase2-batch10-p0-repeat2-p0", "experimentId": "extended-fable51-xhigh-phase2-batch10-p0-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-fable-5-1", "effort": "xhigh", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 175.95319433303666, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 16774, "cachedInput": 19680, "cacheWrite": 6408, "reasoning": 13026, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.9718999999999999, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "fable51-xhigh-phase2-batch10-p0/repeat2/P0" }, { "id": "extended-fable51-xhigh-phase2-batch10-p0-repeat2-p1", "experimentId": "extended-fable51-xhigh-phase2-batch10-p0-repeat2-p0", "parentBaselineId": "extended-fable51-xhigh-phase2-batch10-p0-repeat2-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-fable-5-1", "effort": "xhigh", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 167.33343474802678, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 15630, "cachedInput": 21486, "cacheWrite": 6399, "reasoning": 11882, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.9149714999999999, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "fable51-xhigh-phase2-batch10-p0/repeat2/P1" }, { "id": "extended-fable51-xhigh-phase2-batch10-p0-repeat2-p2", "experimentId": "extended-fable51-xhigh-phase2-batch10-p0-repeat2-p0", "parentBaselineId": "extended-fable51-xhigh-phase2-batch10-p0-repeat2-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-fable-5-1", "effort": "xhigh", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 186.41871399895172, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 16395, "cachedInput": 31698, "cacheWrite": 6398, "reasoning": 12656, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.9557545, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "fable51-xhigh-phase2-batch10-p0/repeat2/P2" }, { "id": "extended-fable51-xhigh-phase2-batch10-p0-repeat3-p0", "experimentId": "extended-fable51-xhigh-phase2-batch10-p0-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-fable-5-1", "effort": "xhigh", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 204.09926537505817, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 18227, "cachedInput": 19680, "cacheWrite": 6407, "reasoning": 14480, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 1.04453, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "fable51-xhigh-phase2-batch10-p0/repeat3/P0" }, { "id": "extended-fable51-xhigh-phase2-batch10-p0-repeat3-p1", "experimentId": "extended-fable51-xhigh-phase2-batch10-p0-repeat3-p0", "parentBaselineId": "extended-fable51-xhigh-phase2-batch10-p0-repeat3-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-fable-5-1", "effort": "xhigh", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 161.36850374899223, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 14753, "cachedInput": 21486, "cacheWrite": 6399, "reasoning": 11005, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.8711215, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "fable51-xhigh-phase2-batch10-p0/repeat3/P1" }, { "id": "extended-fable51-xhigh-phase2-batch10-p0-repeat3-p2", "experimentId": "extended-fable51-xhigh-phase2-batch10-p0-repeat3-p0", "parentBaselineId": "extended-fable51-xhigh-phase2-batch10-p0-repeat3-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-fable-5-1", "effort": "xhigh", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 156.87035045895027, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 14426, "cachedInput": 31698, "cacheWrite": 6398, "reasoning": 10683, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.8573045, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "fable51-xhigh-phase2-batch10-p0/repeat3/P2" }, { "id": "extended-gemini31-pro-preview-high-p0-openrouter-v3-repeat2-p0", "experimentId": "extended-gemini31-pro-preview-high-p0-openrouter-v3-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat2", "model": "google/gemini-3.1-pro-preview", "effort": "high", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 11227, "output": 22706, "cachedInput": 0, "cacheWrite": 0, "reasoning": 19446, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.294926, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini31-pro-preview-high-p0-openrouter-v3/repeat2/P0" }, { "id": "extended-gemini31-pro-preview-high-p0-openrouter-v3-repeat2-p1", "experimentId": "extended-gemini31-pro-preview-high-p0-openrouter-v3-repeat2-p0", "parentBaselineId": "extended-gemini31-pro-preview-high-p0-openrouter-v3-repeat2-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat2", "model": "google/gemini-3.1-pro-preview", "effort": "high", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12307, "output": 18677, "cachedInput": 0, "cacheWrite": 0, "reasoning": 15194, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.248738, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini31-pro-preview-high-p0-openrouter-v3/repeat2/P1" }, { "id": "extended-gemini31-pro-preview-high-p0-openrouter-v3-repeat2-p2", "experimentId": "extended-gemini31-pro-preview-high-p0-openrouter-v3-repeat2-p0", "parentBaselineId": "extended-gemini31-pro-preview-high-p0-openrouter-v3-repeat2-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat2", "model": "google/gemini-3.1-pro-preview", "effort": "high", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 57, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 17893, "output": 19234, "cachedInput": 0, "cacheWrite": 0, "reasoning": 15731, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.266594, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini31-pro-preview-high-p0-openrouter-v3/repeat2/P2" }, { "id": "extended-gemini31-pro-preview-high-p0-openrouter-v3-repeat3-p0", "experimentId": "extended-gemini31-pro-preview-high-p0-openrouter-v3-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat3", "model": "google/gemini-3.1-pro-preview", "effort": "high", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 11227, "output": 17209, "cachedInput": 0, "cacheWrite": 0, "reasoning": 13655, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.228962, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini31-pro-preview-high-p0-openrouter-v3/repeat3/P0" }, { "id": "extended-gemini31-pro-preview-high-p0-openrouter-v3-repeat3-p1", "experimentId": "extended-gemini31-pro-preview-high-p0-openrouter-v3-repeat3-p0", "parentBaselineId": "extended-gemini31-pro-preview-high-p0-openrouter-v3-repeat3-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat3", "model": "google/gemini-3.1-pro-preview", "effort": "high", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12307, "output": 17469, "cachedInput": 0, "cacheWrite": 0, "reasoning": 13915, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.234242, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini31-pro-preview-high-p0-openrouter-v3/repeat3/P1" }, { "id": "extended-gemini31-pro-preview-high-p0-openrouter-v3-repeat3-p2", "experimentId": "extended-gemini31-pro-preview-high-p0-openrouter-v3-repeat3-p0", "parentBaselineId": "extended-gemini31-pro-preview-high-p0-openrouter-v3-repeat3-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat3", "model": "google/gemini-3.1-pro-preview", "effort": "high", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 57, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 17893, "output": 19047, "cachedInput": 0, "cacheWrite": 0, "reasoning": 15448, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.26435, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini31-pro-preview-high-p0-openrouter-v3/repeat3/P2" }, { "id": "extended-gemini31-pro-preview-low-p0-openrouter-v3-repeat2-p0", "experimentId": "extended-gemini31-pro-preview-low-p0-openrouter-v3-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat2", "model": "google/gemini-3.1-pro-preview", "effort": "low", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 11227, "output": 5746, "cachedInput": 0, "cacheWrite": 0, "reasoning": 2597, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.091406, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini31-pro-preview-low-p0-openrouter-v3/repeat2/P0" }, { "id": "extended-gemini31-pro-preview-low-p0-openrouter-v3-repeat2-p1", "experimentId": "extended-gemini31-pro-preview-low-p0-openrouter-v3-repeat2-p0", "parentBaselineId": "extended-gemini31-pro-preview-low-p0-openrouter-v3-repeat2-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat2", "model": "google/gemini-3.1-pro-preview", "effort": "low", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12307, "output": 4608, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1197, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.07991, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini31-pro-preview-low-p0-openrouter-v3/repeat2/P1" }, { "id": "extended-gemini31-pro-preview-low-p0-openrouter-v3-repeat2-p2", "experimentId": "extended-gemini31-pro-preview-low-p0-openrouter-v3-repeat2-p0", "parentBaselineId": "extended-gemini31-pro-preview-low-p0-openrouter-v3-repeat2-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat2", "model": "google/gemini-3.1-pro-preview", "effort": "low", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 17893, "output": 3414, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.076754, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini31-pro-preview-low-p0-openrouter-v3/repeat2/P2" }, { "id": "extended-gemini31-pro-preview-low-p0-openrouter-v3-repeat3-p0", "experimentId": "extended-gemini31-pro-preview-low-p0-openrouter-v3-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat3", "model": "google/gemini-3.1-pro-preview", "effort": "low", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 11227, "output": 4855, "cachedInput": 0, "cacheWrite": 0, "reasoning": 1685, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.080714, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini31-pro-preview-low-p0-openrouter-v3/repeat3/P0" }, { "id": "extended-gemini31-pro-preview-low-p0-openrouter-v3-repeat3-p1", "experimentId": "extended-gemini31-pro-preview-low-p0-openrouter-v3-repeat3-p0", "parentBaselineId": "extended-gemini31-pro-preview-low-p0-openrouter-v3-repeat3-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat3", "model": "google/gemini-3.1-pro-preview", "effort": "low", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12307, "output": 5260, "cachedInput": 0, "cacheWrite": 0, "reasoning": 2355, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.087734, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini31-pro-preview-low-p0-openrouter-v3/repeat3/P1" }, { "id": "extended-gemini31-pro-preview-low-p0-openrouter-v3-repeat3-p2", "experimentId": "extended-gemini31-pro-preview-low-p0-openrouter-v3-repeat3-p0", "parentBaselineId": "extended-gemini31-pro-preview-low-p0-openrouter-v3-repeat3-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat3", "model": "google/gemini-3.1-pro-preview", "effort": "low", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 17893, "output": 3414, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.076754, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini31-pro-preview-low-p0-openrouter-v3/repeat3/P2" }, { "id": "extended-gemini36-flash-low-p0-openrouter-v3-repeat2-p0", "experimentId": "extended-gemini36-flash-low-p0-openrouter-v3-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat2", "model": "google/gemini-3.6-flash", "effort": "low", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 55, "sentiment": 57, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 11227, "output": 3411, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0212115, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini36-flash-low-p0-openrouter-v3/repeat2/P0" }, { "id": "extended-gemini36-flash-low-p0-openrouter-v3-repeat2-p1", "experimentId": "extended-gemini36-flash-low-p0-openrouter-v3-repeat2-p0", "parentBaselineId": "extended-gemini36-flash-low-p0-openrouter-v3-repeat2-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat2", "model": "google/gemini-3.6-flash", "effort": "low", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 54, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12307, "output": 2944, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.02027025, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini36-flash-low-p0-openrouter-v3/repeat2/P1" }, { "id": "extended-gemini36-flash-low-p0-openrouter-v3-repeat2-p2", "experimentId": "extended-gemini36-flash-low-p0-openrouter-v3-repeat2-p0", "parentBaselineId": "extended-gemini36-flash-low-p0-openrouter-v3-repeat2-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat2", "model": "google/gemini-3.6-flash", "effort": "low", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 17893, "output": 2188, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.02162475, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini36-flash-low-p0-openrouter-v3/repeat2/P2" }, { "id": "extended-gemini36-flash-low-p0-openrouter-v3-repeat3-p0", "experimentId": "extended-gemini36-flash-low-p0-openrouter-v3-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat3", "model": "google/gemini-3.6-flash", "effort": "low", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 54, "sentiment": 57, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 11227, "output": 2700, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.01854525, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini36-flash-low-p0-openrouter-v3/repeat3/P0" }, { "id": "extended-gemini36-flash-low-p0-openrouter-v3-repeat3-p1", "experimentId": "extended-gemini36-flash-low-p0-openrouter-v3-repeat3-p0", "parentBaselineId": "extended-gemini36-flash-low-p0-openrouter-v3-repeat3-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat3", "model": "google/gemini-3.6-flash", "effort": "low", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12307, "output": 2411, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0182715, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini36-flash-low-p0-openrouter-v3/repeat3/P1" }, { "id": "extended-gemini36-flash-low-p0-openrouter-v3-repeat3-p2", "experimentId": "extended-gemini36-flash-low-p0-openrouter-v3-repeat3-p0", "parentBaselineId": "extended-gemini36-flash-low-p0-openrouter-v3-repeat3-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat3", "model": "google/gemini-3.6-flash", "effort": "low", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 17893, "output": 2432, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.02253975, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini36-flash-low-p0-openrouter-v3/repeat3/P2" }, { "id": "extended-gemini36-flash-medium-p0-openrouter-v3-repeat2-p0", "experimentId": "extended-gemini36-flash-medium-p0-openrouter-v3-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat2", "model": "google/gemini-3.6-flash", "effort": "medium", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 55, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 11227, "output": 16467, "cachedInput": 0, "cacheWrite": 0, "reasoning": 14032, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0701715, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini36-flash-medium-p0-openrouter-v3/repeat2/P0" }, { "id": "extended-gemini36-flash-medium-p0-openrouter-v3-repeat2-p1", "experimentId": "extended-gemini36-flash-medium-p0-openrouter-v3-repeat2-p0", "parentBaselineId": "extended-gemini36-flash-medium-p0-openrouter-v3-repeat2-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat2", "model": "google/gemini-3.6-flash", "effort": "medium", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 55, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12307, "output": 14704, "cachedInput": 0, "cacheWrite": 0, "reasoning": 12468, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.06437025, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini36-flash-medium-p0-openrouter-v3/repeat2/P1" }, { "id": "extended-gemini36-flash-medium-p0-openrouter-v3-repeat2-p2", "experimentId": "extended-gemini36-flash-medium-p0-openrouter-v3-repeat2-p0", "parentBaselineId": "extended-gemini36-flash-medium-p0-openrouter-v3-repeat2-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat2", "model": "google/gemini-3.6-flash", "effort": "medium", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 17893, "output": 16266, "cachedInput": 0, "cacheWrite": 0, "reasoning": 13563, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.07441725, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini36-flash-medium-p0-openrouter-v3/repeat2/P2" }, { "id": "extended-gemini36-flash-medium-p0-openrouter-v3-repeat3-p0", "experimentId": "extended-gemini36-flash-medium-p0-openrouter-v3-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat3", "model": "google/gemini-3.6-flash", "effort": "medium", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 11227, "output": 18022, "cachedInput": 0, "cacheWrite": 0, "reasoning": 15539, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.07600275, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini36-flash-medium-p0-openrouter-v3/repeat3/P0" }, { "id": "extended-gemini36-flash-medium-p0-openrouter-v3-repeat3-p1", "experimentId": "extended-gemini36-flash-medium-p0-openrouter-v3-repeat3-p0", "parentBaselineId": "extended-gemini36-flash-medium-p0-openrouter-v3-repeat3-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat3", "model": "google/gemini-3.6-flash", "effort": "medium", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 55, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12307, "output": 15563, "cachedInput": 0, "cacheWrite": 0, "reasoning": 13131, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0675915, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini36-flash-medium-p0-openrouter-v3/repeat3/P1" }, { "id": "extended-gemini36-flash-medium-p0-openrouter-v3-repeat3-p2", "experimentId": "extended-gemini36-flash-medium-p0-openrouter-v3-repeat3-p0", "parentBaselineId": "extended-gemini36-flash-medium-p0-openrouter-v3-repeat3-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat3", "model": "google/gemini-3.6-flash", "effort": "medium", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 17893, "output": 16602, "cachedInput": 0, "cacheWrite": 0, "reasoning": 14655, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.07567725, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini36-flash-medium-p0-openrouter-v3/repeat3/P2" }, { "id": "extended-gemini37-flash-high-p0-openrouter-v3-repeat2-p0", "experimentId": "extended-gemini37-flash-high-p0-openrouter-v3-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat2", "model": "google/gemini-3.7-flash", "effort": "high", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 58, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 11227, "output": 27635, "cachedInput": 0, "cacheWrite": 0, "reasoning": 25178, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.1120515, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini37-flash-high-p0-openrouter-v3/repeat2/P0" }, { "id": "extended-gemini37-flash-high-p0-openrouter-v3-repeat2-p1", "experimentId": "extended-gemini37-flash-high-p0-openrouter-v3-repeat2-p0", "parentBaselineId": "extended-gemini37-flash-high-p0-openrouter-v3-repeat2-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat2", "model": "google/gemini-3.7-flash", "effort": "high", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12307, "output": 26176, "cachedInput": 0, "cacheWrite": 0, "reasoning": 23229, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.10739025, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini37-flash-high-p0-openrouter-v3/repeat2/P1" }, { "id": "extended-gemini37-flash-high-p0-openrouter-v3-repeat2-p2", "experimentId": "extended-gemini37-flash-high-p0-openrouter-v3-repeat2-p0", "parentBaselineId": "extended-gemini37-flash-high-p0-openrouter-v3-repeat2-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat2", "model": "google/gemini-3.7-flash", "effort": "high", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 59, "follow_up_needed": 58, "serious_concern_reported": 58, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 17893, "output": 24669, "cachedInput": 0, "cacheWrite": 0, "reasoning": 21408, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.1059285, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini37-flash-high-p0-openrouter-v3/repeat2/P2" }, { "id": "extended-gemini37-flash-high-p0-openrouter-v3-repeat3-p0", "experimentId": "extended-gemini37-flash-high-p0-openrouter-v3-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat3", "model": "google/gemini-3.7-flash", "effort": "high", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 50, "metrics": { "all_four": 47, "sentiment": 49, "follow_up_needed": 49, "serious_concern_reported": 49, "testimonial_potential": 49 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 11227, "output": 26821, "cachedInput": 0, "cacheWrite": 0, "reasoning": 24122, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.108999, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini37-flash-high-p0-openrouter-v3/repeat3/P0" }, { "id": "extended-gemini37-flash-high-p0-openrouter-v3-repeat3-p1", "experimentId": "extended-gemini37-flash-high-p0-openrouter-v3-repeat3-p0", "parentBaselineId": "extended-gemini37-flash-high-p0-openrouter-v3-repeat3-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat3", "model": "google/gemini-3.7-flash", "effort": "high", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 50, "metrics": { "all_four": 47, "sentiment": 49, "follow_up_needed": 49, "serious_concern_reported": 49, "testimonial_potential": 49 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12307, "output": 29579, "cachedInput": 0, "cacheWrite": 0, "reasoning": 26902, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.1201515, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini37-flash-high-p0-openrouter-v3/repeat3/P1" }, { "id": "extended-gemini37-flash-high-p0-openrouter-v3-repeat3-p2", "experimentId": "extended-gemini37-flash-high-p0-openrouter-v3-repeat3-p0", "parentBaselineId": "extended-gemini37-flash-high-p0-openrouter-v3-repeat3-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat3", "model": "google/gemini-3.7-flash", "effort": "high", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 50, "metrics": { "all_four": 47, "sentiment": 49, "follow_up_needed": 49, "serious_concern_reported": 48, "testimonial_potential": 49 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 17893, "output": 27769, "cachedInput": 0, "cacheWrite": 0, "reasoning": 25360, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.1175535, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini37-flash-high-p0-openrouter-v3/repeat3/P2" }, { "id": "extended-gemini37-flash-low-p0-openrouter-v3-repeat2-p0", "experimentId": "extended-gemini37-flash-low-p0-openrouter-v3-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat2", "model": "google/gemini-3.7-flash", "effort": "low", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 11227, "output": 3510, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.02158275, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini37-flash-low-p0-openrouter-v3/repeat2/P0" }, { "id": "extended-gemini37-flash-low-p0-openrouter-v3-repeat2-p1", "experimentId": "extended-gemini37-flash-low-p0-openrouter-v3-repeat2-p0", "parentBaselineId": "extended-gemini37-flash-low-p0-openrouter-v3-repeat2-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat2", "model": "google/gemini-3.7-flash", "effort": "low", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12307, "output": 3263, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0214665, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini37-flash-low-p0-openrouter-v3/repeat2/P1" }, { "id": "extended-gemini37-flash-low-p0-openrouter-v3-repeat2-p2", "experimentId": "extended-gemini37-flash-low-p0-openrouter-v3-repeat2-p0", "parentBaselineId": "extended-gemini37-flash-low-p0-openrouter-v3-repeat2-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat2", "model": "google/gemini-3.7-flash", "effort": "low", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 17893, "output": 3531, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.026661, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini37-flash-low-p0-openrouter-v3/repeat2/P2" }, { "id": "extended-gemini37-flash-low-p0-openrouter-v3-repeat3-p0", "experimentId": "extended-gemini37-flash-low-p0-openrouter-v3-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat3", "model": "google/gemini-3.7-flash", "effort": "low", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 57, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 11227, "output": 3555, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0217515, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini37-flash-low-p0-openrouter-v3/repeat3/P0" }, { "id": "extended-gemini37-flash-low-p0-openrouter-v3-repeat3-p1", "experimentId": "extended-gemini37-flash-low-p0-openrouter-v3-repeat3-p0", "parentBaselineId": "extended-gemini37-flash-low-p0-openrouter-v3-repeat3-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat3", "model": "google/gemini-3.7-flash", "effort": "low", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 60, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12307, "output": 3534, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.02248275, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini37-flash-low-p0-openrouter-v3/repeat3/P1" }, { "id": "extended-gemini37-flash-low-p0-openrouter-v3-repeat3-p2", "experimentId": "extended-gemini37-flash-low-p0-openrouter-v3-repeat3-p0", "parentBaselineId": "extended-gemini37-flash-low-p0-openrouter-v3-repeat3-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat3", "model": "google/gemini-3.7-flash", "effort": "low", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 17893, "output": 3483, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.026481, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini37-flash-low-p0-openrouter-v3/repeat3/P2" }, { "id": "extended-gemini37-flash-medium-p0-openrouter-v3-repeat2-p0", "experimentId": "extended-gemini37-flash-medium-p0-openrouter-v3-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat2", "model": "google/gemini-3.7-flash", "effort": "medium", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 11227, "output": 12754, "cachedInput": 0, "cacheWrite": 0, "reasoning": 9271, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.05624775, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini37-flash-medium-p0-openrouter-v3/repeat2/P0" }, { "id": "extended-gemini37-flash-medium-p0-openrouter-v3-repeat2-p1", "experimentId": "extended-gemini37-flash-medium-p0-openrouter-v3-repeat2-p0", "parentBaselineId": "extended-gemini37-flash-medium-p0-openrouter-v3-repeat2-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat2", "model": "google/gemini-3.7-flash", "effort": "medium", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12307, "output": 12933, "cachedInput": 0, "cacheWrite": 0, "reasoning": 9477, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.057729, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini37-flash-medium-p0-openrouter-v3/repeat2/P1" }, { "id": "extended-gemini37-flash-medium-p0-openrouter-v3-repeat2-p2", "experimentId": "extended-gemini37-flash-medium-p0-openrouter-v3-repeat2-p0", "parentBaselineId": "extended-gemini37-flash-medium-p0-openrouter-v3-repeat2-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat2", "model": "google/gemini-3.7-flash", "effort": "medium", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 17893, "output": 11866, "cachedInput": 0, "cacheWrite": 0, "reasoning": 8338, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.05791725, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini37-flash-medium-p0-openrouter-v3/repeat2/P2" }, { "id": "extended-gemini37-flash-medium-p0-openrouter-v3-repeat3-p0", "experimentId": "extended-gemini37-flash-medium-p0-openrouter-v3-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat3", "model": "google/gemini-3.7-flash", "effort": "medium", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 11227, "output": 14656, "cachedInput": 0, "cacheWrite": 0, "reasoning": 11438, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.06338025, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini37-flash-medium-p0-openrouter-v3/repeat3/P0" }, { "id": "extended-gemini37-flash-medium-p0-openrouter-v3-repeat3-p1", "experimentId": "extended-gemini37-flash-medium-p0-openrouter-v3-repeat3-p0", "parentBaselineId": "extended-gemini37-flash-medium-p0-openrouter-v3-repeat3-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat3", "model": "google/gemini-3.7-flash", "effort": "medium", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12307, "output": 12767, "cachedInput": 0, "cacheWrite": 0, "reasoning": 9263, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0571065, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini37-flash-medium-p0-openrouter-v3/repeat3/P1" }, { "id": "extended-gemini37-flash-medium-p0-openrouter-v3-repeat3-p2", "experimentId": "extended-gemini37-flash-medium-p0-openrouter-v3-repeat3-p0", "parentBaselineId": "extended-gemini37-flash-medium-p0-openrouter-v3-repeat3-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat3", "model": "google/gemini-3.7-flash", "effort": "medium", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 58, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 17893, "output": 13270, "cachedInput": 0, "cacheWrite": 0, "reasoning": 9760, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.06318225, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini37-flash-medium-p0-openrouter-v3/repeat3/P2" }, { "id": "extended-gemini38-flash-medium-p0-openrouter-v3-repeat2-p0", "experimentId": "extended-gemini38-flash-medium-p0-openrouter-v3-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat2", "model": "google/gemini-3.8-flash", "effort": "medium", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 11227, "output": 19774, "cachedInput": 0, "cacheWrite": 0, "reasoning": 16511, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.08257275, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini38-flash-medium-p0-openrouter-v3/repeat2/P0" }, { "id": "extended-gemini38-flash-medium-p0-openrouter-v3-repeat2-p1", "experimentId": "extended-gemini38-flash-medium-p0-openrouter-v3-repeat2-p0", "parentBaselineId": "extended-gemini38-flash-medium-p0-openrouter-v3-repeat2-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat2", "model": "google/gemini-3.8-flash", "effort": "medium", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 50, "metrics": { "all_four": 47, "sentiment": 49, "follow_up_needed": 49, "serious_concern_reported": 48, "testimonial_potential": 49 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12307, "output": 20227, "cachedInput": 0, "cacheWrite": 0, "reasoning": 17064, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0850815, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini38-flash-medium-p0-openrouter-v3/repeat2/P1" }, { "id": "extended-gemini38-flash-medium-p0-openrouter-v3-repeat2-p2", "experimentId": "extended-gemini38-flash-medium-p0-openrouter-v3-repeat2-p0", "parentBaselineId": "extended-gemini38-flash-medium-p0-openrouter-v3-repeat2-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat2", "model": "google/gemini-3.8-flash", "effort": "medium", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 17893, "output": 22374, "cachedInput": 0, "cacheWrite": 0, "reasoning": 18891, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.09732225, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini38-flash-medium-p0-openrouter-v3/repeat2/P2" }, { "id": "extended-gemini38-flash-medium-p0-openrouter-v3-repeat3-p0", "experimentId": "extended-gemini38-flash-medium-p0-openrouter-v3-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat3", "model": "google/gemini-3.8-flash", "effort": "medium", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 50, "metrics": { "all_four": 47, "sentiment": 49, "follow_up_needed": 49, "serious_concern_reported": 48, "testimonial_potential": 49 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 11227, "output": 21564, "cachedInput": 0, "cacheWrite": 0, "reasoning": 18376, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.08928525, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini38-flash-medium-p0-openrouter-v3/repeat3/P0" }, { "id": "extended-gemini38-flash-medium-p0-openrouter-v3-repeat3-p1", "experimentId": "extended-gemini38-flash-medium-p0-openrouter-v3-repeat3-p0", "parentBaselineId": "extended-gemini38-flash-medium-p0-openrouter-v3-repeat3-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat3", "model": "google/gemini-3.8-flash", "effort": "medium", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 55, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12307, "output": 16444, "cachedInput": 0, "cacheWrite": 0, "reasoning": 13524, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.07089525, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini38-flash-medium-p0-openrouter-v3/repeat3/P1" }, { "id": "extended-gemini38-flash-medium-p0-openrouter-v3-repeat3-p2", "experimentId": "extended-gemini38-flash-medium-p0-openrouter-v3-repeat3-p0", "parentBaselineId": "extended-gemini38-flash-medium-p0-openrouter-v3-repeat3-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat3", "model": "google/gemini-3.8-flash", "effort": "medium", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 60, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 17893, "output": 18069, "cachedInput": 0, "cacheWrite": 0, "reasoning": 15124, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0811785, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini38-flash-medium-p0-openrouter-v3/repeat3/P2" }, { "id": "extended-gemini38-low-p0-openrouter-v2-repeat2-p0", "experimentId": "extended-gemini38-low-p0-openrouter-v2-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat2", "model": "google/gemini-3.8-flash", "effort": "low", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 11227, "output": 3459, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0213915, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini38-low-p0-openrouter-v2/repeat2/P0" }, { "id": "extended-gemini38-low-p0-openrouter-v2-repeat2-p1", "experimentId": "extended-gemini38-low-p0-openrouter-v2-repeat2-p0", "parentBaselineId": "extended-gemini38-low-p0-openrouter-v2-repeat2-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat2", "model": "google/gemini-3.8-flash", "effort": "low", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12307, "output": 3507, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0223815, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini38-low-p0-openrouter-v2/repeat2/P1" }, { "id": "extended-gemini38-low-p0-openrouter-v2-repeat2-p2", "experimentId": "extended-gemini38-low-p0-openrouter-v2-repeat2-p0", "parentBaselineId": "extended-gemini38-low-p0-openrouter-v2-repeat2-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat2", "model": "google/gemini-3.8-flash", "effort": "low", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 55, "sentiment": 57, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 17893, "output": 3483, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.026481, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini38-low-p0-openrouter-v2/repeat2/P2" }, { "id": "extended-gemini38-low-p0-openrouter-v2-repeat3-p0", "experimentId": "extended-gemini38-low-p0-openrouter-v2-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat3", "model": "google/gemini-3.8-flash", "effort": "low", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 11227, "output": 3510, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.02158275, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini38-low-p0-openrouter-v2/repeat3/P0" }, { "id": "extended-gemini38-low-p0-openrouter-v2-repeat3-p1", "experimentId": "extended-gemini38-low-p0-openrouter-v2-repeat3-p0", "parentBaselineId": "extended-gemini38-low-p0-openrouter-v2-repeat3-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat3", "model": "google/gemini-3.8-flash", "effort": "low", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12307, "output": 3486, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.02230275, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini38-low-p0-openrouter-v2/repeat3/P1" }, { "id": "extended-gemini38-low-p0-openrouter-v2-repeat3-p2", "experimentId": "extended-gemini38-low-p0-openrouter-v2-repeat3-p0", "parentBaselineId": "extended-gemini38-low-p0-openrouter-v2-repeat3-p0", "protocolId": "report-only-gemini-repeats-v1", "repeatPass": "repeat3", "model": "google/gemini-3.8-flash", "effort": "low", "provider": "google-ai-studio", "surface": "Google AI Studio", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 57, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock_if_recorded", "requests": 0, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 17893, "output": 3411, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.026211, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceRecordSha256": "760f24fd7cb79318db54f52f1dcca43243461e9a7c32d0aba2db209348f2b4b2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemini-repeats.json", "sourceFamily": "gemini-repeats", "sourceStage": "gemini38-low-p0-openrouter-v2/repeat3/P2" }, { "id": "extended-gemma4-e2b-sdk-thinking-off-fresh1-p0", "experimentId": "extended-gemma4-e2b-sdk-thinking-off-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-small-local-repeats-v1", "repeatPass": "fresh1", "model": "gemma4-e2b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 35, "sentiment": 52, "follow_up_needed": 58, "serious_concern_reported": 42, "testimonial_potential": 54 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 45.733552087, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 97768, "output": 2098, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceRecordSha256": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceFamily": "small-local-repeats", "sourceStage": "gemma4-e2b-sdk-thinking-off/fresh1/P0" }, { "id": "extended-gemma4-e2b-sdk-thinking-off-fresh1-p1", "experimentId": "extended-gemma4-e2b-sdk-thinking-off-fresh1-p0", "parentBaselineId": "extended-gemma4-e2b-sdk-thinking-off-fresh1-p0", "protocolId": "report-only-small-local-repeats-v1", "repeatPass": "fresh1", "model": "gemma4-e2b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 34, "sentiment": 52, "follow_up_needed": 58, "serious_concern_reported": 43, "testimonial_potential": 49 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 44.504048039, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 108568, "output": 2079, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceRecordSha256": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceFamily": "small-local-repeats", "sourceStage": "gemma4-e2b-sdk-thinking-off/fresh1/P1" }, { "id": "extended-gemma4-e2b-sdk-thinking-off-fresh1-p2", "experimentId": "extended-gemma4-e2b-sdk-thinking-off-fresh1-p0", "parentBaselineId": "extended-gemma4-e2b-sdk-thinking-off-fresh1-p0", "protocolId": "report-only-small-local-repeats-v1", "repeatPass": "fresh1", "model": "gemma4-e2b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 31, "sentiment": 49, "follow_up_needed": 59, "serious_concern_reported": 42, "testimonial_potential": 48 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 55.216797368, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 164428, "output": 2089, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceRecordSha256": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceFamily": "small-local-repeats", "sourceStage": "gemma4-e2b-sdk-thinking-off/fresh1/P2" }, { "id": "extended-gemma4-e2b-sdk-thinking-off-fresh2-p0", "experimentId": "extended-gemma4-e2b-sdk-thinking-off-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-small-local-repeats-v1", "repeatPass": "fresh2", "model": "gemma4-e2b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 35, "sentiment": 51, "follow_up_needed": 59, "serious_concern_reported": 43, "testimonial_potential": 51 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 145.681622243, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 97768, "output": 2098, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceRecordSha256": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceFamily": "small-local-repeats", "sourceStage": "gemma4-e2b-sdk-thinking-off/fresh2/P0" }, { "id": "extended-gemma4-e2b-sdk-thinking-off-fresh2-p1", "experimentId": "extended-gemma4-e2b-sdk-thinking-off-fresh2-p0", "parentBaselineId": "extended-gemma4-e2b-sdk-thinking-off-fresh2-p0", "protocolId": "report-only-small-local-repeats-v1", "repeatPass": "fresh2", "model": "gemma4-e2b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 33, "sentiment": 52, "follow_up_needed": 59, "serious_concern_reported": 41, "testimonial_potential": 50 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 144.111364791, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 108568, "output": 2090, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceRecordSha256": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceFamily": "small-local-repeats", "sourceStage": "gemma4-e2b-sdk-thinking-off/fresh2/P1" }, { "id": "extended-gemma4-e2b-sdk-thinking-off-fresh2-p2", "experimentId": "extended-gemma4-e2b-sdk-thinking-off-fresh2-p0", "parentBaselineId": "extended-gemma4-e2b-sdk-thinking-off-fresh2-p0", "protocolId": "report-only-small-local-repeats-v1", "repeatPass": "fresh2", "model": "gemma4-e2b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 31, "sentiment": 48, "follow_up_needed": 59, "serious_concern_reported": 43, "testimonial_potential": 46 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 147.887888547, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 164428, "output": 2111, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceRecordSha256": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceFamily": "small-local-repeats", "sourceStage": "gemma4-e2b-sdk-thinking-off/fresh2/P2" }, { "id": "extended-gemma4-e2b-sdk-thinking-off-fresh3-p0", "experimentId": "extended-gemma4-e2b-sdk-thinking-off-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-small-local-repeats-v1", "repeatPass": "fresh3", "model": "gemma4-e2b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 35, "sentiment": 51, "follow_up_needed": 59, "serious_concern_reported": 42, "testimonial_potential": 52 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 138.260153123, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 97768, "output": 2094, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceRecordSha256": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceFamily": "small-local-repeats", "sourceStage": "gemma4-e2b-sdk-thinking-off/fresh3/P0" }, { "id": "extended-gemma4-e2b-sdk-thinking-off-fresh3-p1", "experimentId": "extended-gemma4-e2b-sdk-thinking-off-fresh3-p0", "parentBaselineId": "extended-gemma4-e2b-sdk-thinking-off-fresh3-p0", "protocolId": "report-only-small-local-repeats-v1", "repeatPass": "fresh3", "model": "gemma4-e2b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 33, "sentiment": 52, "follow_up_needed": 59, "serious_concern_reported": 41, "testimonial_potential": 50 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 143.778118588, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 108568, "output": 2069, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceRecordSha256": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceFamily": "small-local-repeats", "sourceStage": "gemma4-e2b-sdk-thinking-off/fresh3/P1" }, { "id": "extended-gemma4-e2b-sdk-thinking-off-fresh3-p2", "experimentId": "extended-gemma4-e2b-sdk-thinking-off-fresh3-p0", "parentBaselineId": "extended-gemma4-e2b-sdk-thinking-off-fresh3-p0", "protocolId": "report-only-small-local-repeats-v1", "repeatPass": "fresh3", "model": "gemma4-e2b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 33, "sentiment": 50, "follow_up_needed": 59, "serious_concern_reported": 42, "testimonial_potential": 49 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 154.737154958, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 164428, "output": 2060, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceRecordSha256": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceFamily": "small-local-repeats", "sourceStage": "gemma4-e2b-sdk-thinking-off/fresh3/P2" }, { "id": "extended-gemma4-e2b-sdk-thinking-on-fresh1-p0", "experimentId": "extended-gemma4-e2b-sdk-thinking-on-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-small-local-repeats-v1", "repeatPass": "fresh1", "model": "gemma4-e2b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 38, "sentiment": 51, "follow_up_needed": 57, "serious_concern_reported": 47, "testimonial_potential": 55 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 512.938161627, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 97888, "output": 31407, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceRecordSha256": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceFamily": "small-local-repeats", "sourceStage": "gemma4-e2b-sdk-thinking-on/fresh1/P0" }, { "id": "extended-gemma4-e2b-sdk-thinking-on-fresh1-p1", "experimentId": "extended-gemma4-e2b-sdk-thinking-on-fresh1-p0", "parentBaselineId": "extended-gemma4-e2b-sdk-thinking-on-fresh1-p0", "protocolId": "report-only-small-local-repeats-v1", "repeatPass": "fresh1", "model": "gemma4-e2b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 36, "sentiment": 48, "follow_up_needed": 56, "serious_concern_reported": 47, "testimonial_potential": 54 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 466.737175578, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 108688, "output": 28999, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceRecordSha256": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceFamily": "small-local-repeats", "sourceStage": "gemma4-e2b-sdk-thinking-on/fresh1/P1" }, { "id": "extended-gemma4-e2b-sdk-thinking-on-fresh1-p2", "experimentId": "extended-gemma4-e2b-sdk-thinking-on-fresh1-p0", "parentBaselineId": "extended-gemma4-e2b-sdk-thinking-on-fresh1-p0", "protocolId": "report-only-small-local-repeats-v1", "repeatPass": "fresh1", "model": "gemma4-e2b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 36, "sentiment": 46, "follow_up_needed": 56, "serious_concern_reported": 50, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 494.035487331, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 164548, "output": 30423, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceRecordSha256": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceFamily": "small-local-repeats", "sourceStage": "gemma4-e2b-sdk-thinking-on/fresh1/P2" }, { "id": "extended-gemma4-e2b-sdk-thinking-on-fresh2-p0", "experimentId": "extended-gemma4-e2b-sdk-thinking-on-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-small-local-repeats-v1", "repeatPass": "fresh2", "model": "gemma4-e2b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 37, "sentiment": 52, "follow_up_needed": 58, "serious_concern_reported": 48, "testimonial_potential": 52 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 616.924675579, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 97888, "output": 30393, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceRecordSha256": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceFamily": "small-local-repeats", "sourceStage": "gemma4-e2b-sdk-thinking-on/fresh2/P0" }, { "id": "extended-gemma4-e2b-sdk-thinking-on-fresh2-p1", "experimentId": "extended-gemma4-e2b-sdk-thinking-on-fresh2-p0", "parentBaselineId": "extended-gemma4-e2b-sdk-thinking-on-fresh2-p0", "protocolId": "report-only-small-local-repeats-v1", "repeatPass": "fresh2", "model": "gemma4-e2b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 39, "sentiment": 54, "follow_up_needed": 57, "serious_concern_reported": 48, "testimonial_potential": 54 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 549.162846246, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 108688, "output": 29627, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceRecordSha256": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceFamily": "small-local-repeats", "sourceStage": "gemma4-e2b-sdk-thinking-on/fresh2/P1" }, { "id": "extended-gemma4-e2b-sdk-thinking-on-fresh2-p2", "experimentId": "extended-gemma4-e2b-sdk-thinking-on-fresh2-p0", "parentBaselineId": "extended-gemma4-e2b-sdk-thinking-on-fresh2-p0", "protocolId": "report-only-small-local-repeats-v1", "repeatPass": "fresh2", "model": "gemma4-e2b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 36, "sentiment": 46, "follow_up_needed": 58, "serious_concern_reported": 48, "testimonial_potential": 53 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 709.570663495, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 164548, "output": 30093, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceRecordSha256": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceFamily": "small-local-repeats", "sourceStage": "gemma4-e2b-sdk-thinking-on/fresh2/P2" }, { "id": "extended-gemma4-e2b-sdk-thinking-on-fresh3-p0", "experimentId": "extended-gemma4-e2b-sdk-thinking-on-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-small-local-repeats-v1", "repeatPass": "fresh3", "model": "gemma4-e2b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 39, "sentiment": 51, "follow_up_needed": 58, "serious_concern_reported": 48, "testimonial_potential": 54 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 655.731769376, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 97888, "output": 30605, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceRecordSha256": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceFamily": "small-local-repeats", "sourceStage": "gemma4-e2b-sdk-thinking-on/fresh3/P0" }, { "id": "extended-gemma4-e2b-sdk-thinking-on-fresh3-p1", "experimentId": "extended-gemma4-e2b-sdk-thinking-on-fresh3-p0", "parentBaselineId": "extended-gemma4-e2b-sdk-thinking-on-fresh3-p0", "protocolId": "report-only-small-local-repeats-v1", "repeatPass": "fresh3", "model": "gemma4-e2b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 39, "sentiment": 51, "follow_up_needed": 57, "serious_concern_reported": 48, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 686.908655958, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 108688, "output": 29425, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceRecordSha256": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceFamily": "small-local-repeats", "sourceStage": "gemma4-e2b-sdk-thinking-on/fresh3/P1" }, { "id": "extended-gemma4-e2b-sdk-thinking-on-fresh3-p2", "experimentId": "extended-gemma4-e2b-sdk-thinking-on-fresh3-p0", "parentBaselineId": "extended-gemma4-e2b-sdk-thinking-on-fresh3-p0", "protocolId": "report-only-small-local-repeats-v1", "repeatPass": "fresh3", "model": "gemma4-e2b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 35, "sentiment": 48, "follow_up_needed": 56, "serious_concern_reported": 48, "testimonial_potential": 55 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 629.703974253, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 164548, "output": 30450, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceRecordSha256": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceFamily": "small-local-repeats", "sourceStage": "gemma4-e2b-sdk-thinking-on/fresh3/P2" }, { "id": "extended-gemma4-e4b-sdk-thinking-off-fresh1-p0", "experimentId": "extended-gemma4-e4b-sdk-thinking-off-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-small-local-repeats-v1", "repeatPass": "fresh1", "model": "gemma4-e4b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 38, "sentiment": 46, "follow_up_needed": 58, "serious_concern_reported": 52, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 93.895898999, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 97768, "output": 2100, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceRecordSha256": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceFamily": "small-local-repeats", "sourceStage": "gemma4-e4b-sdk-thinking-off/fresh1/P0" }, { "id": "extended-gemma4-e4b-sdk-thinking-off-fresh1-p1", "experimentId": "extended-gemma4-e4b-sdk-thinking-off-fresh1-p0", "parentBaselineId": "extended-gemma4-e4b-sdk-thinking-off-fresh1-p0", "protocolId": "report-only-small-local-repeats-v1", "repeatPass": "fresh1", "model": "gemma4-e4b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 41, "sentiment": 48, "follow_up_needed": 58, "serious_concern_reported": 52, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 96.480132002, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 108568, "output": 2100, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceRecordSha256": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceFamily": "small-local-repeats", "sourceStage": "gemma4-e4b-sdk-thinking-off/fresh1/P1" }, { "id": "extended-gemma4-e4b-sdk-thinking-off-fresh1-p2", "experimentId": "extended-gemma4-e4b-sdk-thinking-off-fresh1-p0", "parentBaselineId": "extended-gemma4-e4b-sdk-thinking-off-fresh1-p0", "protocolId": "report-only-small-local-repeats-v1", "repeatPass": "fresh1", "model": "gemma4-e4b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 42, "sentiment": 48, "follow_up_needed": 58, "serious_concern_reported": 54, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 105.308259414, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 164428, "output": 2106, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceRecordSha256": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceFamily": "small-local-repeats", "sourceStage": "gemma4-e4b-sdk-thinking-off/fresh1/P2" }, { "id": "extended-gemma4-e4b-sdk-thinking-off-fresh2-p0", "experimentId": "extended-gemma4-e4b-sdk-thinking-off-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-small-local-repeats-v1", "repeatPass": "fresh2", "model": "gemma4-e4b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 40, "sentiment": 48, "follow_up_needed": 58, "serious_concern_reported": 52, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 98.804047122, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 97768, "output": 2100, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceRecordSha256": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceFamily": "small-local-repeats", "sourceStage": "gemma4-e4b-sdk-thinking-off/fresh2/P0" }, { "id": "extended-gemma4-e4b-sdk-thinking-off-fresh2-p1", "experimentId": "extended-gemma4-e4b-sdk-thinking-off-fresh2-p0", "parentBaselineId": "extended-gemma4-e4b-sdk-thinking-off-fresh2-p0", "protocolId": "report-only-small-local-repeats-v1", "repeatPass": "fresh2", "model": "gemma4-e4b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 40, "sentiment": 46, "follow_up_needed": 58, "serious_concern_reported": 52, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 95.540114667, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 108568, "output": 2100, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceRecordSha256": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceFamily": "small-local-repeats", "sourceStage": "gemma4-e4b-sdk-thinking-off/fresh2/P1" }, { "id": "extended-gemma4-e4b-sdk-thinking-off-fresh2-p2", "experimentId": "extended-gemma4-e4b-sdk-thinking-off-fresh2-p0", "parentBaselineId": "extended-gemma4-e4b-sdk-thinking-off-fresh2-p0", "protocolId": "report-only-small-local-repeats-v1", "repeatPass": "fresh2", "model": "gemma4-e4b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 42, "sentiment": 49, "follow_up_needed": 58, "serious_concern_reported": 54, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 114.613753082, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 164428, "output": 2106, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceRecordSha256": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceFamily": "small-local-repeats", "sourceStage": "gemma4-e4b-sdk-thinking-off/fresh2/P2" }, { "id": "extended-gemma4-e4b-sdk-thinking-off-fresh3-p0", "experimentId": "extended-gemma4-e4b-sdk-thinking-off-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-small-local-repeats-v1", "repeatPass": "fresh3", "model": "gemma4-e4b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 39, "sentiment": 46, "follow_up_needed": 58, "serious_concern_reported": 53, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 104.398625956, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 97768, "output": 2103, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceRecordSha256": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceFamily": "small-local-repeats", "sourceStage": "gemma4-e4b-sdk-thinking-off/fresh3/P0" }, { "id": "extended-gemma4-e4b-sdk-thinking-off-fresh3-p1", "experimentId": "extended-gemma4-e4b-sdk-thinking-off-fresh3-p0", "parentBaselineId": "extended-gemma4-e4b-sdk-thinking-off-fresh3-p0", "protocolId": "report-only-small-local-repeats-v1", "repeatPass": "fresh3", "model": "gemma4-e4b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 40, "sentiment": 48, "follow_up_needed": 58, "serious_concern_reported": 52, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 76.53574295199999, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 108568, "output": 2100, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceRecordSha256": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceFamily": "small-local-repeats", "sourceStage": "gemma4-e4b-sdk-thinking-off/fresh3/P1" }, { "id": "extended-gemma4-e4b-sdk-thinking-off-fresh3-p2", "experimentId": "extended-gemma4-e4b-sdk-thinking-off-fresh3-p0", "parentBaselineId": "extended-gemma4-e4b-sdk-thinking-off-fresh3-p0", "protocolId": "report-only-small-local-repeats-v1", "repeatPass": "fresh3", "model": "gemma4-e4b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 42, "sentiment": 48, "follow_up_needed": 58, "serious_concern_reported": 54, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 95.664277041, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 164428, "output": 2106, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceRecordSha256": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceFamily": "small-local-repeats", "sourceStage": "gemma4-e4b-sdk-thinking-off/fresh3/P2" }, { "id": "extended-gemma4-e4b-sdk-thinking-on-fresh1-p0", "experimentId": "extended-gemma4-e4b-sdk-thinking-on-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-small-local-repeats-v1", "repeatPass": "fresh1", "model": "gemma4-e4b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 40, "sentiment": 46, "follow_up_needed": 58, "serious_concern_reported": 56, "testimonial_potential": 56 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 477.952936421, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 97888, "output": 16226, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceRecordSha256": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceFamily": "small-local-repeats", "sourceStage": "gemma4-e4b-sdk-thinking-on/fresh1/P0" }, { "id": "extended-gemma4-e4b-sdk-thinking-on-fresh1-p1", "experimentId": "extended-gemma4-e4b-sdk-thinking-on-fresh1-p0", "parentBaselineId": "extended-gemma4-e4b-sdk-thinking-on-fresh1-p0", "protocolId": "report-only-small-local-repeats-v1", "repeatPass": "fresh1", "model": "gemma4-e4b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 43, "sentiment": 52, "follow_up_needed": 59, "serious_concern_reported": 53, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 418.923870038, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 108688, "output": 13186, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceRecordSha256": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceFamily": "small-local-repeats", "sourceStage": "gemma4-e4b-sdk-thinking-on/fresh1/P1" }, { "id": "extended-gemma4-e4b-sdk-thinking-on-fresh1-p2", "experimentId": "extended-gemma4-e4b-sdk-thinking-on-fresh1-p0", "parentBaselineId": "extended-gemma4-e4b-sdk-thinking-on-fresh1-p0", "protocolId": "report-only-small-local-repeats-v1", "repeatPass": "fresh1", "model": "gemma4-e4b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 49, "sentiment": 55, "follow_up_needed": 59, "serious_concern_reported": 57, "testimonial_potential": 55 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 1156.955431247, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 164548, "output": 26490, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceRecordSha256": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceFamily": "small-local-repeats", "sourceStage": "gemma4-e4b-sdk-thinking-on/fresh1/P2" }, { "id": "extended-gemma4-e4b-sdk-thinking-on-fresh2-p1", "experimentId": "extended-gemma4-e4b-sdk-thinking-on-fresh2-p0", "parentBaselineId": "extended-gemma4-e4b-sdk-thinking-on-fresh2-p0", "protocolId": "report-only-small-local-repeats-v1", "repeatPass": "fresh2", "model": "gemma4-e4b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 44, "sentiment": 52, "follow_up_needed": 59, "serious_concern_reported": 54, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 452.640898957, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 108688, "output": 12271, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceRecordSha256": "b74c1c9e72043104c76f2f6938fca8359a85f3628036f5fb7388730a283f03cd", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/small-local-repeats.json", "sourceFamily": "small-local-repeats", "sourceStage": "gemma4-e4b-sdk-thinking-on/fresh2/P1" }, { "id": "extended-gemma4-e4b-sdk-thinking-on-fresh2-p2", "experimentId": "extended-gemma4-e4b-sdk-thinking-on-fresh2-p0", "parentBaselineId": "extended-gemma4-e4b-sdk-thinking-on-fresh2-p0", "protocolId": "report-only-e4b-interruption-findings-v1", "repeatPass": "fresh2", "model": "gemma4-e4b-sdk-thinking-on", "effort": "on", "provider": "local", "surface": "local", "condition": "P2", "complete": false, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": null, "valid": 58, "metrics": { "all_four": 48, "sentiment": 56, "follow_up_needed": 57, "serious_concern_reported": 53, "testimonial_potential": 54 }, "pairedEligible": false, "resultStatus": "completed_interrupted_composite", "timing": { "kind": "client_observed_wall_clock_for_attempts_only", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/e4b-interruption-findings.json", "sourceRecordSha256": "8c6474ee4d672ff4e9fb435a9d138a6dd61b9e14e89b65045cdc44a8fb109835", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/e4b-interruption-findings.json", "sourceFamily": "e4b-interruption-findings", "sourceStage": "gemma4-e4b-sdk-thinking-on/fresh2/P2" }, { "id": "extended-haiku45-fresh-matched3-batch10-pass1-p0", "experimentId": "extended-haiku45-fresh-matched3-batch10-pass1-p0", "parentBaselineId": null, "protocolId": "report-only-haiku-fresh-matched3-v1", "repeatPass": "pass1", "model": "claude-haiku-4-5-20251001", "effort": "not_applicable", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 55, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 57, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 257.3890907910245, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 20071, "output": 25503, "cachedInput": 0, "cacheWrite": 0, "reasoning": 18435, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.147586, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/haiku-fresh-matched3.json", "sourceRecordSha256": "6b49805ec97c55401b85eec2bd5ede5d18b8fe60ad63f7f7daa4fe4a922313f2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/haiku-fresh-matched3.json", "sourceFamily": "haiku-fresh-matched3", "sourceStage": "haiku45-fresh-matched3-batch10/pass1/P0" }, { "id": "extended-haiku45-fresh-matched3-batch10-pass1-p1", "experimentId": "extended-haiku45-fresh-matched3-batch10-pass1-p0", "parentBaselineId": "extended-haiku45-fresh-matched3-batch10-pass1-p0", "protocolId": "report-only-haiku-fresh-matched3-v1", "repeatPass": "pass1", "model": "claude-haiku-4-5-20251001", "effort": "not_applicable", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 53, "sentiment": 56, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 284.3089997919451, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 21207, "output": 26580, "cachedInput": 0, "cacheWrite": 0, "reasoning": 21909, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.154107, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/haiku-fresh-matched3.json", "sourceRecordSha256": "6b49805ec97c55401b85eec2bd5ede5d18b8fe60ad63f7f7daa4fe4a922313f2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/haiku-fresh-matched3.json", "sourceFamily": "haiku-fresh-matched3", "sourceStage": "haiku45-fresh-matched3-batch10/pass1/P1" }, { "id": "extended-haiku45-fresh-matched3-batch10-pass1-p2", "experimentId": "extended-haiku45-fresh-matched3-batch10-pass1-p0", "parentBaselineId": "extended-haiku45-fresh-matched3-batch10-pass1-p0", "protocolId": "report-only-haiku-fresh-matched3-v1", "repeatPass": "pass1", "model": "claude-haiku-4-5-20251001", "effort": "not_applicable", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 54, "sentiment": 57, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 274.9644142080215, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 60, "output": 26192, "cachedInput": 0, "cacheWrite": 27205, "reasoning": 20700, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.18543, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/haiku-fresh-matched3.json", "sourceRecordSha256": "6b49805ec97c55401b85eec2bd5ede5d18b8fe60ad63f7f7daa4fe4a922313f2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/haiku-fresh-matched3.json", "sourceFamily": "haiku-fresh-matched3", "sourceStage": "haiku45-fresh-matched3-batch10/pass1/P2" }, { "id": "extended-haiku45-fresh-matched3-batch10-pass2-p0", "experimentId": "extended-haiku45-fresh-matched3-batch10-pass2-p0", "parentBaselineId": null, "protocolId": "report-only-haiku-fresh-matched3-v1", "repeatPass": "pass2", "model": "claude-haiku-4-5-20251001", "effort": "not_applicable", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 55, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 57, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 295.3661237079941, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 20069, "output": 27710, "cachedInput": 0, "cacheWrite": 0, "reasoning": 21564, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.158619, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/haiku-fresh-matched3.json", "sourceRecordSha256": "6b49805ec97c55401b85eec2bd5ede5d18b8fe60ad63f7f7daa4fe4a922313f2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/haiku-fresh-matched3.json", "sourceFamily": "haiku-fresh-matched3", "sourceStage": "haiku45-fresh-matched3-batch10/pass2/P0" }, { "id": "extended-haiku45-fresh-matched3-batch10-pass2-p1", "experimentId": "extended-haiku45-fresh-matched3-batch10-pass2-p0", "parentBaselineId": "extended-haiku45-fresh-matched3-batch10-pass2-p0", "protocolId": "report-only-haiku-fresh-matched3-v1", "repeatPass": "pass2", "model": "claude-haiku-4-5-20251001", "effort": "not_applicable", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 248.66321979201166, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 21202, "output": 23150, "cachedInput": 0, "cacheWrite": 0, "reasoning": 17812, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.136952, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/haiku-fresh-matched3.json", "sourceRecordSha256": "6b49805ec97c55401b85eec2bd5ede5d18b8fe60ad63f7f7daa4fe4a922313f2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/haiku-fresh-matched3.json", "sourceFamily": "haiku-fresh-matched3", "sourceStage": "haiku45-fresh-matched3-batch10/pass2/P1" }, { "id": "extended-haiku45-fresh-matched3-batch10-pass2-p2", "experimentId": "extended-haiku45-fresh-matched3-batch10-pass2-p0", "parentBaselineId": "extended-haiku45-fresh-matched3-batch10-pass2-p0", "protocolId": "report-only-haiku-fresh-matched3-v1", "repeatPass": "pass2", "model": "claude-haiku-4-5-20251001", "effort": "not_applicable", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 55, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 260.32371379298274, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 60, "output": 25655, "cachedInput": 0, "cacheWrite": 27206, "reasoning": 20164, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.182747, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/haiku-fresh-matched3.json", "sourceRecordSha256": "6b49805ec97c55401b85eec2bd5ede5d18b8fe60ad63f7f7daa4fe4a922313f2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/haiku-fresh-matched3.json", "sourceFamily": "haiku-fresh-matched3", "sourceStage": "haiku45-fresh-matched3-batch10/pass2/P2" }, { "id": "extended-haiku45-fresh-matched3-batch10-pass3-p0", "experimentId": "extended-haiku45-fresh-matched3-batch10-pass3-p0", "parentBaselineId": null, "protocolId": "report-only-haiku-fresh-matched3-v1", "repeatPass": "pass3", "model": "claude-haiku-4-5-20251001", "effort": "not_applicable", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 57, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 243.80595179097145, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 20070, "output": 24683, "cachedInput": 0, "cacheWrite": 0, "reasoning": 17434, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.143485, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/haiku-fresh-matched3.json", "sourceRecordSha256": "6b49805ec97c55401b85eec2bd5ede5d18b8fe60ad63f7f7daa4fe4a922313f2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/haiku-fresh-matched3.json", "sourceFamily": "haiku-fresh-matched3", "sourceStage": "haiku45-fresh-matched3-batch10/pass3/P0" }, { "id": "extended-haiku45-fresh-matched3-batch10-pass3-p1", "experimentId": "extended-haiku45-fresh-matched3-batch10-pass3-p0", "parentBaselineId": "extended-haiku45-fresh-matched3-batch10-pass3-p0", "protocolId": "report-only-haiku-fresh-matched3-v1", "repeatPass": "pass3", "model": "claude-haiku-4-5-20251001", "effort": "not_applicable", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 59, "sentiment": 60, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 276.496266040951, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 21201, "output": 26729, "cachedInput": 0, "cacheWrite": 0, "reasoning": 21504, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.15484599999999998, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/haiku-fresh-matched3.json", "sourceRecordSha256": "6b49805ec97c55401b85eec2bd5ede5d18b8fe60ad63f7f7daa4fe4a922313f2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/haiku-fresh-matched3.json", "sourceFamily": "haiku-fresh-matched3", "sourceStage": "haiku45-fresh-matched3-batch10/pass3/P1" }, { "id": "extended-haiku45-fresh-matched3-batch10-pass3-p2", "experimentId": "extended-haiku45-fresh-matched3-batch10-pass3-p0", "parentBaselineId": "extended-haiku45-fresh-matched3-batch10-pass3-p0", "protocolId": "report-only-haiku-fresh-matched3-v1", "repeatPass": "pass3", "model": "claude-haiku-4-5-20251001", "effort": "not_applicable", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 302.5701222079515, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 60, "output": 29094, "cachedInput": 0, "cacheWrite": 27202, "reasoning": 22193, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.199934, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/haiku-fresh-matched3.json", "sourceRecordSha256": "6b49805ec97c55401b85eec2bd5ede5d18b8fe60ad63f7f7daa4fe4a922313f2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/haiku-fresh-matched3.json", "sourceFamily": "haiku-fresh-matched3", "sourceStage": "haiku45-fresh-matched3-batch10/pass3/P2" }, { "id": "extended-kev-openrouter-native-p0-fresh1-p0", "experimentId": "extended-kev-openrouter-native-p0-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-kev-native-repeats-v1", "repeatPass": "fresh1", "model": "jaredpalmer/kev-4b", "effort": null, "provider": "SiliconFlow", "surface": "SiliconFlow", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 48, "sentiment": 52, "follow_up_needed": 58, "serious_concern_reported": 55, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.004703412, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/kev-native-repeats.json", "sourceRecordSha256": "3f8b95ae790a8252fe2bb7a6823a8ee8196a245bf37bd4fb4f5944cb2b0e0fa9", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/kev-native-repeats.json", "sourceFamily": "kev-native-repeats", "sourceStage": "kev-openrouter-native-p0/fresh1/P0" }, { "id": "extended-kev-openrouter-native-p0-fresh2-p0", "experimentId": "extended-kev-openrouter-native-p0-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-kev-native-repeats-v1", "repeatPass": "fresh2", "model": "jaredpalmer/kev-4b", "effort": null, "provider": "SiliconFlow", "surface": "SiliconFlow", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 48, "sentiment": 52, "follow_up_needed": 58, "serious_concern_reported": 55, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.004703412, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/kev-native-repeats.json", "sourceRecordSha256": "3f8b95ae790a8252fe2bb7a6823a8ee8196a245bf37bd4fb4f5944cb2b0e0fa9", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/kev-native-repeats.json", "sourceFamily": "kev-native-repeats", "sourceStage": "kev-openrouter-native-p0/fresh2/P0" }, { "id": "extended-kev-openrouter-native-prompts-fresh1-p1", "experimentId": "extended-kev-openrouter-native-prompts-fresh1-p0", "parentBaselineId": "extended-kev-openrouter-native-prompts-fresh1-p0", "protocolId": "report-only-kev-native-prompt-findings-v1", "repeatPass": "fresh1", "model": "kev-openrouter-native-prompts", "effort": null, "provider": "OpenRouter", "surface": "OpenRouter", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 49, "sentiment": 53, "follow_up_needed": 58, "serious_concern_reported": 55, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.005207412, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/kev-native-prompt-findings.json", "sourceRecordSha256": "0b860a96067bdd729c35bd131dd10a4495f7526ad7a01ee979077af36be52683", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/kev-native-prompt-findings.json", "sourceFamily": "kev-native-prompt-findings", "sourceStage": "kev-openrouter-native-prompts/fresh1/P1" }, { "id": "extended-kev-openrouter-native-prompts-fresh1-p2", "experimentId": "extended-kev-openrouter-native-prompts-fresh1-p0", "parentBaselineId": "extended-kev-openrouter-native-prompts-fresh1-p0", "protocolId": "report-only-kev-native-prompt-findings-v1", "repeatPass": "fresh1", "model": "kev-openrouter-native-prompts", "effort": null, "provider": "OpenRouter", "surface": "OpenRouter", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 46, "sentiment": 54, "follow_up_needed": 53, "serious_concern_reported": 55, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.005638332, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/kev-native-prompt-findings.json", "sourceRecordSha256": "0b860a96067bdd729c35bd131dd10a4495f7526ad7a01ee979077af36be52683", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/kev-native-prompt-findings.json", "sourceFamily": "kev-native-prompt-findings", "sourceStage": "kev-openrouter-native-prompts/fresh1/P2" }, { "id": "extended-kev-openrouter-native-prompts-fresh2-p1", "experimentId": "extended-kev-openrouter-native-prompts-fresh2-p0", "parentBaselineId": "extended-kev-openrouter-native-prompts-fresh2-p0", "protocolId": "report-only-kev-native-prompt-findings-v1", "repeatPass": "fresh2", "model": "kev-openrouter-native-prompts", "effort": null, "provider": "OpenRouter", "surface": "OpenRouter", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 49, "sentiment": 53, "follow_up_needed": 58, "serious_concern_reported": 55, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.005207412, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/kev-native-prompt-findings.json", "sourceRecordSha256": "0b860a96067bdd729c35bd131dd10a4495f7526ad7a01ee979077af36be52683", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/kev-native-prompt-findings.json", "sourceFamily": "kev-native-prompt-findings", "sourceStage": "kev-openrouter-native-prompts/fresh2/P1" }, { "id": "extended-kev-openrouter-native-prompts-fresh2-p2", "experimentId": "extended-kev-openrouter-native-prompts-fresh2-p0", "parentBaselineId": "extended-kev-openrouter-native-prompts-fresh2-p0", "protocolId": "report-only-kev-native-prompt-findings-v1", "repeatPass": "fresh2", "model": "kev-openrouter-native-prompts", "effort": null, "provider": "OpenRouter", "surface": "OpenRouter", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 46, "sentiment": 54, "follow_up_needed": 53, "serious_concern_reported": 55, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.005638332, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/kev-native-prompt-findings.json", "sourceRecordSha256": "0b860a96067bdd729c35bd131dd10a4495f7526ad7a01ee979077af36be52683", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/kev-native-prompt-findings.json", "sourceFamily": "kev-native-prompt-findings", "sourceStage": "kev-openrouter-native-prompts/fresh2/P2" }, { "id": "extended-kev-openrouter-native-prompts-fresh3-p1", "experimentId": "extended-kev-openrouter-native-prompts-fresh3-p0", "parentBaselineId": "extended-kev-openrouter-native-prompts-fresh3-p0", "protocolId": "report-only-kev-native-prompt-findings-v1", "repeatPass": "fresh3", "model": "kev-openrouter-native-prompts", "effort": null, "provider": "OpenRouter", "surface": "OpenRouter", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 49, "sentiment": 53, "follow_up_needed": 58, "serious_concern_reported": 55, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.005207412, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/kev-native-prompt-findings.json", "sourceRecordSha256": "0b860a96067bdd729c35bd131dd10a4495f7526ad7a01ee979077af36be52683", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/kev-native-prompt-findings.json", "sourceFamily": "kev-native-prompt-findings", "sourceStage": "kev-openrouter-native-prompts/fresh3/P1" }, { "id": "extended-kev-openrouter-native-prompts-fresh3-p2", "experimentId": "extended-kev-openrouter-native-prompts-fresh3-p0", "parentBaselineId": "extended-kev-openrouter-native-prompts-fresh3-p0", "protocolId": "report-only-kev-native-prompt-findings-v1", "repeatPass": "fresh3", "model": "kev-openrouter-native-prompts", "effort": null, "provider": "OpenRouter", "surface": "OpenRouter", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 46, "sentiment": 54, "follow_up_needed": 53, "serious_concern_reported": 55, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.005638332, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/kev-native-prompt-findings.json", "sourceRecordSha256": "0b860a96067bdd729c35bd131dd10a4495f7526ad7a01ee979077af36be52683", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/kev-native-prompt-findings.json", "sourceFamily": "kev-native-prompt-findings", "sourceStage": "kev-openrouter-native-prompts/fresh3/P2" }, { "id": "extended-laya-english-expanded-cpu-repeat2-p0", "experimentId": "extended-laya-english-expanded-cpu-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-laya-repeats-v1", "repeatPass": "repeat2", "model": "laya-english-expanded-cpu", "effort": null, "provider": "Local native CPU", "surface": "Local native CPU", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 0, "sentiment": 41, "follow_up_needed": 42, "serious_concern_reported": 33, "testimonial_potential": 13 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 727.1726339160814, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 393168, "output": 0, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local CPU electricity and hardware cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/laya-repeats.json", "sourceRecordSha256": "a5e6f8b2faabb6db9bf6588cb1c3909a3694546297b7a6ebbac6c4bf12412ccf", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/laya-repeats.json", "sourceFamily": "laya-repeats", "sourceStage": "laya-english-expanded-cpu/repeat2/P0" }, { "id": "extended-laya-english-expanded-cpu-repeat3-p0", "experimentId": "extended-laya-english-expanded-cpu-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-laya-repeats-v1", "repeatPass": "repeat3", "model": "laya-english-expanded-cpu", "effort": null, "provider": "Local native CPU", "surface": "Local native CPU", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 0, "sentiment": 41, "follow_up_needed": 42, "serious_concern_reported": 33, "testimonial_potential": 13 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 1463.9582369960262, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 393168, "output": 0, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local CPU electricity and hardware cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/laya-repeats.json", "sourceRecordSha256": "a5e6f8b2faabb6db9bf6588cb1c3909a3694546297b7a6ebbac6c4bf12412ccf", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/laya-repeats.json", "sourceFamily": "laya-repeats", "sourceStage": "laya-english-expanded-cpu/repeat3/P0" }, { "id": "extended-laya-multilingual-expanded-cpu-repeat2-p0", "experimentId": "extended-laya-multilingual-expanded-cpu-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-laya-repeats-v1", "repeatPass": "repeat2", "model": "laya-multilingual-expanded-cpu", "effort": null, "provider": "Local native CPU", "surface": "Local native CPU", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 0, "sentiment": 33, "follow_up_needed": 37, "serious_concern_reported": 24, "testimonial_potential": 10 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 703.1551339150756, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 382128, "output": 0, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local CPU electricity and hardware cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/laya-repeats.json", "sourceRecordSha256": "a5e6f8b2faabb6db9bf6588cb1c3909a3694546297b7a6ebbac6c4bf12412ccf", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/laya-repeats.json", "sourceFamily": "laya-repeats", "sourceStage": "laya-multilingual-expanded-cpu/repeat2/P0" }, { "id": "extended-laya-multilingual-expanded-cpu-repeat3-p0", "experimentId": "extended-laya-multilingual-expanded-cpu-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-laya-repeats-v1", "repeatPass": "repeat3", "model": "laya-multilingual-expanded-cpu", "effort": null, "provider": "Local native CPU", "surface": "Local native CPU", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 0, "sentiment": 33, "follow_up_needed": 37, "serious_concern_reported": 24, "testimonial_potential": 10 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 1069.6219031290093, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 382128, "output": 0, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local CPU electricity and hardware cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/laya-repeats.json", "sourceRecordSha256": "a5e6f8b2faabb6db9bf6588cb1c3909a3694546297b7a6ebbac6c4bf12412ccf", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/laya-repeats.json", "sourceFamily": "laya-repeats", "sourceStage": "laya-multilingual-expanded-cpu/repeat3/P0" }, { "id": "extended-laya-typed-expanded-cpu-repeat2-p0", "experimentId": "extended-laya-typed-expanded-cpu-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-laya-repeats-v1", "repeatPass": "repeat2", "model": "laya-typed-expanded-cpu", "effort": null, "provider": "Local native CPU", "surface": "Local native CPU", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 0, "sentiment": 39, "follow_up_needed": 47, "serious_concern_reported": 32, "testimonial_potential": 10 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 1000.8334295869572, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 393168, "output": 0, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local CPU electricity and hardware cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/laya-repeats.json", "sourceRecordSha256": "a5e6f8b2faabb6db9bf6588cb1c3909a3694546297b7a6ebbac6c4bf12412ccf", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/laya-repeats.json", "sourceFamily": "laya-repeats", "sourceStage": "laya-typed-expanded-cpu/repeat2/P0" }, { "id": "extended-laya-typed-expanded-cpu-repeat3-p0", "experimentId": "extended-laya-typed-expanded-cpu-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-laya-repeats-v1", "repeatPass": "repeat3", "model": "laya-typed-expanded-cpu", "effort": null, "provider": "Local native CPU", "surface": "Local native CPU", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 0, "sentiment": 39, "follow_up_needed": 47, "serious_concern_reported": 32, "testimonial_potential": 10 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 913.2673453740135, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 393168, "output": 0, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local CPU electricity and hardware cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/laya-repeats.json", "sourceRecordSha256": "a5e6f8b2faabb6db9bf6588cb1c3909a3694546297b7a6ebbac6c4bf12412ccf", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/laya-repeats.json", "sourceFamily": "laya-repeats", "sourceStage": "laya-typed-expanded-cpu/repeat3/P0" }, { "id": "extended-openjev-adaptive-fresh1-p0", "experimentId": "extended-openjev-adaptive-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-openjev-native-repeats-v1", "repeatPass": "fresh1", "model": "openjev-adaptive", "effort": null, "provider": "local", "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 52, "sentiment": 54, "follow_up_needed": 60, "serious_concern_reported": 57, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_http_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 285.40529799996875, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 123989, "output": 0, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured; HTTP usage is not a bill." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-native-repeats.json", "sourceRecordSha256": "485a79dbab84a693a6ddfd53b2333ee394d095a4ea5a8e2989b17d546706c69e", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-native-repeats.json", "sourceFamily": "openjev-native-repeats", "sourceStage": "openjev-adaptive/fresh1/P0" }, { "id": "extended-openjev-adaptive-fresh2-p0", "experimentId": "extended-openjev-adaptive-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-openjev-native-repeats-v1", "repeatPass": "fresh2", "model": "openjev-adaptive", "effort": null, "provider": "local", "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 52, "sentiment": 54, "follow_up_needed": 60, "serious_concern_reported": 57, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_http_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 286.98424950405024, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 123989, "output": 0, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured; HTTP usage is not a bill." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-native-repeats.json", "sourceRecordSha256": "485a79dbab84a693a6ddfd53b2333ee394d095a4ea5a8e2989b17d546706c69e", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-native-repeats.json", "sourceFamily": "openjev-native-repeats", "sourceStage": "openjev-adaptive/fresh2/P0" }, { "id": "extended-openjev-adaptive-fresh3-p0", "experimentId": "extended-openjev-adaptive-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-openjev-native-repeats-v1", "repeatPass": "fresh3", "model": "openjev-adaptive", "effort": null, "provider": "local", "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 52, "sentiment": 54, "follow_up_needed": 60, "serious_concern_reported": 57, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_http_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 289.3513373360329, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 123989, "output": 0, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured; HTTP usage is not a bill." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-native-repeats.json", "sourceRecordSha256": "485a79dbab84a693a6ddfd53b2333ee394d095a4ea5a8e2989b17d546706c69e", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-native-repeats.json", "sourceFamily": "openjev-native-repeats", "sourceStage": "openjev-adaptive/fresh3/P0" }, { "id": "extended-openjev-fixed-fresh1-p0", "experimentId": "extended-openjev-fixed-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-openjev-native-repeats-v1", "repeatPass": "fresh1", "model": "openjev-fixed", "effort": null, "provider": "local", "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 53, "sentiment": 56, "follow_up_needed": 60, "serious_concern_reported": 57, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_http_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 239.76808195514604, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 123989, "output": 0, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured; HTTP usage is not a bill." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-native-repeats.json", "sourceRecordSha256": "485a79dbab84a693a6ddfd53b2333ee394d095a4ea5a8e2989b17d546706c69e", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-native-repeats.json", "sourceFamily": "openjev-native-repeats", "sourceStage": "openjev-fixed/fresh1/P0" }, { "id": "extended-openjev-fixed-fresh2-p0", "experimentId": "extended-openjev-fixed-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-openjev-native-repeats-v1", "repeatPass": "fresh2", "model": "openjev-fixed", "effort": null, "provider": "local", "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 53, "sentiment": 56, "follow_up_needed": 60, "serious_concern_reported": 57, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_http_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 254.37550500192447, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 123989, "output": 0, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured; HTTP usage is not a bill." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-native-repeats.json", "sourceRecordSha256": "485a79dbab84a693a6ddfd53b2333ee394d095a4ea5a8e2989b17d546706c69e", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-native-repeats.json", "sourceFamily": "openjev-native-repeats", "sourceStage": "openjev-fixed/fresh2/P0" }, { "id": "extended-openjev-fixed-fresh3-p0", "experimentId": "extended-openjev-fixed-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-openjev-native-repeats-v1", "repeatPass": "fresh3", "model": "openjev-fixed", "effort": null, "provider": "local", "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 53, "sentiment": 56, "follow_up_needed": 60, "serious_concern_reported": 57, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_http_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 255.13528829303687, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 123989, "output": 0, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured; HTTP usage is not a bill." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-native-repeats.json", "sourceRecordSha256": "485a79dbab84a693a6ddfd53b2333ee394d095a4ea5a8e2989b17d546706c69e", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-native-repeats.json", "sourceFamily": "openjev-native-repeats", "sourceStage": "openjev-fixed/fresh3/P0" }, { "id": "extended-openjev-generated-off-fresh1-p0", "experimentId": "extended-openjev-generated-off-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-openjev-generated-repeats-v1", "repeatPass": "fresh1", "model": "openjev-generated-off", "effort": null, "provider": "local", "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 53, "metrics": { "all_four": 48, "sentiment": 52, "follow_up_needed": 52, "serious_concern_reported": 52, "testimonial_potential": 51 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_http_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 476.18278129101964, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 100168, "output": 2172, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceRecordSha256": "fa198837ea32f92556ed05a26023a632f3cf9b026970ed006d6370a537000562", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceFamily": "openjev-generated-repeats", "sourceStage": "openjev-generated-off/fresh1/P0" }, { "id": "extended-openjev-generated-off-fresh1-p1", "experimentId": "extended-openjev-generated-off-fresh1-p0", "parentBaselineId": "extended-openjev-generated-off-fresh1-p0", "protocolId": "report-only-openjev-generated-repeats-v1", "repeatPass": "fresh1", "model": "openjev-generated-off", "effort": null, "provider": "local", "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 53, "metrics": { "all_four": 48, "sentiment": 51, "follow_up_needed": 52, "serious_concern_reported": 51, "testimonial_potential": 53 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_http_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 482.91770749824354, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 110968, "output": 2645, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceRecordSha256": "fa198837ea32f92556ed05a26023a632f3cf9b026970ed006d6370a537000562", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceFamily": "openjev-generated-repeats", "sourceStage": "openjev-generated-off/fresh1/P1" }, { "id": "extended-openjev-generated-off-fresh1-p2", "experimentId": "extended-openjev-generated-off-fresh1-p0", "parentBaselineId": "extended-openjev-generated-off-fresh1-p0", "protocolId": "report-only-openjev-generated-repeats-v1", "repeatPass": "fresh1", "model": "openjev-generated-off", "effort": null, "provider": "local", "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 56, "metrics": { "all_four": 51, "sentiment": 55, "follow_up_needed": 55, "serious_concern_reported": 55, "testimonial_potential": 54 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_http_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 689.6118849999039, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 166828, "output": 2764, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceRecordSha256": "fa198837ea32f92556ed05a26023a632f3cf9b026970ed006d6370a537000562", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceFamily": "openjev-generated-repeats", "sourceStage": "openjev-generated-off/fresh1/P2" }, { "id": "extended-openjev-generated-off-fresh2-p0", "experimentId": "extended-openjev-generated-off-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-openjev-generated-repeats-v1", "repeatPass": "fresh2", "model": "openjev-generated-off", "effort": null, "provider": "local", "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 55, "metrics": { "all_four": 51, "sentiment": 54, "follow_up_needed": 54, "serious_concern_reported": 54, "testimonial_potential": 54 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_http_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 428.74042846099474, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 100168, "output": 2183, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceRecordSha256": "fa198837ea32f92556ed05a26023a632f3cf9b026970ed006d6370a537000562", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceFamily": "openjev-generated-repeats", "sourceStage": "openjev-generated-off/fresh2/P0" }, { "id": "extended-openjev-generated-off-fresh2-p1", "experimentId": "extended-openjev-generated-off-fresh2-p0", "parentBaselineId": "extended-openjev-generated-off-fresh2-p0", "protocolId": "report-only-openjev-generated-repeats-v1", "repeatPass": "fresh2", "model": "openjev-generated-off", "effort": null, "provider": "local", "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 53, "metrics": { "all_four": 50, "sentiment": 51, "follow_up_needed": 53, "serious_concern_reported": 51, "testimonial_potential": 53 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_http_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 490.4430819172412, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 110968, "output": 2626, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceRecordSha256": "fa198837ea32f92556ed05a26023a632f3cf9b026970ed006d6370a537000562", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceFamily": "openjev-generated-repeats", "sourceStage": "openjev-generated-off/fresh2/P1" }, { "id": "extended-openjev-generated-off-fresh2-p2", "experimentId": "extended-openjev-generated-off-fresh2-p0", "parentBaselineId": "extended-openjev-generated-off-fresh2-p0", "protocolId": "report-only-openjev-generated-repeats-v1", "repeatPass": "fresh2", "model": "openjev-generated-off", "effort": null, "provider": "local", "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 57, "metrics": { "all_four": 54, "sentiment": 56, "follow_up_needed": 56, "serious_concern_reported": 56, "testimonial_potential": 57 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_http_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 663.2012516671675, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 166828, "output": 2750, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceRecordSha256": "fa198837ea32f92556ed05a26023a632f3cf9b026970ed006d6370a537000562", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceFamily": "openjev-generated-repeats", "sourceStage": "openjev-generated-off/fresh2/P2" }, { "id": "extended-openjev-generated-off-fresh3-p0", "experimentId": "extended-openjev-generated-off-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-openjev-generated-repeats-v1", "repeatPass": "fresh3", "model": "openjev-generated-off", "effort": null, "provider": "local", "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 54, "metrics": { "all_four": 49, "sentiment": 52, "follow_up_needed": 53, "serious_concern_reported": 53, "testimonial_potential": 53 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_http_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 459.86774792312644, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 100168, "output": 2138, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceRecordSha256": "fa198837ea32f92556ed05a26023a632f3cf9b026970ed006d6370a537000562", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceFamily": "openjev-generated-repeats", "sourceStage": "openjev-generated-off/fresh3/P0" }, { "id": "extended-openjev-generated-off-fresh3-p1", "experimentId": "extended-openjev-generated-off-fresh3-p0", "parentBaselineId": "extended-openjev-generated-off-fresh3-p0", "protocolId": "report-only-openjev-generated-repeats-v1", "repeatPass": "fresh3", "model": "openjev-generated-off", "effort": null, "provider": "local", "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 56, "metrics": { "all_four": 49, "sentiment": 54, "follow_up_needed": 55, "serious_concern_reported": 54, "testimonial_potential": 54 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_http_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 578.9903756640269, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 110968, "output": 2638, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceRecordSha256": "fa198837ea32f92556ed05a26023a632f3cf9b026970ed006d6370a537000562", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceFamily": "openjev-generated-repeats", "sourceStage": "openjev-generated-off/fresh3/P1" }, { "id": "extended-openjev-generated-off-fresh3-p2", "experimentId": "extended-openjev-generated-off-fresh3-p0", "parentBaselineId": "extended-openjev-generated-off-fresh3-p0", "protocolId": "report-only-openjev-generated-repeats-v1", "repeatPass": "fresh3", "model": "openjev-generated-off", "effort": null, "provider": "local", "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 54, "metrics": { "all_four": 51, "sentiment": 52, "follow_up_needed": 54, "serious_concern_reported": 53, "testimonial_potential": 54 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_http_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 615.0368293357315, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 166828, "output": 2748, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceRecordSha256": "fa198837ea32f92556ed05a26023a632f3cf9b026970ed006d6370a537000562", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceFamily": "openjev-generated-repeats", "sourceStage": "openjev-generated-off/fresh3/P2" }, { "id": "extended-openjev-generated-on-fresh1-p0", "experimentId": "extended-openjev-generated-on-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-openjev-generated-repeats-v1", "repeatPass": "fresh1", "model": "openjev-generated-on", "effort": null, "provider": "local", "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 59, "metrics": { "all_four": 54, "sentiment": 58, "follow_up_needed": 58, "serious_concern_reported": 56, "testimonial_potential": 57 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_http_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 667.5591191617423, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 100288, "output": 2086, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceRecordSha256": "fa198837ea32f92556ed05a26023a632f3cf9b026970ed006d6370a537000562", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceFamily": "openjev-generated-repeats", "sourceStage": "openjev-generated-on/fresh1/P0" }, { "id": "extended-openjev-generated-on-fresh1-p1", "experimentId": "extended-openjev-generated-on-fresh1-p0", "parentBaselineId": "extended-openjev-generated-on-fresh1-p0", "protocolId": "report-only-openjev-generated-repeats-v1", "repeatPass": "fresh1", "model": "openjev-generated-on", "effort": null, "provider": "local", "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 55, "metrics": { "all_four": 50, "sentiment": 53, "follow_up_needed": 53, "serious_concern_reported": 52, "testimonial_potential": 54 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_http_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 670.4264612076804, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 111088, "output": 2142, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceRecordSha256": "fa198837ea32f92556ed05a26023a632f3cf9b026970ed006d6370a537000562", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceFamily": "openjev-generated-repeats", "sourceStage": "openjev-generated-on/fresh1/P1" }, { "id": "extended-openjev-generated-on-fresh1-p2", "experimentId": "extended-openjev-generated-on-fresh1-p0", "parentBaselineId": "extended-openjev-generated-on-fresh1-p0", "protocolId": "report-only-openjev-generated-repeats-v1", "repeatPass": "fresh1", "model": "openjev-generated-on", "effort": null, "provider": "local", "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 52, "metrics": { "all_four": 46, "sentiment": 48, "follow_up_needed": 51, "serious_concern_reported": 51, "testimonial_potential": 52 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_http_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 846.2473677501548, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 166948, "output": 2458, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceRecordSha256": "fa198837ea32f92556ed05a26023a632f3cf9b026970ed006d6370a537000562", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceFamily": "openjev-generated-repeats", "sourceStage": "openjev-generated-on/fresh1/P2" }, { "id": "extended-openjev-generated-on-fresh2-p0", "experimentId": "extended-openjev-generated-on-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-openjev-generated-repeats-v1", "repeatPass": "fresh2", "model": "openjev-generated-on", "effort": null, "provider": "local", "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 58, "metrics": { "all_four": 53, "sentiment": 55, "follow_up_needed": 56, "serious_concern_reported": 56, "testimonial_potential": 57 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_http_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 536.1725062530022, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 100288, "output": 2363, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceRecordSha256": "fa198837ea32f92556ed05a26023a632f3cf9b026970ed006d6370a537000562", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceFamily": "openjev-generated-repeats", "sourceStage": "openjev-generated-on/fresh2/P0" }, { "id": "extended-openjev-generated-on-fresh2-p1", "experimentId": "extended-openjev-generated-on-fresh2-p0", "parentBaselineId": "extended-openjev-generated-on-fresh2-p0", "protocolId": "report-only-openjev-generated-repeats-v1", "repeatPass": "fresh2", "model": "openjev-generated-on", "effort": null, "provider": "local", "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 51, "metrics": { "all_four": 46, "sentiment": 48, "follow_up_needed": 50, "serious_concern_reported": 50, "testimonial_potential": 51 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_http_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 587.0604753000662, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 111088, "output": 2351, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceRecordSha256": "fa198837ea32f92556ed05a26023a632f3cf9b026970ed006d6370a537000562", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceFamily": "openjev-generated-repeats", "sourceStage": "openjev-generated-on/fresh2/P1" }, { "id": "extended-openjev-generated-on-fresh2-p2", "experimentId": "extended-openjev-generated-on-fresh2-p0", "parentBaselineId": "extended-openjev-generated-on-fresh2-p0", "protocolId": "report-only-openjev-generated-repeats-v1", "repeatPass": "fresh2", "model": "openjev-generated-on", "effort": null, "provider": "local", "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 52, "metrics": { "all_four": 47, "sentiment": 48, "follow_up_needed": 52, "serious_concern_reported": 51, "testimonial_potential": 52 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_http_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 769.6663701283396, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 166948, "output": 2437, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceRecordSha256": "fa198837ea32f92556ed05a26023a632f3cf9b026970ed006d6370a537000562", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceFamily": "openjev-generated-repeats", "sourceStage": "openjev-generated-on/fresh2/P2" }, { "id": "extended-openjev-generated-on-fresh3-p0", "experimentId": "extended-openjev-generated-on-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-openjev-generated-repeats-v1", "repeatPass": "fresh3", "model": "openjev-generated-on", "effort": null, "provider": "local", "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 57, "metrics": { "all_four": 49, "sentiment": 54, "follow_up_needed": 57, "serious_concern_reported": 54, "testimonial_potential": 55 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_http_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 534.755461620749, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 100288, "output": 2131, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceRecordSha256": "fa198837ea32f92556ed05a26023a632f3cf9b026970ed006d6370a537000562", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceFamily": "openjev-generated-repeats", "sourceStage": "openjev-generated-on/fresh3/P0" }, { "id": "extended-openjev-generated-on-fresh3-p1", "experimentId": "extended-openjev-generated-on-fresh3-p0", "parentBaselineId": "extended-openjev-generated-on-fresh3-p0", "protocolId": "report-only-openjev-generated-repeats-v1", "repeatPass": "fresh3", "model": "openjev-generated-on", "effort": null, "provider": "local", "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 51, "metrics": { "all_four": 49, "sentiment": 50, "follow_up_needed": 51, "serious_concern_reported": 50, "testimonial_potential": 51 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_http_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 516.9101201241137, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 111088, "output": 2199, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceRecordSha256": "fa198837ea32f92556ed05a26023a632f3cf9b026970ed006d6370a537000562", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceFamily": "openjev-generated-repeats", "sourceStage": "openjev-generated-on/fresh3/P1" }, { "id": "extended-openjev-generated-on-fresh3-p2", "experimentId": "extended-openjev-generated-on-fresh3-p0", "parentBaselineId": "extended-openjev-generated-on-fresh3-p0", "protocolId": "report-only-openjev-generated-repeats-v1", "repeatPass": "fresh3", "model": "openjev-generated-on", "effort": null, "provider": "local", "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 47, "metrics": { "all_four": 42, "sentiment": 46, "follow_up_needed": 45, "serious_concern_reported": 46, "testimonial_potential": 46 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_http_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 719.1130057912669, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 166948, "output": 2433, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceRecordSha256": "fa198837ea32f92556ed05a26023a632f3cf9b026970ed006d6370a537000562", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-generated-repeats.json", "sourceFamily": "openjev-generated-repeats", "sourceStage": "openjev-generated-on/fresh3/P2" }, { "id": "extended-openjev-thinking-fresh1-p0", "experimentId": "extended-openjev-thinking-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-openjev-native-repeats-v1", "repeatPass": "fresh1", "model": "openjev-thinking", "effort": null, "provider": "local", "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 53, "sentiment": 57, "follow_up_needed": 57, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_http_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 1514.7387012500258, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 274237, "output": 25599, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured; HTTP usage is not a bill." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-native-repeats.json", "sourceRecordSha256": "485a79dbab84a693a6ddfd53b2333ee394d095a4ea5a8e2989b17d546706c69e", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-native-repeats.json", "sourceFamily": "openjev-native-repeats", "sourceStage": "openjev-thinking/fresh1/P0" }, { "id": "extended-openjev-thinking-fresh2-p0", "experimentId": "extended-openjev-thinking-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-openjev-native-repeats-v1", "repeatPass": "fresh2", "model": "openjev-thinking", "effort": null, "provider": "local", "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 54, "sentiment": 57, "follow_up_needed": 58, "serious_concern_reported": 57, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_http_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 1553.0856296700367, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 274066, "output": 25428, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured; HTTP usage is not a bill." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-native-repeats.json", "sourceRecordSha256": "485a79dbab84a693a6ddfd53b2333ee394d095a4ea5a8e2989b17d546706c69e", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-native-repeats.json", "sourceFamily": "openjev-native-repeats", "sourceStage": "openjev-thinking/fresh2/P0" }, { "id": "extended-openjev-thinking-fresh3-p0", "experimentId": "extended-openjev-thinking-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-openjev-native-repeats-v1", "repeatPass": "fresh3", "model": "openjev-thinking", "effort": null, "provider": "local", "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 54, "sentiment": 57, "follow_up_needed": 58, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_http_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 2147.597180588229, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 273598, "output": 24960, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured; HTTP usage is not a bill." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-native-repeats.json", "sourceRecordSha256": "485a79dbab84a693a6ddfd53b2333ee394d095a4ea5a8e2989b17d546706c69e", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/openjev-native-repeats.json", "sourceFamily": "openjev-native-repeats", "sourceStage": "openjev-thinking/fresh3/P0" }, { "id": "extended-openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price-fresh1-p0", "experimentId": "extended-openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-additional-hosted-fresh-repeats-v1", "repeatPass": "fresh1", "model": "deepseek/deepseek-v4.1-flash", "effort": "high", "provider": "open-inference/fp4", "surface": "OpenRouter · open-inference/fp4", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 59, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 59 }, "pairedEligible": false, "resultStatus": "completed_with_intrinsic_invalid", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 85717, "output": 23913, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.034324790897, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/additional-hosted-fresh-repeats.json", "sourceRecordSha256": "cfd11bb576566097c6d351896e05578ffd6e1a35014011194d0d06fee0e85cf4", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/additional-hosted-fresh-repeats.json", "sourceFamily": "additional-hosted-fresh-repeats", "sourceStage": "openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price/fresh1/P0" }, { "id": "extended-openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price-fresh1-p1", "experimentId": "extended-openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price-fresh1-p0", "parentBaselineId": "extended-openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price-fresh1-p0", "protocolId": "report-only-additional-hosted-fresh-repeats-v1", "repeatPass": "fresh1", "model": "deepseek/deepseek-v4.1-flash", "effort": "high", "provider": "open-inference/fp4", "surface": "OpenRouter · open-inference/fp4", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 59, "metrics": { "all_four": 57, "sentiment": 57, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 59 }, "pairedEligible": false, "resultStatus": "completed_with_intrinsic_invalid", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 96337, "output": 22944, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.031765648225, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/additional-hosted-fresh-repeats.json", "sourceRecordSha256": "cfd11bb576566097c6d351896e05578ffd6e1a35014011194d0d06fee0e85cf4", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/additional-hosted-fresh-repeats.json", "sourceFamily": "additional-hosted-fresh-repeats", "sourceStage": "openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price/fresh1/P1" }, { "id": "extended-openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price-remaining7-price-v1-fresh1-p2", "experimentId": "extended-openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price-remaining7-price-v1-fresh1-p0", "parentBaselineId": "extended-openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price-remaining7-price-v1-fresh1-p0", "protocolId": "report-only-additional-hosted-fresh-repeats-v1", "repeatPass": "fresh1", "model": "deepseek/deepseek-v4.1-flash", "effort": "high", "provider": "open-inference/fp4", "surface": "OpenRouter · open-inference/fp4", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 151117, "output": 19504, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0325023468, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/additional-hosted-fresh-repeats.json", "sourceRecordSha256": "cfd11bb576566097c6d351896e05578ffd6e1a35014011194d0d06fee0e85cf4", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/additional-hosted-fresh-repeats.json", "sourceFamily": "additional-hosted-fresh-repeats", "sourceStage": "openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price-remaining7-price-v1/fresh1/P2" }, { "id": "extended-openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price-remaining7-price-v1-fresh2-p0", "experimentId": "extended-openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price-remaining7-price-v1-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-deepseek-high-remaining6-successor-findings-v1", "repeatPass": "fresh2", "model": "deepseek/deepseek-v4.1-flash", "effort": "high", "provider": "open-inference/fp4", "surface": "OpenRouter · open-inference/fp4", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 59, "metrics": { "all_four": 58, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": false, "resultStatus": "completed_with_intrinsic_invalid", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.031520474702, "estimatedUsd": null, "unknownUpperBoundUsd": 0.0, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-high-remaining6-successor-findings.json", "sourceRecordSha256": "85ba944ed1a3cf5e0b287b4680275852c472beaee2be000c32aa56472fd2e0a6", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-high-remaining6-successor-findings.json", "sourceFamily": "deepseek-high-remaining6-successor-findings", "sourceStage": "openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price-remaining7-price-v1/fresh2/P0" }, { "id": "extended-openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price-remaining7-price-v1-fresh2-p1", "experimentId": "extended-openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price-remaining7-price-v1-fresh2-p0", "parentBaselineId": "extended-openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price-remaining7-price-v1-fresh2-p0", "protocolId": "report-only-deepseek-high-remaining6-successor-findings-v1", "repeatPass": "fresh2", "model": "deepseek/deepseek-v4.1-flash", "effort": "high", "provider": "open-inference/fp4", "surface": "OpenRouter · open-inference/fp4", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": false, "resultStatus": "completed", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0277482953, "estimatedUsd": null, "unknownUpperBoundUsd": 0.0, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-high-remaining6-successor-findings.json", "sourceRecordSha256": "85ba944ed1a3cf5e0b287b4680275852c472beaee2be000c32aa56472fd2e0a6", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-high-remaining6-successor-findings.json", "sourceFamily": "deepseek-high-remaining6-successor-findings", "sourceStage": "openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price-remaining7-price-v1/fresh2/P1" }, { "id": "extended-openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price-remaining7-price-v1-fresh2-p2", "experimentId": "extended-openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price-remaining7-price-v1-fresh2-p0", "parentBaselineId": "extended-openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price-remaining7-price-v1-fresh2-p0", "protocolId": "report-only-deepseek-high-remaining6-successor-findings-v1", "repeatPass": "fresh2", "model": "deepseek/deepseek-v4.1-flash", "effort": "high", "provider": "open-inference/fp4", "surface": "OpenRouter · open-inference/fp4", "condition": "P2", "complete": false, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": null, "valid": 59, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 57, "testimonial_potential": 59 }, "pairedEligible": false, "resultStatus": "interrupted_composite_descriptive_only", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.02860903389, "estimatedUsd": null, "unknownUpperBoundUsd": 0.06905856, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-high-remaining6-successor-findings.json", "sourceRecordSha256": "85ba944ed1a3cf5e0b287b4680275852c472beaee2be000c32aa56472fd2e0a6", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-high-remaining6-successor-findings.json", "sourceFamily": "deepseek-high-remaining6-successor-findings", "sourceStage": "openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price-remaining7-price-v1/fresh2/P2" }, { "id": "extended-openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price-remaining7-price-v1-fresh3-p0", "experimentId": "extended-openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price-remaining7-price-v1-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-deepseek-high-remaining6-successor-findings-v1", "repeatPass": "fresh3", "model": "deepseek/deepseek-v4.1-flash", "effort": "high", "provider": "open-inference/fp4", "surface": "OpenRouter · open-inference/fp4", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 58, "metrics": { "all_four": 58, "sentiment": 58, "follow_up_needed": 58, "serious_concern_reported": 58, "testimonial_potential": 58 }, "pairedEligible": false, "resultStatus": "completed_with_intrinsic_invalid", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.036185557418, "estimatedUsd": null, "unknownUpperBoundUsd": 0.0, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-high-remaining6-successor-findings.json", "sourceRecordSha256": "85ba944ed1a3cf5e0b287b4680275852c472beaee2be000c32aa56472fd2e0a6", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-high-remaining6-successor-findings.json", "sourceFamily": "deepseek-high-remaining6-successor-findings", "sourceStage": "openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price-remaining7-price-v1/fresh3/P0" }, { "id": "extended-openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price-remaining7-price-v1-fresh3-p1", "experimentId": "extended-openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price-remaining7-price-v1-fresh3-p0", "parentBaselineId": "extended-openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price-remaining7-price-v1-fresh3-p0", "protocolId": "report-only-deepseek-high-remaining6-successor-findings-v1", "repeatPass": "fresh3", "model": "deepseek/deepseek-v4.1-flash", "effort": "high", "provider": "open-inference/fp4", "surface": "OpenRouter · open-inference/fp4", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": false, "resultStatus": "completed", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.02685414743, "estimatedUsd": null, "unknownUpperBoundUsd": 0.0, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-high-remaining6-successor-findings.json", "sourceRecordSha256": "85ba944ed1a3cf5e0b287b4680275852c472beaee2be000c32aa56472fd2e0a6", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-high-remaining6-successor-findings.json", "sourceFamily": "deepseek-high-remaining6-successor-findings", "sourceStage": "openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price-remaining7-price-v1/fresh3/P1" }, { "id": "extended-openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price-remaining7-price-v1-fresh3-p2", "experimentId": "extended-openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price-remaining7-price-v1-fresh3-p0", "parentBaselineId": "extended-openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price-remaining7-price-v1-fresh3-p0", "protocolId": "report-only-deepseek-high-remaining6-successor-findings-v1", "repeatPass": "fresh3", "model": "deepseek/deepseek-v4.1-flash", "effort": "high", "provider": "open-inference/fp4", "surface": "OpenRouter · open-inference/fp4", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": false, "resultStatus": "completed", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.031944583072, "estimatedUsd": null, "unknownUpperBoundUsd": 0.0, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-high-remaining6-successor-findings.json", "sourceRecordSha256": "85ba944ed1a3cf5e0b287b4680275852c472beaee2be000c32aa56472fd2e0a6", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-high-remaining6-successor-findings.json", "sourceFamily": "deepseek-high-remaining6-successor-findings", "sourceStage": "openrouter-paid-deepseek-v41-flash-high-authority-v3-current-price-remaining7-price-v1/fresh3/P2" }, { "id": "extended-openrouter-paid-deepseek-v41-flash-low-fresh1-p0", "experimentId": "extended-openrouter-paid-deepseek-v41-flash-low-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-additional-hosted-fresh-repeats-v1", "repeatPass": "fresh1", "model": "deepseek/deepseek-v4.1-flash", "effort": "low", "provider": "open-inference/fp4", "surface": "OpenRouter · open-inference/fp4", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 59, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 58, "serious_concern_reported": 58, "testimonial_potential": 59 }, "pairedEligible": false, "resultStatus": "completed", "timing": { "kind": "client_http_duration_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 4095.3547794609913, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 85717, "output": 32176, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.01743459, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts are observed provider usage charges; missing usage fields remain null." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/additional-hosted-fresh-repeats.json", "sourceRecordSha256": "cfd11bb576566097c6d351896e05578ffd6e1a35014011194d0d06fee0e85cf4", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/additional-hosted-fresh-repeats.json", "sourceFamily": "additional-hosted-fresh-repeats", "sourceStage": "openrouter-paid-deepseek-v41-flash-low/fresh1/P0" }, { "id": "extended-openrouter-paid-deepseek-v41-flash-low-fresh1-p1", "experimentId": "extended-openrouter-paid-deepseek-v41-flash-low-fresh1-p0", "parentBaselineId": "extended-openrouter-paid-deepseek-v41-flash-low-fresh1-p0", "protocolId": "report-only-additional-hosted-fresh-repeats-v1", "repeatPass": "fresh1", "model": "deepseek/deepseek-v4.1-flash", "effort": "low", "provider": "open-inference/fp4", "surface": "OpenRouter · open-inference/fp4", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_http_duration_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 2946.7763541678432, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 96337, "output": 21134, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.01165805, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts are observed provider usage charges; missing usage fields remain null." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/additional-hosted-fresh-repeats.json", "sourceRecordSha256": "cfd11bb576566097c6d351896e05578ffd6e1a35014011194d0d06fee0e85cf4", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/additional-hosted-fresh-repeats.json", "sourceFamily": "additional-hosted-fresh-repeats", "sourceStage": "openrouter-paid-deepseek-v41-flash-low/fresh1/P1" }, { "id": "extended-openrouter-paid-deepseek-v41-flash-low-fresh1-p2", "experimentId": "extended-openrouter-paid-deepseek-v41-flash-low-fresh1-p0", "parentBaselineId": "extended-openrouter-paid-deepseek-v41-flash-low-fresh1-p0", "protocolId": "report-only-deepseek-low-final-suffix-findings-v1", "repeatPass": "fresh1", "model": "deepseek/deepseek-v4.1-flash", "effort": "low", "provider": "open-inference/fp4", "surface": "OpenRouter · open-inference/fp4", "condition": "P2", "complete": false, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 57, "valid": 56, "metrics": { "all_four": 53, "sentiment": 56, "follow_up_needed": 54, "serious_concern_reported": 54, "testimonial_potential": 56 }, "pairedEligible": false, "resultStatus": "completed_interrupted_composite", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 4176.688540835938, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 144657, "output": 25527, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 57, "totalRequests": 60, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.017093728007, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-low-final-suffix-findings.json", "sourceRecordSha256": "ab856fca91fcff7aa3e81749c0bdeaef63f0cd9af20475fdefb0a6b0e691290b", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-low-final-suffix-findings.json", "sourceFamily": "deepseek-low-final-suffix-findings", "sourceStage": "openrouter-paid-deepseek-v41-flash-low/fresh1/P2" }, { "id": "extended-openrouter-paid-deepseek-v41-flash-low-remaining6-price-v2-fresh2-p0", "experimentId": "extended-openrouter-paid-deepseek-v41-flash-low-remaining6-price-v2-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-deepseek-low-fresh3-findings-v1", "repeatPass": "fresh2", "model": "deepseek/deepseek-v4.1-flash", "effort": "low", "provider": "open-inference/fp4", "surface": "OpenRouter · open-inference/fp4", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 59, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 58, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": false, "resultStatus": "completed", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.032199822671, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-low-fresh3-findings.json", "sourceRecordSha256": "bb9db920f74443d7e4b25b6b1f66e14b3f8ee97d67e7fc3eb2d154032821c97c", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-low-fresh3-findings.json", "sourceFamily": "deepseek-low-fresh3-findings", "sourceStage": "openrouter-paid-deepseek-v41-flash-low-remaining6-price-v2/fresh2/P0" }, { "id": "extended-openrouter-paid-deepseek-v41-flash-low-remaining6-price-v2-fresh2-p1", "experimentId": "extended-openrouter-paid-deepseek-v41-flash-low-remaining6-price-v2-fresh2-p0", "parentBaselineId": "extended-openrouter-paid-deepseek-v41-flash-low-remaining6-price-v2-fresh2-p0", "protocolId": "report-only-deepseek-low-p1-successor-findings-v1", "repeatPass": "fresh2", "model": "deepseek/deepseek-v4.1-flash", "effort": "low", "provider": "open-inference/fp4", "surface": "OpenRouter · open-inference/fp4", "condition": "P1", "complete": false, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 59, "valid": 57, "metrics": { "all_four": 57, "sentiment": 57, "follow_up_needed": 57, "serious_concern_reported": 57, "testimonial_potential": 57 }, "pairedEligible": false, "resultStatus": "interrupted_composite_closed", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.030730605596, "estimatedUsd": null, "unknownUpperBoundUsd": 0.06905856, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-low-p1-successor-findings.json", "sourceRecordSha256": "21e9f369afbbd877021843c77b679c6e3c9898e82037cb3edc7b2b358e95b67e", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-low-p1-successor-findings.json", "sourceFamily": "deepseek-low-p1-successor-findings", "sourceStage": "openrouter-paid-deepseek-v41-flash-low-remaining6-price-v2/fresh2/P1" }, { "id": "extended-openrouter-paid-deepseek-v41-flash-low-remaining6-price-v2-fresh2-p2", "experimentId": "extended-openrouter-paid-deepseek-v41-flash-low-remaining6-price-v2-fresh2-p0", "parentBaselineId": "extended-openrouter-paid-deepseek-v41-flash-low-remaining6-price-v2-fresh2-p0", "protocolId": "report-only-deepseek-low-remaining6-price-v2-findings-v1", "repeatPass": "fresh2", "model": "deepseek/deepseek-v4.1-flash", "effort": "low", "provider": "OpenInference fp4", "surface": "OpenRouter · OpenInference fp4", "condition": "P2", "complete": false, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": null, "valid": 59, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 58, "serious_concern_reported": 57, "testimonial_potential": 59 }, "pairedEligible": false, "resultStatus": "interrupted_composite_descriptive_only", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.030564226637, "estimatedUsd": null, "unknownUpperBoundUsd": 0.06905856, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-low-remaining6-price-v2-findings.json", "sourceRecordSha256": "e45c23c22e875fe5e12c6f8d3dfc9af32ca7f34243fdbdbdd49cfb9e7e17b088", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-low-remaining6-price-v2-findings.json", "sourceFamily": "deepseek-low-remaining6-price-v2-findings", "sourceStage": "openrouter-paid-deepseek-v41-flash-low-remaining6-price-v2/fresh2/P2" }, { "id": "extended-openrouter-paid-deepseek-v41-flash-low-remaining6-price-v2-fresh3-p0", "experimentId": "extended-openrouter-paid-deepseek-v41-flash-low-remaining6-price-v2-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-deepseek-low-fresh3-findings-v1", "repeatPass": "fresh3", "model": "deepseek/deepseek-v4.1-flash", "effort": "low", "provider": "open-inference/fp4", "surface": "OpenRouter · open-inference/fp4", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 59, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 58, "serious_concern_reported": 58, "testimonial_potential": 59 }, "pairedEligible": false, "resultStatus": "completed", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0288877038, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-low-fresh3-findings.json", "sourceRecordSha256": "bb9db920f74443d7e4b25b6b1f66e14b3f8ee97d67e7fc3eb2d154032821c97c", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-low-fresh3-findings.json", "sourceFamily": "deepseek-low-fresh3-findings", "sourceStage": "openrouter-paid-deepseek-v41-flash-low-remaining6-price-v2/fresh3/P0" }, { "id": "extended-openrouter-paid-deepseek-v41-flash-low-remaining6-price-v2-fresh3-p1", "experimentId": "extended-openrouter-paid-deepseek-v41-flash-low-remaining6-price-v2-fresh3-p0", "parentBaselineId": "extended-openrouter-paid-deepseek-v41-flash-low-remaining6-price-v2-fresh3-p0", "protocolId": "report-only-deepseek-low-fresh3-findings-v1", "repeatPass": "fresh3", "model": "deepseek/deepseek-v4.1-flash", "effort": "low", "provider": "open-inference/fp4", "surface": "OpenRouter · open-inference/fp4", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 59, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 57, "testimonial_potential": 59 }, "pairedEligible": false, "resultStatus": "completed", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.028986670052, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-low-fresh3-findings.json", "sourceRecordSha256": "bb9db920f74443d7e4b25b6b1f66e14b3f8ee97d67e7fc3eb2d154032821c97c", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-low-fresh3-findings.json", "sourceFamily": "deepseek-low-fresh3-findings", "sourceStage": "openrouter-paid-deepseek-v41-flash-low-remaining6-price-v2/fresh3/P1" }, { "id": "extended-openrouter-paid-deepseek-v41-flash-low-remaining6-price-v2-fresh3-p2", "experimentId": "extended-openrouter-paid-deepseek-v41-flash-low-remaining6-price-v2-fresh3-p0", "parentBaselineId": "extended-openrouter-paid-deepseek-v41-flash-low-remaining6-price-v2-fresh3-p0", "protocolId": "report-only-deepseek-low-fresh3-findings-v1", "repeatPass": "fresh3", "model": "deepseek/deepseek-v4.1-flash", "effort": "low", "provider": "open-inference/fp4", "surface": "OpenRouter · open-inference/fp4", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": false, "resultStatus": "completed", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0230379678, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-low-fresh3-findings.json", "sourceRecordSha256": "bb9db920f74443d7e4b25b6b1f66e14b3f8ee97d67e7fc3eb2d154032821c97c", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-low-fresh3-findings.json", "sourceFamily": "deepseek-low-fresh3-findings", "sourceStage": "openrouter-paid-deepseek-v41-flash-low-remaining6-price-v2/fresh3/P2" }, { "id": "extended-openrouter-paid-deepseek-v41-flash-off-fresh1-p0", "experimentId": "extended-openrouter-paid-deepseek-v41-flash-off-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-deepseek-fresh-repeats-v1", "repeatPass": "fresh1", "model": "deepseek/deepseek-v4.1-flash", "effort": "off", "provider": "open-inference/fp4", "surface": "OpenRouter · open-inference/fp4", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 48, "sentiment": 52, "follow_up_needed": 59, "serious_concern_reported": 57, "testimonial_potential": 55 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_http_duration_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 389.8813014550542, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 84217, "output": 2793, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0027523, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts are observed provider usage charges; missing usage fields remain null." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-fresh-repeats.json", "sourceRecordSha256": "df407ff4112b3e41e5c245579c6621a0ffdbcde966e6eb26d40ab6960278b6af", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-fresh-repeats.json", "sourceFamily": "deepseek-fresh-repeats", "sourceStage": "openrouter-paid-deepseek-v41-flash-off/fresh1/P0" }, { "id": "extended-openrouter-paid-deepseek-v41-flash-off-fresh1-p1", "experimentId": "extended-openrouter-paid-deepseek-v41-flash-off-fresh1-p0", "parentBaselineId": "extended-openrouter-paid-deepseek-v41-flash-off-fresh1-p0", "protocolId": "report-only-deepseek-fresh-repeats-v1", "repeatPass": "fresh1", "model": "deepseek/deepseek-v4.1-flash", "effort": "off", "provider": "open-inference/fp4", "surface": "OpenRouter · open-inference/fp4", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 47, "sentiment": 50, "follow_up_needed": 60, "serious_concern_reported": 57, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_http_duration_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 344.30765524707385, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 94837, "output": 2558, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.00297068, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts are observed provider usage charges; missing usage fields remain null." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-fresh-repeats.json", "sourceRecordSha256": "df407ff4112b3e41e5c245579c6621a0ffdbcde966e6eb26d40ab6960278b6af", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-fresh-repeats.json", "sourceFamily": "deepseek-fresh-repeats", "sourceStage": "openrouter-paid-deepseek-v41-flash-off/fresh1/P1" }, { "id": "extended-openrouter-paid-deepseek-v41-flash-off-fresh1-p2", "experimentId": "extended-openrouter-paid-deepseek-v41-flash-off-fresh1-p0", "parentBaselineId": "extended-openrouter-paid-deepseek-v41-flash-off-fresh1-p0", "protocolId": "report-only-deepseek-fresh-repeats-v1", "repeatPass": "fresh1", "model": "deepseek/deepseek-v4.1-flash", "effort": "off", "provider": "open-inference/fp4", "surface": "OpenRouter · open-inference/fp4", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 43, "sentiment": 47, "follow_up_needed": 60, "serious_concern_reported": 54, "testimonial_potential": 56 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_http_duration_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 373.04394937408506, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 149617, "output": 2560, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.00370515, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts are observed provider usage charges; missing usage fields remain null." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-fresh-repeats.json", "sourceRecordSha256": "df407ff4112b3e41e5c245579c6621a0ffdbcde966e6eb26d40ab6960278b6af", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-fresh-repeats.json", "sourceFamily": "deepseek-fresh-repeats", "sourceStage": "openrouter-paid-deepseek-v41-flash-off/fresh1/P2" }, { "id": "extended-openrouter-paid-deepseek-v41-flash-off-fresh2-p0", "experimentId": "extended-openrouter-paid-deepseek-v41-flash-off-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-deepseek-fresh-repeats-v1", "repeatPass": "fresh2", "model": "deepseek/deepseek-v4.1-flash", "effort": "off", "provider": "open-inference/fp4", "surface": "OpenRouter · open-inference/fp4", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 49, "sentiment": 53, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 55 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_http_duration_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 392.45291687501594, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 84217, "output": 2793, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.00265654, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts are observed provider usage charges; missing usage fields remain null." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-fresh-repeats.json", "sourceRecordSha256": "df407ff4112b3e41e5c245579c6621a0ffdbcde966e6eb26d40ab6960278b6af", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-fresh-repeats.json", "sourceFamily": "deepseek-fresh-repeats", "sourceStage": "openrouter-paid-deepseek-v41-flash-off/fresh2/P0" }, { "id": "extended-openrouter-paid-deepseek-v41-flash-off-fresh2-p1", "experimentId": "extended-openrouter-paid-deepseek-v41-flash-off-fresh2-p0", "parentBaselineId": "extended-openrouter-paid-deepseek-v41-flash-off-fresh2-p0", "protocolId": "report-only-deepseek-fresh-repeats-v1", "repeatPass": "fresh2", "model": "deepseek/deepseek-v4.1-flash", "effort": "off", "provider": "open-inference/fp4", "surface": "OpenRouter · open-inference/fp4", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 47, "sentiment": 49, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 56 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_http_duration_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 404.29162138313404, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 94837, "output": 2461, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.00277323, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts are observed provider usage charges; missing usage fields remain null." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-fresh-repeats.json", "sourceRecordSha256": "df407ff4112b3e41e5c245579c6621a0ffdbcde966e6eb26d40ab6960278b6af", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-fresh-repeats.json", "sourceFamily": "deepseek-fresh-repeats", "sourceStage": "openrouter-paid-deepseek-v41-flash-off/fresh2/P1" }, { "id": "extended-openrouter-paid-deepseek-v41-flash-off-fresh2-p2", "experimentId": "extended-openrouter-paid-deepseek-v41-flash-off-fresh2-p0", "parentBaselineId": "extended-openrouter-paid-deepseek-v41-flash-off-fresh2-p0", "protocolId": "report-only-deepseek-fresh-repeats-v1", "repeatPass": "fresh2", "model": "deepseek/deepseek-v4.1-flash", "effort": "off", "provider": "open-inference/fp4", "surface": "OpenRouter · open-inference/fp4", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 45, "sentiment": 48, "follow_up_needed": 60, "serious_concern_reported": 54, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_http_duration_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 408.73615933192195, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 149617, "output": 2521, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.00361167, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts are observed provider usage charges; missing usage fields remain null." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-fresh-repeats.json", "sourceRecordSha256": "df407ff4112b3e41e5c245579c6621a0ffdbcde966e6eb26d40ab6960278b6af", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-fresh-repeats.json", "sourceFamily": "deepseek-fresh-repeats", "sourceStage": "openrouter-paid-deepseek-v41-flash-off/fresh2/P2" }, { "id": "extended-openrouter-paid-deepseek-v41-flash-off-fresh3-p0", "experimentId": "extended-openrouter-paid-deepseek-v41-flash-off-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-deepseek-fresh-repeats-v1", "repeatPass": "fresh3", "model": "deepseek/deepseek-v4.1-flash", "effort": "off", "provider": "open-inference/fp4", "surface": "OpenRouter · open-inference/fp4", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 48, "sentiment": 52, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 55 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_http_duration_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 503.5666777479346, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 84217, "output": 2796, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.00273904, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts are observed provider usage charges; missing usage fields remain null." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-fresh-repeats.json", "sourceRecordSha256": "df407ff4112b3e41e5c245579c6621a0ffdbcde966e6eb26d40ab6960278b6af", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-fresh-repeats.json", "sourceFamily": "deepseek-fresh-repeats", "sourceStage": "openrouter-paid-deepseek-v41-flash-off/fresh3/P0" }, { "id": "extended-openrouter-paid-deepseek-v41-flash-off-fresh3-p1", "experimentId": "extended-openrouter-paid-deepseek-v41-flash-off-fresh3-p0", "parentBaselineId": "extended-openrouter-paid-deepseek-v41-flash-off-fresh3-p0", "protocolId": "report-only-deepseek-fresh-repeats-v1", "repeatPass": "fresh3", "model": "deepseek/deepseek-v4.1-flash", "effort": "off", "provider": "open-inference/fp4", "surface": "OpenRouter · open-inference/fp4", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 45, "sentiment": 49, "follow_up_needed": 60, "serious_concern_reported": 57, "testimonial_potential": 56 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_http_duration_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 484.3652176629985, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 94837, "output": 2545, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.00271965, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts are observed provider usage charges; missing usage fields remain null." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-fresh-repeats.json", "sourceRecordSha256": "df407ff4112b3e41e5c245579c6621a0ffdbcde966e6eb26d40ab6960278b6af", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-fresh-repeats.json", "sourceFamily": "deepseek-fresh-repeats", "sourceStage": "openrouter-paid-deepseek-v41-flash-off/fresh3/P1" }, { "id": "extended-openrouter-paid-deepseek-v41-flash-off-fresh3-p2", "experimentId": "extended-openrouter-paid-deepseek-v41-flash-off-fresh3-p0", "parentBaselineId": "extended-openrouter-paid-deepseek-v41-flash-off-fresh3-p0", "protocolId": "report-only-deepseek-fresh-repeats-v1", "repeatPass": "fresh3", "model": "deepseek/deepseek-v4.1-flash", "effort": "off", "provider": "open-inference/fp4", "surface": "OpenRouter · open-inference/fp4", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 46, "sentiment": 49, "follow_up_needed": 60, "serious_concern_reported": 55, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_http_duration_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 488.47291825388675, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 149617, "output": 2564, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.00378149, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts are observed provider usage charges; missing usage fields remain null." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-fresh-repeats.json", "sourceRecordSha256": "df407ff4112b3e41e5c245579c6621a0ffdbcde966e6eb26d40ab6960278b6af", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/deepseek-fresh-repeats.json", "sourceFamily": "deepseek-fresh-repeats", "sourceStage": "openrouter-paid-deepseek-v41-flash-off/fresh3/P2" }, { "id": "extended-openrouter-paid-gemma4-26b-a4b-off-repeat2-p0", "experimentId": "extended-openrouter-paid-gemma4-26b-a4b-off-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-hosted-repeats-v1", "repeatPass": "repeat2", "model": "google/gemma-4-26b-a4b-it", "effort": "off", "provider": "deepinfra/fp8", "surface": "OpenRouter · deepinfra/fp8", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 52, "sentiment": 58, "follow_up_needed": 58, "serious_concern_reported": 57, "testimonial_potential": 56 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 167.70712250297947, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 87688, "output": 2175, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.00687766, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceRecordSha256": "15d6b725a2300a2c4f6b6a5984b2abac5fd9f08587a326eda64d1c41147cf458", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceFamily": "hosted-repeats", "sourceStage": "openrouter-paid-gemma4-26b-a4b-off/repeat2/P0" }, { "id": "extended-openrouter-paid-gemma4-26b-a4b-off-repeat2-p1", "experimentId": "extended-openrouter-paid-gemma4-26b-a4b-off-repeat2-p0", "parentBaselineId": "extended-openrouter-paid-gemma4-26b-a4b-off-repeat2-p0", "protocolId": "report-only-hosted-repeats-v1", "repeatPass": "repeat2", "model": "google/gemma-4-26b-a4b-it", "effort": "off", "provider": "deepinfra/fp8", "surface": "OpenRouter · deepinfra/fp8", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 52, "sentiment": 56, "follow_up_needed": 58, "serious_concern_reported": 57, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 113.11440850200597, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 98488, "output": 2135, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.00762006, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceRecordSha256": "15d6b725a2300a2c4f6b6a5984b2abac5fd9f08587a326eda64d1c41147cf458", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceFamily": "hosted-repeats", "sourceStage": "openrouter-paid-gemma4-26b-a4b-off/repeat2/P1" }, { "id": "extended-openrouter-paid-gemma4-26b-a4b-off-repeat2-p2", "experimentId": "extended-openrouter-paid-gemma4-26b-a4b-off-repeat2-p0", "parentBaselineId": "extended-openrouter-paid-gemma4-26b-a4b-off-repeat2-p0", "protocolId": "report-only-hosted-repeats-v1", "repeatPass": "repeat2", "model": "google/gemma-4-26b-a4b-it", "effort": "off", "provider": "deepinfra/fp8", "surface": "OpenRouter · deepinfra/fp8", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 51, "sentiment": 57, "follow_up_needed": 57, "serious_concern_reported": 58, "testimonial_potential": 56 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 258.5262712479889, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 154348, "output": 2176, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0115442, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceRecordSha256": "15d6b725a2300a2c4f6b6a5984b2abac5fd9f08587a326eda64d1c41147cf458", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceFamily": "hosted-repeats", "sourceStage": "openrouter-paid-gemma4-26b-a4b-off/repeat2/P2" }, { "id": "extended-openrouter-paid-gemma4-26b-a4b-off-repeat3-p0", "experimentId": "extended-openrouter-paid-gemma4-26b-a4b-off-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-hosted-repeats-v1", "repeatPass": "repeat3", "model": "google/gemma-4-26b-a4b-it", "effort": "off", "provider": "deepinfra/fp8", "surface": "OpenRouter · deepinfra/fp8", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 52, "sentiment": 58, "follow_up_needed": 58, "serious_concern_reported": 57, "testimonial_potential": 56 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 115.46311574701394, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 87688, "output": 2174, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.00687732, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceRecordSha256": "15d6b725a2300a2c4f6b6a5984b2abac5fd9f08587a326eda64d1c41147cf458", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceFamily": "hosted-repeats", "sourceStage": "openrouter-paid-gemma4-26b-a4b-off/repeat3/P0" }, { "id": "extended-openrouter-paid-gemma4-26b-a4b-off-repeat3-p1", "experimentId": "extended-openrouter-paid-gemma4-26b-a4b-off-repeat3-p0", "parentBaselineId": "extended-openrouter-paid-gemma4-26b-a4b-off-repeat3-p0", "protocolId": "report-only-hosted-repeats-v1", "repeatPass": "repeat3", "model": "google/gemma-4-26b-a4b-it", "effort": "off", "provider": "deepinfra/fp8", "surface": "OpenRouter · deepinfra/fp8", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 52, "sentiment": 56, "follow_up_needed": 58, "serious_concern_reported": 58, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 130.7303007090377, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 98488, "output": 2128, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.00761768, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceRecordSha256": "15d6b725a2300a2c4f6b6a5984b2abac5fd9f08587a326eda64d1c41147cf458", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceFamily": "hosted-repeats", "sourceStage": "openrouter-paid-gemma4-26b-a4b-off/repeat3/P1" }, { "id": "extended-openrouter-paid-gemma4-26b-a4b-off-repeat3-p2", "experimentId": "extended-openrouter-paid-gemma4-26b-a4b-off-repeat3-p0", "parentBaselineId": "extended-openrouter-paid-gemma4-26b-a4b-off-repeat3-p0", "protocolId": "report-only-hosted-repeats-v1", "repeatPass": "repeat3", "model": "google/gemma-4-26b-a4b-it", "effort": "off", "provider": "deepinfra/fp8", "surface": "OpenRouter · deepinfra/fp8", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 53, "sentiment": 58, "follow_up_needed": 57, "serious_concern_reported": 58, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 160.73304429199197, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 154348, "output": 2177, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.01154454, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceRecordSha256": "15d6b725a2300a2c4f6b6a5984b2abac5fd9f08587a326eda64d1c41147cf458", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceFamily": "hosted-repeats", "sourceStage": "openrouter-paid-gemma4-26b-a4b-off/repeat3/P2" }, { "id": "extended-openrouter-paid-gemma4-26b-a4b-on-fresh1-p0", "experimentId": "extended-openrouter-paid-gemma4-26b-a4b-on-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-hosted-v2-repeats-v1", "repeatPass": "fresh1", "model": "google/gemma-4-26b-a4b-it", "effort": "on", "provider": "deepinfra/fp8", "surface": "OpenRouter · deepinfra/fp8", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 59, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_request_to_record_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 1110.180834415136, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 87568, "output": 38773, "cachedInput": null, "cacheWrite": null, "reasoning": 39273, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.01931258, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-v2-repeats.json", "sourceRecordSha256": "f385e8a5f969c1d0bea269e6a3279a84eaadd3e45f2dbe20a6d71f2bafaacceb", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-v2-repeats.json", "sourceFamily": "hosted-v2-repeats", "sourceStage": "openrouter-paid-gemma4-26b-a4b-on/fresh1/P0" }, { "id": "extended-openrouter-paid-gemma4-26b-a4b-on-fresh1-p1", "experimentId": "extended-openrouter-paid-gemma4-26b-a4b-on-fresh1-p0", "parentBaselineId": "extended-openrouter-paid-gemma4-26b-a4b-on-fresh1-p0", "protocolId": "report-only-hosted-v2-repeats-v1", "repeatPass": "fresh1", "model": "google/gemma-4-26b-a4b-it", "effort": "on", "provider": "deepinfra/fp8", "surface": "OpenRouter · deepinfra/fp8", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_request_to_record_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 1162.1422725440934, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 98368, "output": 39977, "cachedInput": null, "cacheWrite": null, "reasoning": 40426, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.02047794, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-v2-repeats.json", "sourceRecordSha256": "f385e8a5f969c1d0bea269e6a3279a84eaadd3e45f2dbe20a6d71f2bafaacceb", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-v2-repeats.json", "sourceFamily": "hosted-v2-repeats", "sourceStage": "openrouter-paid-gemma4-26b-a4b-on/fresh1/P1" }, { "id": "extended-openrouter-paid-gemma4-26b-a4b-on-fresh1-p2", "experimentId": "extended-openrouter-paid-gemma4-26b-a4b-on-fresh1-p0", "parentBaselineId": "extended-openrouter-paid-gemma4-26b-a4b-on-fresh1-p0", "protocolId": "report-only-gemma26-continuation-findings-v1", "repeatPass": "fresh1", "model": "google/gemma-4-26b-a4b-it", "effort": "on", "provider": "deepinfra/fp8", "surface": "OpenRouter · deepinfra/fp8", "condition": "P2", "complete": false, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 59, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 58, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": false, "resultStatus": "completed_interrupted", "timing": { "kind": "client_request_to_record_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 855.6874257888412, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": 60, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.02346166, "estimatedUsd": null, "unknownUpperBoundUsd": 0.01974272, "unknownCostCount": 1, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemma26-continuation-findings.json", "sourceRecordSha256": "cce3d6d24e1708960ffe16158016017d8d28cbcdc2a5deb60e76e47b51cb32e7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemma26-continuation-findings.json", "sourceFamily": "gemma26-continuation-findings", "sourceStage": "openrouter-paid-gemma4-26b-a4b-on/fresh1/P2" }, { "id": "extended-openrouter-paid-gemma4-26b-a4b-on-fresh2-p0", "experimentId": "extended-openrouter-paid-gemma4-26b-a4b-on-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-gemma26-second-continuation-findings-v1", "repeatPass": "fresh2", "model": "google/gemma-4-26b-a4b-it", "effort": "on", "provider": "deepinfra/fp8", "surface": "OpenRouter · deepinfra/fp8", "condition": "P0", "complete": false, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 59, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 58 }, "pairedEligible": false, "resultStatus": "completed_composite_interrupted", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemma26-second-continuation-findings.json", "sourceRecordSha256": "f23d805f23117d39da1e1229d2bc2516eb667e1d17c355bc7ab5223c9bbb8ee0", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemma26-second-continuation-findings.json", "sourceFamily": "gemma26-second-continuation-findings", "sourceStage": "openrouter-paid-gemma4-26b-a4b-on/fresh2/P0" }, { "id": "extended-openrouter-paid-gemma4-26b-a4b-on-fresh2-p1", "experimentId": "extended-openrouter-paid-gemma4-26b-a4b-on-fresh2-p0", "parentBaselineId": "extended-openrouter-paid-gemma4-26b-a4b-on-fresh2-p0", "protocolId": "report-only-gemma26-continuation-findings-v1", "repeatPass": "fresh2", "model": "google/gemma-4-26b-a4b-it", "effort": "on", "provider": "deepinfra/fp8", "surface": "OpenRouter · deepinfra/fp8", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": false, "resultStatus": "completed", "timing": { "kind": "client_request_to_record_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 1119.2660323308664, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": 60, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0206884, "estimatedUsd": null, "unknownUpperBoundUsd": 0.0, "unknownCostCount": 0, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemma26-continuation-findings.json", "sourceRecordSha256": "cce3d6d24e1708960ffe16158016017d8d28cbcdc2a5deb60e76e47b51cb32e7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemma26-continuation-findings.json", "sourceFamily": "gemma26-continuation-findings", "sourceStage": "openrouter-paid-gemma4-26b-a4b-on/fresh2/P1" }, { "id": "extended-openrouter-paid-gemma4-26b-a4b-on-fresh2-p2", "experimentId": "extended-openrouter-paid-gemma4-26b-a4b-on-fresh2-p0", "parentBaselineId": "extended-openrouter-paid-gemma4-26b-a4b-on-fresh2-p0", "protocolId": "report-only-gemma26-continuation-findings-v1", "repeatPass": "fresh2", "model": "google/gemma-4-26b-a4b-it", "effort": "on", "provider": "deepinfra/fp8", "surface": "OpenRouter · deepinfra/fp8", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 58, "serious_concern_reported": 60, "testimonial_potential": 60 }, "pairedEligible": false, "resultStatus": "completed", "timing": { "kind": "client_request_to_record_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 960.4090177450562, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": 60, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.02368094, "estimatedUsd": null, "unknownUpperBoundUsd": 0.0, "unknownCostCount": 0, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemma26-continuation-findings.json", "sourceRecordSha256": "cce3d6d24e1708960ffe16158016017d8d28cbcdc2a5deb60e76e47b51cb32e7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemma26-continuation-findings.json", "sourceFamily": "gemma26-continuation-findings", "sourceStage": "openrouter-paid-gemma4-26b-a4b-on/fresh2/P2" }, { "id": "extended-openrouter-paid-gemma4-26b-a4b-on-fresh3-p0", "experimentId": "extended-openrouter-paid-gemma4-26b-a4b-on-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-gemma26-fresh3-p0-checkpoint-v1", "repeatPass": "fresh3", "model": "google/gemma-4-26b-a4b-it", "effort": "on", "provider": "deepinfra/fp8", "surface": "OpenRouter · deepinfra/fp8", "condition": "P0", "complete": false, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 60 }, "pairedEligible": false, "resultStatus": "completed_interrupted_composite", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemma26-fresh3-p0-checkpoint.json", "sourceRecordSha256": "89cdf0bb3dcc82c4aa90662b4994067c8faa99b7c16b9244ef07d14394bdd8bf", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemma26-fresh3-p0-checkpoint.json", "sourceFamily": "gemma26-fresh3-p0-checkpoint", "sourceStage": "openrouter-paid-gemma4-26b-a4b-on/fresh3/P0" }, { "id": "extended-openrouter-paid-gemma4-26b-a4b-on-fresh3-p1", "experimentId": "extended-openrouter-paid-gemma4-26b-a4b-on-fresh3-p0", "parentBaselineId": "extended-openrouter-paid-gemma4-26b-a4b-on-fresh3-p0", "protocolId": "report-only-gemma26-fresh3-p1-interrupted-checkpoint-v1", "repeatPass": "fresh3", "model": "google/gemma-4-26b-a4b-it", "effort": "on", "provider": "deepinfra/fp8", "surface": "OpenRouter · deepinfra/fp8", "condition": "P1", "complete": false, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 59, "metrics": { "all_four": 57, "sentiment": 57, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 59 }, "pairedEligible": false, "resultStatus": "completed_interrupted_composite", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemma26-fresh3-p1-interrupted-checkpoint.json", "sourceRecordSha256": "2dab60820ffde5c4e31b871bf95a31d975ca28663ec2a6ad0cc22eca4b770176", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemma26-fresh3-p1-interrupted-checkpoint.json", "sourceFamily": "gemma26-fresh3-p1-interrupted-checkpoint", "sourceStage": "openrouter-paid-gemma4-26b-a4b-on/fresh3/P1" }, { "id": "extended-openrouter-paid-gemma4-26b-a4b-on-fresh3-p2", "experimentId": "extended-openrouter-paid-gemma4-26b-a4b-on-fresh3-p0", "parentBaselineId": "extended-openrouter-paid-gemma4-26b-a4b-on-fresh3-p0", "protocolId": "report-only-gemma26-p2-repeat-findings-v1", "repeatPass": "fresh3", "model": "google/gemma-4-26b-a4b-it", "effort": "on", "provider": "deepinfra/fp8", "surface": "OpenRouter · deepinfra/fp8", "condition": "P2", "complete": false, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 58, "metrics": { "all_four": 56, "sentiment": 57, "follow_up_needed": 57, "serious_concern_reported": 58, "testimonial_potential": 58 }, "pairedEligible": false, "resultStatus": "completed_interrupted_composite", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemma26-p2-repeat-findings.json", "sourceRecordSha256": "f595203141acf14ab9994e39d329ad177fdd79a429fa17844af553728c448fd9", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/gemma26-p2-repeat-findings.json", "sourceFamily": "gemma26-p2-repeat-findings", "sourceStage": "openrouter-paid-gemma4-26b-a4b-on/fresh3/P2" }, { "id": "extended-openrouter-paid-gemma4-31b-off-repeat2-p0", "experimentId": "extended-openrouter-paid-gemma4-31b-off-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-hosted-repeats-v1", "repeatPass": "repeat2", "model": "google/gemma-4-31b-it", "effort": "off", "provider": "deepinfra/turbo", "surface": "OpenRouter · deepinfra/turbo", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 55, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 108.61095488003048, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 87688, "output": 2660, "cachedInput": 82688, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0054888, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceRecordSha256": "15d6b725a2300a2c4f6b6a5984b2abac5fd9f08587a326eda64d1c41147cf458", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceFamily": "hosted-repeats", "sourceStage": "openrouter-paid-gemma4-31b-off/repeat2/P0" }, { "id": "extended-openrouter-paid-gemma4-31b-off-repeat2-p1", "experimentId": "extended-openrouter-paid-gemma4-31b-off-repeat2-p0", "parentBaselineId": "extended-openrouter-paid-gemma4-31b-off-repeat2-p0", "protocolId": "report-only-hosted-repeats-v1", "repeatPass": "repeat2", "model": "google/gemma-4-31b-it", "effort": "off", "provider": "deepinfra/turbo", "surface": "OpenRouter · deepinfra/turbo", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 54, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 113.55757425104093, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 98488, "output": 2352, "cachedInput": 90944, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.00602584, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceRecordSha256": "15d6b725a2300a2c4f6b6a5984b2abac5fd9f08587a326eda64d1c41147cf458", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceFamily": "hosted-repeats", "sourceStage": "openrouter-paid-gemma4-31b-off/repeat2/P1" }, { "id": "extended-openrouter-paid-gemma4-31b-off-repeat2-p2", "experimentId": "extended-openrouter-paid-gemma4-31b-off-repeat2-p0", "parentBaselineId": "extended-openrouter-paid-gemma4-31b-off-repeat2-p0", "protocolId": "report-only-hosted-repeats-v1", "repeatPass": "repeat2", "model": "google/gemma-4-31b-it", "effort": "off", "provider": "deepinfra/turbo", "surface": "OpenRouter · deepinfra/turbo", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 137.78086750196235, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 154348, "output": 2586, "cachedInput": 138848, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.00921664, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceRecordSha256": "15d6b725a2300a2c4f6b6a5984b2abac5fd9f08587a326eda64d1c41147cf458", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceFamily": "hosted-repeats", "sourceStage": "openrouter-paid-gemma4-31b-off/repeat2/P2" }, { "id": "extended-openrouter-paid-gemma4-31b-off-repeat3-p0", "experimentId": "extended-openrouter-paid-gemma4-31b-off-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-hosted-repeats-v1", "repeatPass": "repeat3", "model": "google/gemma-4-31b-it", "effort": "off", "provider": "deepinfra/turbo", "surface": "OpenRouter · deepinfra/turbo", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 55, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 110.14073325399659, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 87688, "output": 2674, "cachedInput": 81472, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0055422, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceRecordSha256": "15d6b725a2300a2c4f6b6a5984b2abac5fd9f08587a326eda64d1c41147cf458", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceFamily": "hosted-repeats", "sourceStage": "openrouter-paid-gemma4-31b-off/repeat3/P0" }, { "id": "extended-openrouter-paid-gemma4-31b-off-repeat3-p1", "experimentId": "extended-openrouter-paid-gemma4-31b-off-repeat3-p0", "parentBaselineId": "extended-openrouter-paid-gemma4-31b-off-repeat3-p0", "protocolId": "report-only-hosted-repeats-v1", "repeatPass": "repeat3", "model": "google/gemma-4-31b-it", "effort": "off", "provider": "deepinfra/turbo", "surface": "OpenRouter · deepinfra/turbo", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 54, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 102.91889491995971, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 98488, "output": 2300, "cachedInput": 89472, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.00606704, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceRecordSha256": "15d6b725a2300a2c4f6b6a5984b2abac5fd9f08587a326eda64d1c41147cf458", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceFamily": "hosted-repeats", "sourceStage": "openrouter-paid-gemma4-31b-off/repeat3/P1" }, { "id": "extended-openrouter-paid-gemma4-31b-off-repeat3-p2", "experimentId": "extended-openrouter-paid-gemma4-31b-off-repeat3-p0", "parentBaselineId": "extended-openrouter-paid-gemma4-31b-off-repeat3-p0", "protocolId": "report-only-hosted-repeats-v1", "repeatPass": "repeat3", "model": "google/gemma-4-31b-it", "effort": "off", "provider": "deepinfra/turbo", "surface": "OpenRouter · deepinfra/turbo", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 54, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 148.05281333398307, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 154348, "output": 2495, "cachedInput": 136512, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.00927914, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceRecordSha256": "15d6b725a2300a2c4f6b6a5984b2abac5fd9f08587a326eda64d1c41147cf458", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceFamily": "hosted-repeats", "sourceStage": "openrouter-paid-gemma4-31b-off/repeat3/P2" }, { "id": "extended-openrouter-paid-gemma4-31b-on-repeat2-p0", "experimentId": "extended-openrouter-paid-gemma4-31b-on-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-hosted-repeats-v1", "repeatPass": "repeat2", "model": "google/gemma-4-31b-it", "effort": "on", "provider": "deepinfra/turbo", "surface": "OpenRouter · deepinfra/turbo", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 57, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 753.0196292030596, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 87568, "output": 26374, "cachedInput": 79136, "cacheWrite": 0, "reasoning": 25873, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.01368284, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceRecordSha256": "15d6b725a2300a2c4f6b6a5984b2abac5fd9f08587a326eda64d1c41147cf458", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceFamily": "hosted-repeats", "sourceStage": "openrouter-paid-gemma4-31b-on/repeat2/P0" }, { "id": "extended-openrouter-paid-gemma4-31b-on-repeat2-p1", "experimentId": "extended-openrouter-paid-gemma4-31b-on-repeat2-p0", "parentBaselineId": "extended-openrouter-paid-gemma4-31b-on-repeat2-p0", "protocolId": "report-only-hosted-repeats-v1", "repeatPass": "repeat2", "model": "google/gemma-4-31b-it", "effort": "on", "provider": "deepinfra/turbo", "surface": "OpenRouter · deepinfra/turbo", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 653.3055744599842, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 98368, "output": 26267, "cachedInput": 94272, "cacheWrite": 0, "reasoning": 25393, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.01401302, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceRecordSha256": "15d6b725a2300a2c4f6b6a5984b2abac5fd9f08587a326eda64d1c41147cf458", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceFamily": "hosted-repeats", "sourceStage": "openrouter-paid-gemma4-31b-on/repeat2/P1" }, { "id": "extended-openrouter-paid-gemma4-31b-on-repeat2-p2", "experimentId": "extended-openrouter-paid-gemma4-31b-on-repeat2-p0", "parentBaselineId": "extended-openrouter-paid-gemma4-31b-on-repeat2-p0", "protocolId": "report-only-hosted-repeats-v1", "repeatPass": "repeat2", "model": "google/gemma-4-31b-it", "effort": "on", "provider": "deepinfra/turbo", "surface": "OpenRouter · deepinfra/turbo", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 568.7136002530751, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 154228, "output": 26482, "cachedInput": 151520, "cacheWrite": 0, "reasoning": 25324, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0168236, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceRecordSha256": "15d6b725a2300a2c4f6b6a5984b2abac5fd9f08587a326eda64d1c41147cf458", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceFamily": "hosted-repeats", "sourceStage": "openrouter-paid-gemma4-31b-on/repeat2/P2" }, { "id": "extended-openrouter-paid-gemma4-31b-on-repeat3-p0", "experimentId": "extended-openrouter-paid-gemma4-31b-on-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-hosted-repeats-v1", "repeatPass": "repeat3", "model": "google/gemma-4-31b-it", "effort": "on", "provider": "deepinfra/turbo", "surface": "OpenRouter · deepinfra/turbo", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 753.4823296619725, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 87568, "output": 24348, "cachedInput": 80800, "cacheWrite": 0, "reasoning": 23756, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.01292744, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceRecordSha256": "15d6b725a2300a2c4f6b6a5984b2abac5fd9f08587a326eda64d1c41147cf458", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceFamily": "hosted-repeats", "sourceStage": "openrouter-paid-gemma4-31b-on/repeat3/P0" }, { "id": "extended-openrouter-paid-gemma4-31b-on-repeat3-p1", "experimentId": "extended-openrouter-paid-gemma4-31b-on-repeat3-p0", "parentBaselineId": "extended-openrouter-paid-gemma4-31b-on-repeat3-p0", "protocolId": "report-only-hosted-repeats-v1", "repeatPass": "repeat3", "model": "google/gemma-4-31b-it", "effort": "on", "provider": "deepinfra/turbo", "surface": "OpenRouter · deepinfra/turbo", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 476.60655325010885, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 98368, "output": 26688, "cachedInput": 96032, "cacheWrite": 0, "reasoning": 26088, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.01408576, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceRecordSha256": "15d6b725a2300a2c4f6b6a5984b2abac5fd9f08587a326eda64d1c41147cf458", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceFamily": "hosted-repeats", "sourceStage": "openrouter-paid-gemma4-31b-on/repeat3/P1" }, { "id": "extended-openrouter-paid-gemma4-31b-on-repeat3-p2", "experimentId": "extended-openrouter-paid-gemma4-31b-on-repeat3-p0", "parentBaselineId": "extended-openrouter-paid-gemma4-31b-on-repeat3-p0", "protocolId": "report-only-hosted-repeats-v1", "repeatPass": "repeat3", "model": "google/gemma-4-31b-it", "effort": "on", "provider": "deepinfra/turbo", "surface": "OpenRouter · deepinfra/turbo", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 743.1123756260495, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 154228, "output": 25187, "cachedInput": 138368, "cacheWrite": 0, "reasoning": 24071, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.01690938, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceRecordSha256": "15d6b725a2300a2c4f6b6a5984b2abac5fd9f08587a326eda64d1c41147cf458", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceFamily": "hosted-repeats", "sourceStage": "openrouter-paid-gemma4-31b-on/repeat3/P2" }, { "id": "extended-openrouter-paid-mistral-small32-24b-venice-not-applicable-repeat2-p0", "experimentId": "extended-openrouter-paid-mistral-small32-24b-venice-not-applicable-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-hosted-repeats-v1", "repeatPass": "repeat2", "model": "mistralai/mistral-small-3.2-24b-instruct", "effort": "na", "provider": "venice/fp8", "surface": "OpenRouter · venice/fp8", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 47, "sentiment": 54, "follow_up_needed": 57, "serious_concern_reported": 54, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 153.5296520019183, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 85851, "output": 2727, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.00873028125, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceRecordSha256": "15d6b725a2300a2c4f6b6a5984b2abac5fd9f08587a326eda64d1c41147cf458", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceFamily": "hosted-repeats", "sourceStage": "openrouter-paid-mistral-small32-24b-venice-not-applicable/repeat2/P0" }, { "id": "extended-openrouter-paid-mistral-small32-24b-venice-not-applicable-repeat2-p1", "experimentId": "extended-openrouter-paid-mistral-small32-24b-venice-not-applicable-repeat2-p0", "parentBaselineId": "extended-openrouter-paid-mistral-small32-24b-venice-not-applicable-repeat2-p0", "protocolId": "report-only-hosted-repeats-v1", "repeatPass": "repeat2", "model": "mistralai/mistral-small-3.2-24b-instruct", "effort": "na", "provider": "venice/fp8", "surface": "OpenRouter · venice/fp8", "condition": "P1", "complete": false, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 59, "valid": 59, "metrics": { "all_four": 46, "sentiment": 53, "follow_up_needed": 56, "serious_concern_reported": 52, "testimonial_potential": 58 }, "pairedEligible": false, "resultStatus": "partial", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 176.51716700092948, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": 60, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.009567375, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 1, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceRecordSha256": "15d6b725a2300a2c4f6b6a5984b2abac5fd9f08587a326eda64d1c41147cf458", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceFamily": "hosted-repeats", "sourceStage": "openrouter-paid-mistral-small32-24b-venice-not-applicable/repeat2/P1" }, { "id": "extended-openrouter-paid-mistral-small32-24b-venice-not-applicable-repeat2-p2", "experimentId": "extended-openrouter-paid-mistral-small32-24b-venice-not-applicable-repeat2-p0", "parentBaselineId": "extended-openrouter-paid-mistral-small32-24b-venice-not-applicable-repeat2-p0", "protocolId": "report-only-hosted-repeats-v1", "repeatPass": "repeat2", "model": "mistralai/mistral-small-3.2-24b-instruct", "effort": "na", "provider": "venice/fp8", "surface": "OpenRouter · venice/fp8", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 46, "sentiment": 53, "follow_up_needed": 57, "serious_concern_reported": 54, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 230.18961566897633, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 152451, "output": 2737, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.01497653125, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceRecordSha256": "15d6b725a2300a2c4f6b6a5984b2abac5fd9f08587a326eda64d1c41147cf458", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceFamily": "hosted-repeats", "sourceStage": "openrouter-paid-mistral-small32-24b-venice-not-applicable/repeat2/P2" }, { "id": "extended-openrouter-paid-mistral-small32-24b-venice-not-applicable-repeat3-p0", "experimentId": "extended-openrouter-paid-mistral-small32-24b-venice-not-applicable-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-hosted-repeats-v1", "repeatPass": "repeat3", "model": "mistralai/mistral-small-3.2-24b-instruct", "effort": "na", "provider": "venice/fp8", "surface": "OpenRouter · venice/fp8", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 47, "sentiment": 54, "follow_up_needed": 57, "serious_concern_reported": 54, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 102.69979925596272, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 85851, "output": 2727, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.00873028125, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceRecordSha256": "15d6b725a2300a2c4f6b6a5984b2abac5fd9f08587a326eda64d1c41147cf458", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceFamily": "hosted-repeats", "sourceStage": "openrouter-paid-mistral-small32-24b-venice-not-applicable/repeat3/P0" }, { "id": "extended-openrouter-paid-mistral-small32-24b-venice-not-applicable-repeat3-p1", "experimentId": "extended-openrouter-paid-mistral-small32-24b-venice-not-applicable-repeat3-p0", "parentBaselineId": "extended-openrouter-paid-mistral-small32-24b-venice-not-applicable-repeat3-p0", "protocolId": "report-only-hosted-repeats-v1", "repeatPass": "repeat3", "model": "mistralai/mistral-small-3.2-24b-instruct", "effort": "na", "provider": "venice/fp8", "surface": "OpenRouter · venice/fp8", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 45, "sentiment": 54, "follow_up_needed": 57, "serious_concern_reported": 52, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 162.17044849792728, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 96591, "output": 2687, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.00972715625, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceRecordSha256": "15d6b725a2300a2c4f6b6a5984b2abac5fd9f08587a326eda64d1c41147cf458", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceFamily": "hosted-repeats", "sourceStage": "openrouter-paid-mistral-small32-24b-venice-not-applicable/repeat3/P1" }, { "id": "extended-openrouter-paid-mistral-small32-24b-venice-not-applicable-repeat3-p2", "experimentId": "extended-openrouter-paid-mistral-small32-24b-venice-not-applicable-repeat3-p0", "parentBaselineId": "extended-openrouter-paid-mistral-small32-24b-venice-not-applicable-repeat3-p0", "protocolId": "report-only-hosted-repeats-v1", "repeatPass": "repeat3", "model": "mistralai/mistral-small-3.2-24b-instruct", "effort": "na", "provider": "venice/fp8", "surface": "OpenRouter · venice/fp8", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 46, "sentiment": 53, "follow_up_needed": 57, "serious_concern_reported": 54, "testimonial_potential": 56 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 210.5185889179702, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 152451, "output": 2731, "cachedInput": 0, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.01497503125, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceRecordSha256": "15d6b725a2300a2c4f6b6a5984b2abac5fd9f08587a326eda64d1c41147cf458", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceFamily": "hosted-repeats", "sourceStage": "openrouter-paid-mistral-small32-24b-venice-not-applicable/repeat3/P2" }, { "id": "extended-openrouter-paid-mistral-small4-119b-none-fresh1-p0", "experimentId": "extended-openrouter-paid-mistral-small4-119b-none-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-mistral119-fresh1-p0-findings-v1", "repeatPass": "fresh1", "model": "mistralai/mistral-small-2603", "effort": "none", "provider": "mistral/zdr", "surface": "OpenRouter · mistral/zdr", "condition": "P0", "complete": false, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 55, "valid": 55, "metrics": { "all_four": 40, "sentiment": 46, "follow_up_needed": 52, "serious_concern_reported": 48, "testimonial_potential": 51 }, "pairedEligible": false, "resultStatus": "partial_unscored_as_repeat", "timing": { "kind": "unavailable", "requests": 55, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 79.517, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 78702, "output": 2164, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 55, "totalRequests": 60, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.005084835, "estimatedUsd": null, "unknownUpperBoundUsd": 0.208896, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/mistral119-fresh1-p0-findings.json", "sourceRecordSha256": "12deeac00c9a044fe3a66b28399fb27a147ac153225eb3d02376c3d1d53052d2", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/mistral119-fresh1-p0-findings.json", "sourceFamily": "mistral119-fresh1-p0-findings", "sourceStage": "openrouter-paid-mistral-small4-119b-none/fresh1/P0" }, { "id": "extended-openrouter-paid-qwen3.8-27b-medium-fresh1-p0", "experimentId": "extended-openrouter-paid-qwen3.8-27b-medium-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-qwen27-final-descriptive-findings-v1", "repeatPass": "fresh1", "model": "qwen/qwen3.8-27b", "effort": "medium", "provider": "deepinfra/bf16", "surface": "OpenRouter · deepinfra/bf16", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 59 }, "pairedEligible": false, "resultStatus": "completed", "timing": { "kind": "client_request_to_record_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 907.4547947900137, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 85830, "output": 30813, "cachedInput": null, "cacheWrite": null, "reasoning": 35987, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.066327075, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceRecordSha256": "008fa43be645b4414a57e3e0783d6e5fc0bf428c09fa1bd5771fd064b93b1c42", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceFamily": "qwen27-final-descriptive-findings", "sourceStage": "openrouter-paid-qwen3.8-27b-medium/fresh1/P0" }, { "id": "extended-openrouter-paid-qwen3.8-27b-medium-fresh1-p1", "experimentId": "extended-openrouter-paid-qwen3.8-27b-medium-fresh1-p0", "parentBaselineId": "extended-openrouter-paid-qwen3.8-27b-medium-fresh1-p0", "protocolId": "report-only-qwen27-final-descriptive-findings-v1", "repeatPass": "fresh1", "model": "qwen/qwen3.8-27b", "effort": "medium", "provider": "deepinfra/bf16", "surface": "OpenRouter · deepinfra/bf16", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 54, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 58 }, "pairedEligible": false, "resultStatus": "completed", "timing": { "kind": "client_request_to_record_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 877.7168087480823, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 96450, "output": 28740, "cachedInput": null, "cacheWrite": null, "reasoning": 33787, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0597114, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceRecordSha256": "008fa43be645b4414a57e3e0783d6e5fc0bf428c09fa1bd5771fd064b93b1c42", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceFamily": "qwen27-final-descriptive-findings", "sourceStage": "openrouter-paid-qwen3.8-27b-medium/fresh1/P1" }, { "id": "extended-openrouter-paid-qwen3.8-27b-medium-fresh1-p2", "experimentId": "extended-openrouter-paid-qwen3.8-27b-medium-fresh1-p0", "parentBaselineId": "extended-openrouter-paid-qwen3.8-27b-medium-fresh1-p0", "protocolId": "report-only-qwen27-final-descriptive-findings-v1", "repeatPass": "fresh1", "model": "qwen/qwen3.8-27b", "effort": "medium", "provider": "deepinfra/bf16", "surface": "OpenRouter · deepinfra/bf16", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": false, "resultStatus": "completed", "timing": { "kind": "client_request_to_record_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 856.604288584087, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 151830, "output": 29539, "cachedInput": null, "cacheWrite": null, "reasoning": 34473, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.064136325, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceRecordSha256": "008fa43be645b4414a57e3e0783d6e5fc0bf428c09fa1bd5771fd064b93b1c42", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceFamily": "qwen27-final-descriptive-findings", "sourceStage": "openrouter-paid-qwen3.8-27b-medium/fresh1/P2" }, { "id": "extended-openrouter-paid-qwen3.8-27b-medium-fresh2-p0", "experimentId": "extended-openrouter-paid-qwen3.8-27b-medium-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-qwen27-final-descriptive-findings-v1", "repeatPass": "fresh2", "model": "qwen/qwen3.8-27b", "effort": "medium", "provider": "deepinfra/bf16", "surface": "OpenRouter · deepinfra/bf16", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 59, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 60 }, "pairedEligible": false, "resultStatus": "completed", "timing": { "kind": "client_request_to_record_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 1041.8118212131667, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 85830, "output": 30748, "cachedInput": null, "cacheWrite": null, "reasoning": 35815, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0663816, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceRecordSha256": "008fa43be645b4414a57e3e0783d6e5fc0bf428c09fa1bd5771fd064b93b1c42", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceFamily": "qwen27-final-descriptive-findings", "sourceStage": "openrouter-paid-qwen3.8-27b-medium/fresh2/P0" }, { "id": "extended-openrouter-paid-qwen3.8-27b-medium-fresh2-p1", "experimentId": "extended-openrouter-paid-qwen3.8-27b-medium-fresh2-p0", "parentBaselineId": "extended-openrouter-paid-qwen3.8-27b-medium-fresh2-p0", "protocolId": "report-only-qwen27-final-descriptive-findings-v1", "repeatPass": "fresh2", "model": "qwen/qwen3.8-27b", "effort": "medium", "provider": "deepinfra/bf16", "surface": "OpenRouter · deepinfra/bf16", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": false, "resultStatus": "completed", "timing": { "kind": "client_request_to_record_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 1140.4771110423026, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 96450, "output": 27880, "cachedInput": null, "cacheWrite": null, "reasoning": 32576, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0633909, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceRecordSha256": "008fa43be645b4414a57e3e0783d6e5fc0bf428c09fa1bd5771fd064b93b1c42", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceFamily": "qwen27-final-descriptive-findings", "sourceStage": "openrouter-paid-qwen3.8-27b-medium/fresh2/P1" }, { "id": "extended-openrouter-paid-qwen3.8-27b-medium-fresh2-p2", "experimentId": "extended-openrouter-paid-qwen3.8-27b-medium-fresh2-p0", "parentBaselineId": "extended-openrouter-paid-qwen3.8-27b-medium-fresh2-p0", "protocolId": "report-only-qwen27-final-descriptive-findings-v1", "repeatPass": "fresh2", "model": "qwen/qwen3.8-27b", "effort": "medium", "provider": "deepinfra/bf16", "surface": "OpenRouter · deepinfra/bf16", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": false, "resultStatus": "completed", "timing": { "kind": "client_request_to_record_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 1307.4354355399264, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 151830, "output": 29088, "cachedInput": null, "cacheWrite": null, "reasoning": 34088, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0744039, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceRecordSha256": "008fa43be645b4414a57e3e0783d6e5fc0bf428c09fa1bd5771fd064b93b1c42", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceFamily": "qwen27-final-descriptive-findings", "sourceStage": "openrouter-paid-qwen3.8-27b-medium/fresh2/P2" }, { "id": "extended-openrouter-paid-qwen3.8-27b-medium-fresh3-p0", "experimentId": "extended-openrouter-paid-qwen3.8-27b-medium-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-qwen27-final-descriptive-findings-v1", "repeatPass": "fresh3", "model": "qwen/qwen3.8-27b", "effort": "medium", "provider": "deepinfra/bf16", "surface": "OpenRouter · deepinfra/bf16", "condition": "P0", "complete": false, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 59, "valid": 59, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 58 }, "pairedEligible": false, "resultStatus": "completed_interrupted_composite", "timing": { "kind": "client_request_to_record_not_pure_inference", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 1530.9367593379575, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0646527, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 1, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceRecordSha256": "008fa43be645b4414a57e3e0783d6e5fc0bf428c09fa1bd5771fd064b93b1c42", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceFamily": "qwen27-final-descriptive-findings", "sourceStage": "openrouter-paid-qwen3.8-27b-medium/fresh3/P0" }, { "id": "extended-openrouter-paid-qwen3.8-27b-medium-fresh3-p1", "experimentId": "extended-openrouter-paid-qwen3.8-27b-medium-fresh3-p0", "parentBaselineId": "extended-openrouter-paid-qwen3.8-27b-medium-fresh3-p0", "protocolId": "report-only-qwen27-final-descriptive-findings-v1", "repeatPass": "fresh3", "model": "qwen/qwen3.8-27b", "effort": "medium", "provider": "deepinfra/bf16", "surface": "OpenRouter · deepinfra/bf16", "condition": "P1", "complete": false, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 59 }, "pairedEligible": false, "resultStatus": "completed_interrupted_composite", "timing": { "kind": "client_request_to_record_not_pure_inference", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 1133.9976578360656, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 96450, "output": 27815, "cachedInput": null, "cacheWrite": null, "reasoning": 32440, "reportedRequests": 60, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.063798225, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceRecordSha256": "008fa43be645b4414a57e3e0783d6e5fc0bf428c09fa1bd5771fd064b93b1c42", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceFamily": "qwen27-final-descriptive-findings", "sourceStage": "openrouter-paid-qwen3.8-27b-medium/fresh3/P1" }, { "id": "extended-openrouter-paid-qwen3.8-27b-medium-fresh3-p2", "experimentId": "extended-openrouter-paid-qwen3.8-27b-medium-fresh3-p0", "parentBaselineId": "extended-openrouter-paid-qwen3.8-27b-medium-fresh3-p0", "protocolId": "report-only-qwen27-final-descriptive-findings-v1", "repeatPass": "fresh3", "model": "qwen/qwen3.8-27b", "effort": "medium", "provider": "deepinfra/bf16", "surface": "OpenRouter · deepinfra/bf16", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": false, "resultStatus": "completed", "timing": { "kind": "client_request_to_record_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 935.5865062899538, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 151830, "output": 29614, "cachedInput": null, "cacheWrite": null, "reasoning": 34633, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.06533535, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceRecordSha256": "008fa43be645b4414a57e3e0783d6e5fc0bf428c09fa1bd5771fd064b93b1c42", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceFamily": "qwen27-final-descriptive-findings", "sourceStage": "openrouter-paid-qwen3.8-27b-medium/fresh3/P2" }, { "id": "extended-openrouter-paid-qwen3.8-27b-off-repeat2-p0", "experimentId": "extended-openrouter-paid-qwen3.8-27b-off-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-hosted-repeats-v1", "repeatPass": "repeat2", "model": "qwen/qwen3.8-27b", "effort": "off", "provider": "deepinfra/bf16", "surface": "OpenRouter · deepinfra/bf16", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 53, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 56 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 303.60107879099087, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 85950, "output": 2703, "cachedInput": 27440, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.014873625, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceRecordSha256": "15d6b725a2300a2c4f6b6a5984b2abac5fd9f08587a326eda64d1c41147cf458", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceFamily": "hosted-repeats", "sourceStage": "openrouter-paid-qwen3.8-27b-off/repeat2/P0" }, { "id": "extended-openrouter-paid-qwen3.8-27b-off-repeat2-p1", "experimentId": "extended-openrouter-paid-qwen3.8-27b-off-repeat2-p0", "parentBaselineId": "extended-openrouter-paid-qwen3.8-27b-off-repeat2-p0", "protocolId": "report-only-hosted-repeats-v1", "repeatPass": "repeat2", "model": "qwen/qwen3.8-27b", "effort": "off", "provider": "deepinfra/bf16", "surface": "OpenRouter · deepinfra/bf16", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 55, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 301.6441496669722, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 96570, "output": 2716, "cachedInput": 73696, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0112872, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceRecordSha256": "15d6b725a2300a2c4f6b6a5984b2abac5fd9f08587a326eda64d1c41147cf458", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceFamily": "hosted-repeats", "sourceStage": "openrouter-paid-qwen3.8-27b-off/repeat2/P1" }, { "id": "extended-openrouter-paid-qwen3.8-27b-off-repeat2-p2", "experimentId": "extended-openrouter-paid-qwen3.8-27b-off-repeat2-p0", "parentBaselineId": "extended-openrouter-paid-qwen3.8-27b-off-repeat2-p0", "protocolId": "report-only-hosted-repeats-v1", "repeatPass": "repeat2", "model": "qwen/qwen3.8-27b", "effort": "off", "provider": "deepinfra/bf16", "surface": "OpenRouter · deepinfra/bf16", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 54, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 250.5549170000304, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 151950, "output": 2714, "cachedInput": 115248, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.01491585, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceRecordSha256": "15d6b725a2300a2c4f6b6a5984b2abac5fd9f08587a326eda64d1c41147cf458", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceFamily": "hosted-repeats", "sourceStage": "openrouter-paid-qwen3.8-27b-off/repeat2/P2" }, { "id": "extended-openrouter-paid-qwen3.8-27b-off-repeat3-p0", "experimentId": "extended-openrouter-paid-qwen3.8-27b-off-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-hosted-repeats-v1", "repeatPass": "repeat3", "model": "qwen/qwen3.8-27b", "effort": "off", "provider": "deepinfra/bf16", "surface": "OpenRouter · deepinfra/bf16", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 54, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 200.5239245419216, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 85950, "output": 2718, "cachedInput": 45472, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.01287315, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceRecordSha256": "15d6b725a2300a2c4f6b6a5984b2abac5fd9f08587a326eda64d1c41147cf458", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceFamily": "hosted-repeats", "sourceStage": "openrouter-paid-qwen3.8-27b-off/repeat3/P0" }, { "id": "extended-openrouter-paid-qwen3.8-27b-off-repeat3-p1", "experimentId": "extended-openrouter-paid-qwen3.8-27b-off-repeat3-p0", "parentBaselineId": "extended-openrouter-paid-qwen3.8-27b-off-repeat3-p0", "protocolId": "report-only-hosted-repeats-v1", "repeatPass": "repeat3", "model": "qwen/qwen3.8-27b", "effort": "off", "provider": "deepinfra/bf16", "surface": "OpenRouter · deepinfra/bf16", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 55, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 230.23631720698904, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 96570, "output": 2716, "cachedInput": 81536, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0104052, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceRecordSha256": "15d6b725a2300a2c4f6b6a5984b2abac5fd9f08587a326eda64d1c41147cf458", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceFamily": "hosted-repeats", "sourceStage": "openrouter-paid-qwen3.8-27b-off/repeat3/P1" }, { "id": "extended-openrouter-paid-qwen3.8-27b-off-repeat3-p2", "experimentId": "extended-openrouter-paid-qwen3.8-27b-off-repeat3-p0", "parentBaselineId": "extended-openrouter-paid-qwen3.8-27b-off-repeat3-p0", "protocolId": "report-only-hosted-repeats-v1", "repeatPass": "repeat3", "model": "qwen/qwen3.8-27b", "effort": "off", "provider": "deepinfra/bf16", "surface": "OpenRouter · deepinfra/bf16", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 54, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 211.5728607920173, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 151950, "output": 2718, "cachedInput": 134064, "cacheWrite": 0, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.01280655, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "USD amounts come from saved provider usage; unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceRecordSha256": "15d6b725a2300a2c4f6b6a5984b2abac5fd9f08587a326eda64d1c41147cf458", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/hosted-repeats.json", "sourceFamily": "hosted-repeats", "sourceStage": "openrouter-paid-qwen3.8-27b-off/repeat3/P2" }, { "id": "extended-openrouter-paid-qwen3.8-27b-xhigh-fresh1-p0", "experimentId": "extended-openrouter-paid-qwen3.8-27b-xhigh-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-qwen27-final-descriptive-findings-v1", "repeatPass": "fresh1", "model": "qwen/qwen3.8-27b", "effort": "xhigh", "provider": "deepinfra/bf16", "surface": "OpenRouter · deepinfra/bf16", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": false, "resultStatus": "completed", "timing": { "kind": "client_request_to_record_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 753.7388649631175, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 88110, "output": 24993, "cachedInput": null, "cacheWrite": null, "reasoning": 28509, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.055403775, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceRecordSha256": "008fa43be645b4414a57e3e0783d6e5fc0bf428c09fa1bd5771fd064b93b1c42", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceFamily": "qwen27-final-descriptive-findings", "sourceStage": "openrouter-paid-qwen3.8-27b-xhigh/fresh1/P0" }, { "id": "extended-openrouter-paid-qwen3.8-27b-xhigh-fresh1-p1", "experimentId": "extended-openrouter-paid-qwen3.8-27b-xhigh-fresh1-p0", "parentBaselineId": "extended-openrouter-paid-qwen3.8-27b-xhigh-fresh1-p0", "protocolId": "report-only-qwen27-final-descriptive-findings-v1", "repeatPass": "fresh1", "model": "qwen/qwen3.8-27b", "effort": "xhigh", "provider": "deepinfra/bf16", "surface": "OpenRouter · deepinfra/bf16", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": false, "resultStatus": "completed", "timing": { "kind": "client_request_to_record_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 758.4323222470703, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 98730, "output": 23305, "cachedInput": null, "cacheWrite": null, "reasoning": 26528, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.049333575, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceRecordSha256": "008fa43be645b4414a57e3e0783d6e5fc0bf428c09fa1bd5771fd064b93b1c42", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceFamily": "qwen27-final-descriptive-findings", "sourceStage": "openrouter-paid-qwen3.8-27b-xhigh/fresh1/P1" }, { "id": "extended-openrouter-paid-qwen3.8-27b-xhigh-fresh1-p2", "experimentId": "extended-openrouter-paid-qwen3.8-27b-xhigh-fresh1-p0", "parentBaselineId": "extended-openrouter-paid-qwen3.8-27b-xhigh-fresh1-p0", "protocolId": "report-only-qwen27-final-descriptive-findings-v1", "repeatPass": "fresh1", "model": "qwen/qwen3.8-27b", "effort": "xhigh", "provider": "deepinfra/bf16", "surface": "OpenRouter · deepinfra/bf16", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": false, "resultStatus": "completed", "timing": { "kind": "client_request_to_record_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 730.8231894131168, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 154110, "output": 26023, "cachedInput": null, "cacheWrite": null, "reasoning": 29827, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.058415025, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceRecordSha256": "008fa43be645b4414a57e3e0783d6e5fc0bf428c09fa1bd5771fd064b93b1c42", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceFamily": "qwen27-final-descriptive-findings", "sourceStage": "openrouter-paid-qwen3.8-27b-xhigh/fresh1/P2" }, { "id": "extended-openrouter-paid-qwen3.8-27b-xhigh-fresh2-p0", "experimentId": "extended-openrouter-paid-qwen3.8-27b-xhigh-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-qwen27-final-descriptive-findings-v1", "repeatPass": "fresh2", "model": "qwen/qwen3.8-27b", "effort": "xhigh", "provider": "deepinfra/bf16", "surface": "OpenRouter · deepinfra/bf16", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 60, "follow_up_needed": 60, "serious_concern_reported": 57, "testimonial_potential": 60 }, "pairedEligible": false, "resultStatus": "completed", "timing": { "kind": "client_request_to_record_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 923.1365995871602, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 88110, "output": 23263, "cachedInput": null, "cacheWrite": null, "reasoning": 26229, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.054453225, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceRecordSha256": "008fa43be645b4414a57e3e0783d6e5fc0bf428c09fa1bd5771fd064b93b1c42", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceFamily": "qwen27-final-descriptive-findings", "sourceStage": "openrouter-paid-qwen3.8-27b-xhigh/fresh2/P0" }, { "id": "extended-openrouter-paid-qwen3.8-27b-xhigh-fresh2-p1", "experimentId": "extended-openrouter-paid-qwen3.8-27b-xhigh-fresh2-p0", "parentBaselineId": "extended-openrouter-paid-qwen3.8-27b-xhigh-fresh2-p0", "protocolId": "report-only-qwen27-final-descriptive-findings-v1", "repeatPass": "fresh2", "model": "qwen/qwen3.8-27b", "effort": "xhigh", "provider": "deepinfra/bf16", "surface": "OpenRouter · deepinfra/bf16", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": false, "resultStatus": "completed", "timing": { "kind": "client_request_to_record_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 928.0348488728632, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 98730, "output": 26355, "cachedInput": null, "cacheWrite": null, "reasoning": 30406, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.057521925, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceRecordSha256": "008fa43be645b4414a57e3e0783d6e5fc0bf428c09fa1bd5771fd064b93b1c42", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceFamily": "qwen27-final-descriptive-findings", "sourceStage": "openrouter-paid-qwen3.8-27b-xhigh/fresh2/P1" }, { "id": "extended-openrouter-paid-qwen3.8-27b-xhigh-fresh2-p2", "experimentId": "extended-openrouter-paid-qwen3.8-27b-xhigh-fresh2-p0", "parentBaselineId": "extended-openrouter-paid-qwen3.8-27b-xhigh-fresh2-p0", "protocolId": "report-only-qwen27-final-descriptive-findings-v1", "repeatPass": "fresh2", "model": "qwen/qwen3.8-27b", "effort": "xhigh", "provider": "deepinfra/bf16", "surface": "OpenRouter · deepinfra/bf16", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": false, "resultStatus": "completed", "timing": { "kind": "client_request_to_record_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 1299.0684105427936, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 154110, "output": 26254, "cachedInput": null, "cacheWrite": null, "reasoning": 29878, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.06943215, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceRecordSha256": "008fa43be645b4414a57e3e0783d6e5fc0bf428c09fa1bd5771fd064b93b1c42", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceFamily": "qwen27-final-descriptive-findings", "sourceStage": "openrouter-paid-qwen3.8-27b-xhigh/fresh2/P2" }, { "id": "extended-openrouter-paid-qwen3.8-27b-xhigh-fresh3-p0", "experimentId": "extended-openrouter-paid-qwen3.8-27b-xhigh-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-qwen27-final-descriptive-findings-v1", "repeatPass": "fresh3", "model": "qwen/qwen3.8-27b", "effort": "xhigh", "provider": "deepinfra/bf16", "surface": "OpenRouter · deepinfra/bf16", "condition": "P0", "complete": false, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 59, "valid": 59, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 59 }, "pairedEligible": false, "resultStatus": "completed_interrupted_composite", "timing": { "kind": "client_request_to_record_not_pure_inference", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 1100.3596181263565, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0552159, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 1, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceRecordSha256": "008fa43be645b4414a57e3e0783d6e5fc0bf428c09fa1bd5771fd064b93b1c42", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceFamily": "qwen27-final-descriptive-findings", "sourceStage": "openrouter-paid-qwen3.8-27b-xhigh/fresh3/P0" }, { "id": "extended-openrouter-paid-qwen3.8-27b-xhigh-fresh3-p1", "experimentId": "extended-openrouter-paid-qwen3.8-27b-xhigh-fresh3-p0", "parentBaselineId": "extended-openrouter-paid-qwen3.8-27b-xhigh-fresh3-p0", "protocolId": "report-only-qwen27-final-descriptive-findings-v1", "repeatPass": "fresh3", "model": "qwen/qwen3.8-27b", "effort": "xhigh", "provider": "deepinfra/bf16", "surface": "OpenRouter · deepinfra/bf16", "condition": "P1", "complete": false, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 60, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": false, "resultStatus": "completed_interrupted_composite", "timing": { "kind": "client_request_to_record_not_pure_inference", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 856.7047050002147, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 98730, "output": 23510, "cachedInput": null, "cacheWrite": null, "reasoning": 26878, "reportedRequests": 60, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.05395155, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceRecordSha256": "008fa43be645b4414a57e3e0783d6e5fc0bf428c09fa1bd5771fd064b93b1c42", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceFamily": "qwen27-final-descriptive-findings", "sourceStage": "openrouter-paid-qwen3.8-27b-xhigh/fresh3/P1" }, { "id": "extended-openrouter-paid-qwen3.8-27b-xhigh-fresh3-p2", "experimentId": "extended-openrouter-paid-qwen3.8-27b-xhigh-fresh3-p0", "parentBaselineId": "extended-openrouter-paid-qwen3.8-27b-xhigh-fresh3-p0", "protocolId": "report-only-qwen27-final-descriptive-findings-v1", "repeatPass": "fresh3", "model": "qwen/qwen3.8-27b", "effort": "xhigh", "provider": "deepinfra/bf16", "surface": "OpenRouter · deepinfra/bf16", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": false, "resultStatus": "completed", "timing": { "kind": "client_request_to_record_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 840.2530787552823, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 154110, "output": 25594, "cachedInput": null, "cacheWrite": null, "reasoning": 29311, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.05840445, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceRecordSha256": "008fa43be645b4414a57e3e0783d6e5fc0bf428c09fa1bd5771fd064b93b1c42", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen27-final-descriptive-findings.json", "sourceFamily": "qwen27-final-descriptive-findings", "sourceStage": "openrouter-paid-qwen3.8-27b-xhigh/fresh3/P2" }, { "id": "extended-openrouter-paid-qwen36-35b-a3b-off-fresh1-p0", "experimentId": "extended-openrouter-paid-qwen36-35b-a3b-off-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-qwen36-off-second-interruption-findings-v1", "repeatPass": "fresh1", "model": "qwen/qwen3.6-35b-a3b", "effort": "off", "provider": "akashml/fp8", "surface": "OpenRouter · akashml/fp8", "condition": "P0", "complete": false, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": null, "valid": 59, "metrics": { "all_four": 48, "sentiment": 54, "follow_up_needed": 58, "serious_concern_reported": 56, "testimonial_potential": 54 }, "pairedEligible": false, "resultStatus": "closed_with_service_error", "timing": { "kind": "client_http_duration_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 51.67563604094903, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 84531, "output": 2659, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 59, "totalRequests": 60, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0073486, "estimatedUsd": null, "unknownUpperBoundUsd": 0.0299008, "unknownCostCount": 1, "note": "Known USD costs are observed provider charges; the upper bound is not an invoice charge." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen36-off-second-interruption-findings.json", "sourceRecordSha256": "c6688ff8eb8a3cbc0c3a9c03c33e9121cbcf13d591518099c88e68f09e8712f0", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen36-off-second-interruption-findings.json", "sourceFamily": "qwen36-off-second-interruption-findings", "sourceStage": "openrouter-paid-qwen36-35b-a3b-off/fresh1/P0" }, { "id": "extended-openrouter-paid-qwen36-35b-a3b-off-fresh1-p1", "experimentId": "extended-openrouter-paid-qwen36-35b-a3b-off-fresh1-p0", "parentBaselineId": "extended-openrouter-paid-qwen36-35b-a3b-off-fresh1-p0", "protocolId": "report-only-qwen36-off-second-interruption-findings-v1", "repeatPass": "fresh1", "model": "qwen/qwen3.6-35b-a3b", "effort": "off", "provider": "akashml/fp8", "surface": "OpenRouter · akashml/fp8", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 51, "sentiment": 56, "follow_up_needed": 59, "serious_concern_reported": 57, "testimonial_potential": 56 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_http_duration_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 48.74483166806749, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 96570, "output": 2706, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0075996, "estimatedUsd": null, "unknownUpperBoundUsd": 0.0, "unknownCostCount": 0, "note": "Known USD costs are observed provider charges; the upper bound is not an invoice charge." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen36-off-second-interruption-findings.json", "sourceRecordSha256": "c6688ff8eb8a3cbc0c3a9c03c33e9121cbcf13d591518099c88e68f09e8712f0", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen36-off-second-interruption-findings.json", "sourceFamily": "qwen36-off-second-interruption-findings", "sourceStage": "openrouter-paid-qwen36-35b-a3b-off/fresh1/P1" }, { "id": "extended-openrouter-paid-qwen36-35b-a3b-off-fresh1-p2", "experimentId": "extended-openrouter-paid-qwen36-35b-a3b-off-fresh1-p0", "parentBaselineId": "extended-openrouter-paid-qwen36-35b-a3b-off-fresh1-p0", "protocolId": "report-only-qwen36-off-second-interruption-findings-v1", "repeatPass": "fresh1", "model": "qwen/qwen3.6-35b-a3b", "effort": "off", "provider": "akashml/fp8", "surface": "OpenRouter · akashml/fp8", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 51, "sentiment": 57, "follow_up_needed": 60, "serious_concern_reported": 57, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_http_duration_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 52.270998042979045, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 151950, "output": 2718, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0105084, "estimatedUsd": null, "unknownUpperBoundUsd": 0.0, "unknownCostCount": 0, "note": "Known USD costs are observed provider charges; the upper bound is not an invoice charge." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen36-off-second-interruption-findings.json", "sourceRecordSha256": "c6688ff8eb8a3cbc0c3a9c03c33e9121cbcf13d591518099c88e68f09e8712f0", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen36-off-second-interruption-findings.json", "sourceFamily": "qwen36-off-second-interruption-findings", "sourceStage": "openrouter-paid-qwen36-35b-a3b-off/fresh1/P2" }, { "id": "extended-openrouter-paid-qwen36-35b-a3b-off-fresh2-p0", "experimentId": "extended-openrouter-paid-qwen36-35b-a3b-off-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-qwen36-off-second-interruption-findings-v1", "repeatPass": "fresh2", "model": "qwen/qwen3.6-35b-a3b", "effort": "off", "provider": "akashml/fp8", "surface": "OpenRouter · akashml/fp8", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 51, "sentiment": 56, "follow_up_needed": 59, "serious_concern_reported": 57, "testimonial_potential": 56 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_http_duration_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 49.28689683289849, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 85950, "output": 2706, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0071296, "estimatedUsd": null, "unknownUpperBoundUsd": 0.0, "unknownCostCount": 0, "note": "Known USD costs are observed provider charges; the upper bound is not an invoice charge." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen36-off-second-interruption-findings.json", "sourceRecordSha256": "c6688ff8eb8a3cbc0c3a9c03c33e9121cbcf13d591518099c88e68f09e8712f0", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen36-off-second-interruption-findings.json", "sourceFamily": "qwen36-off-second-interruption-findings", "sourceStage": "openrouter-paid-qwen36-35b-a3b-off/fresh2/P0" }, { "id": "extended-openrouter-paid-qwen36-35b-a3b-off-fresh2-p1", "experimentId": "extended-openrouter-paid-qwen36-35b-a3b-off-fresh2-p0", "parentBaselineId": "extended-openrouter-paid-qwen36-35b-a3b-off-fresh2-p0", "protocolId": "report-only-qwen36-off-second-interruption-findings-v1", "repeatPass": "fresh2", "model": "qwen/qwen3.6-35b-a3b", "effort": "off", "provider": "akashml/fp8", "surface": "OpenRouter · akashml/fp8", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 50, "sentiment": 56, "follow_up_needed": 59, "serious_concern_reported": 57, "testimonial_potential": 55 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_http_duration_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 48.92766350109014, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 96570, "output": 2706, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.007494, "estimatedUsd": null, "unknownUpperBoundUsd": 0.0, "unknownCostCount": 0, "note": "Known USD costs are observed provider charges; the upper bound is not an invoice charge." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen36-off-second-interruption-findings.json", "sourceRecordSha256": "c6688ff8eb8a3cbc0c3a9c03c33e9121cbcf13d591518099c88e68f09e8712f0", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen36-off-second-interruption-findings.json", "sourceFamily": "qwen36-off-second-interruption-findings", "sourceStage": "openrouter-paid-qwen36-35b-a3b-off/fresh2/P1" }, { "id": "extended-openrouter-paid-qwen36-35b-a3b-off-fresh2-p2", "experimentId": "extended-openrouter-paid-qwen36-35b-a3b-off-fresh2-p0", "parentBaselineId": "extended-openrouter-paid-qwen36-35b-a3b-off-fresh2-p0", "protocolId": "report-only-qwen36-off-second-interruption-findings-v1", "repeatPass": "fresh2", "model": "qwen/qwen3.6-35b-a3b", "effort": "off", "provider": "akashml/fp8", "surface": "OpenRouter · akashml/fp8", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 52, "sentiment": 57, "follow_up_needed": 60, "serious_concern_reported": 57, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_http_duration_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 55.19229199492838, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 151950, "output": 2718, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0103228, "estimatedUsd": null, "unknownUpperBoundUsd": 0.0, "unknownCostCount": 0, "note": "Known USD costs are observed provider charges; the upper bound is not an invoice charge." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen36-off-second-interruption-findings.json", "sourceRecordSha256": "c6688ff8eb8a3cbc0c3a9c03c33e9121cbcf13d591518099c88e68f09e8712f0", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen36-off-second-interruption-findings.json", "sourceFamily": "qwen36-off-second-interruption-findings", "sourceStage": "openrouter-paid-qwen36-35b-a3b-off/fresh2/P2" }, { "id": "extended-openrouter-paid-qwen36-35b-a3b-off-fresh3-p0", "experimentId": "extended-openrouter-paid-qwen36-35b-a3b-off-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-qwen36-off-second-interruption-findings-v1", "repeatPass": "fresh3", "model": "qwen/qwen3.6-35b-a3b", "effort": "off", "provider": "akashml/fp8", "surface": "OpenRouter · akashml/fp8", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 50, "sentiment": 56, "follow_up_needed": 59, "serious_concern_reported": 57, "testimonial_potential": 55 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_http_duration_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 50.11110804695636, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 85950, "output": 2706, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0071264, "estimatedUsd": null, "unknownUpperBoundUsd": 0.0, "unknownCostCount": 0, "note": "Known USD costs are observed provider charges; the upper bound is not an invoice charge." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen36-off-second-interruption-findings.json", "sourceRecordSha256": "c6688ff8eb8a3cbc0c3a9c03c33e9121cbcf13d591518099c88e68f09e8712f0", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen36-off-second-interruption-findings.json", "sourceFamily": "qwen36-off-second-interruption-findings", "sourceStage": "openrouter-paid-qwen36-35b-a3b-off/fresh3/P0" }, { "id": "extended-openrouter-paid-qwen36-35b-a3b-off-fresh3-p1", "experimentId": "extended-openrouter-paid-qwen36-35b-a3b-off-fresh3-p0", "parentBaselineId": "extended-openrouter-paid-qwen36-35b-a3b-off-fresh3-p0", "protocolId": "report-only-qwen36-off-second-interruption-findings-v1", "repeatPass": "fresh3", "model": "qwen/qwen3.6-35b-a3b", "effort": "off", "provider": "akashml/fp8", "surface": "OpenRouter · akashml/fp8", "condition": "P1", "complete": false, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": null, "valid": 59, "metrics": { "all_four": 50, "sentiment": 55, "follow_up_needed": 58, "serious_concern_reported": 56, "testimonial_potential": 55 }, "pairedEligible": false, "resultStatus": "closed_with_service_error", "timing": { "kind": "client_http_duration_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 48.19103391515091, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 94957, "output": 2661, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 59, "totalRequests": 60, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.007657, "estimatedUsd": null, "unknownUpperBoundUsd": 0.0598016, "unknownCostCount": 1, "note": "Known USD costs are observed provider charges; the upper bound is not an invoice charge." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen36-off-second-interruption-findings.json", "sourceRecordSha256": "c6688ff8eb8a3cbc0c3a9c03c33e9121cbcf13d591518099c88e68f09e8712f0", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen36-off-second-interruption-findings.json", "sourceFamily": "qwen36-off-second-interruption-findings", "sourceStage": "openrouter-paid-qwen36-35b-a3b-off/fresh3/P1" }, { "id": "extended-openrouter-paid-qwen36-35b-a3b-off-fresh3-p2", "experimentId": "extended-openrouter-paid-qwen36-35b-a3b-off-fresh3-p0", "parentBaselineId": "extended-openrouter-paid-qwen36-35b-a3b-off-fresh3-p0", "protocolId": "report-only-qwen36-off-second-interruption-findings-v1", "repeatPass": "fresh3", "model": "qwen/qwen3.6-35b-a3b", "effort": "off", "provider": "akashml/fp8", "surface": "OpenRouter · akashml/fp8", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 52, "sentiment": 57, "follow_up_needed": 60, "serious_concern_reported": 57, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "client_http_duration_not_provider_inference", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 51.055341792845866, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 151950, "output": 2718, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.010518, "estimatedUsd": null, "unknownUpperBoundUsd": 0.0, "unknownCostCount": 0, "note": "Known USD costs are observed provider charges; the upper bound is not an invoice charge." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen36-off-second-interruption-findings.json", "sourceRecordSha256": "c6688ff8eb8a3cbc0c3a9c03c33e9121cbcf13d591518099c88e68f09e8712f0", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/qwen36-off-second-interruption-findings.json", "sourceFamily": "qwen36-off-second-interruption-findings", "sourceStage": "openrouter-paid-qwen36-35b-a3b-off/fresh3/P2" }, { "id": "extended-openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2-fresh1-p0", "experimentId": "extended-openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-additional-hosted-fresh-repeats-v1", "repeatPass": "fresh1", "model": "qwen/qwen3.6-35b-a3b", "effort": "on", "provider": "akashml/fp8", "surface": "OpenRouter · akashml/fp8", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 54, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 57, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 85830, "output": 68751, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0673437, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/additional-hosted-fresh-repeats.json", "sourceRecordSha256": "cfd11bb576566097c6d351896e05578ffd6e1a35014011194d0d06fee0e85cf4", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/additional-hosted-fresh-repeats.json", "sourceFamily": "additional-hosted-fresh-repeats", "sourceStage": "openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2/fresh1/P0" }, { "id": "extended-openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2-fresh1-p1", "experimentId": "extended-openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2-fresh1-p0", "parentBaselineId": "extended-openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2-fresh1-p0", "protocolId": "report-only-additional-hosted-fresh-repeats-v1", "repeatPass": "fresh1", "model": "qwen/qwen3.6-35b-a3b", "effort": "on", "provider": "akashml/fp8", "surface": "OpenRouter · akashml/fp8", "condition": "P1", "complete": false, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": null, "valid": 59, "metrics": { "all_four": 52, "sentiment": 57, "follow_up_needed": 59, "serious_concern_reported": 56, "testimonial_potential": 56 }, "pairedEligible": false, "resultStatus": "completed_interrupted_composite", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": null, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": 60, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0696082, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 1, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/additional-hosted-fresh-repeats.json", "sourceRecordSha256": "cfd11bb576566097c6d351896e05578ffd6e1a35014011194d0d06fee0e85cf4", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/additional-hosted-fresh-repeats.json", "sourceFamily": "additional-hosted-fresh-repeats", "sourceStage": "openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2/fresh1/P1" }, { "id": "extended-openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2-fresh1-p2", "experimentId": "extended-openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2-fresh1-p0", "parentBaselineId": "extended-openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2-fresh1-p0", "protocolId": "report-only-additional-hosted-fresh-repeats-v1", "repeatPass": "fresh1", "model": "qwen/qwen3.6-35b-a3b", "effort": "on", "provider": "akashml/fp8", "surface": "OpenRouter · akashml/fp8", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 57, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 151830, "output": 61822, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0644868, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/additional-hosted-fresh-repeats.json", "sourceRecordSha256": "cfd11bb576566097c6d351896e05578ffd6e1a35014011194d0d06fee0e85cf4", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/additional-hosted-fresh-repeats.json", "sourceFamily": "additional-hosted-fresh-repeats", "sourceStage": "openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2/fresh1/P2" }, { "id": "extended-openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2-fresh2-p0", "experimentId": "extended-openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-additional-hosted-fresh-repeats-v1", "repeatPass": "fresh2", "model": "qwen/qwen3.6-35b-a3b", "effort": "on", "provider": "akashml/fp8", "surface": "OpenRouter · akashml/fp8", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 53, "sentiment": 57, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 85830, "output": 70354, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0687864, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/additional-hosted-fresh-repeats.json", "sourceRecordSha256": "cfd11bb576566097c6d351896e05578ffd6e1a35014011194d0d06fee0e85cf4", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/additional-hosted-fresh-repeats.json", "sourceFamily": "additional-hosted-fresh-repeats", "sourceStage": "openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2/fresh2/P0" }, { "id": "extended-openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2-fresh2-p1", "experimentId": "extended-openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2-fresh2-p0", "parentBaselineId": "extended-openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2-fresh2-p0", "protocolId": "report-only-additional-hosted-fresh-repeats-v1", "repeatPass": "fresh2", "model": "qwen/qwen3.6-35b-a3b", "effort": "on", "provider": "akashml/fp8", "surface": "OpenRouter · akashml/fp8", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 54, "sentiment": 57, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 96450, "output": 70523, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0700005, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/additional-hosted-fresh-repeats.json", "sourceRecordSha256": "cfd11bb576566097c6d351896e05578ffd6e1a35014011194d0d06fee0e85cf4", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/additional-hosted-fresh-repeats.json", "sourceFamily": "additional-hosted-fresh-repeats", "sourceStage": "openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2/fresh2/P1" }, { "id": "extended-openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2-fresh2-p2", "experimentId": "extended-openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2-fresh2-p0", "parentBaselineId": "extended-openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2-fresh2-p0", "protocolId": "report-only-additional-hosted-fresh-repeats-v1", "repeatPass": "fresh2", "model": "qwen/qwen3.6-35b-a3b", "effort": "on", "provider": "akashml/fp8", "surface": "OpenRouter · akashml/fp8", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 57, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 151830, "output": 63138, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0656712, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/additional-hosted-fresh-repeats.json", "sourceRecordSha256": "cfd11bb576566097c6d351896e05578ffd6e1a35014011194d0d06fee0e85cf4", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/additional-hosted-fresh-repeats.json", "sourceFamily": "additional-hosted-fresh-repeats", "sourceStage": "openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2/fresh2/P2" }, { "id": "extended-openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2-fresh3-p0", "experimentId": "extended-openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-additional-hosted-fresh-repeats-v1", "repeatPass": "fresh3", "model": "qwen/qwen3.6-35b-a3b", "effort": "on", "provider": "akashml/fp8", "surface": "OpenRouter · akashml/fp8", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 51, "sentiment": 56, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 85830, "output": 69063, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0676245, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/additional-hosted-fresh-repeats.json", "sourceRecordSha256": "cfd11bb576566097c6d351896e05578ffd6e1a35014011194d0d06fee0e85cf4", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/additional-hosted-fresh-repeats.json", "sourceFamily": "additional-hosted-fresh-repeats", "sourceStage": "openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2/fresh3/P0" }, { "id": "extended-openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2-fresh3-p1", "experimentId": "extended-openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2-fresh3-p0", "parentBaselineId": "extended-openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2-fresh3-p0", "protocolId": "report-only-additional-hosted-fresh-repeats-v1", "repeatPass": "fresh3", "model": "qwen/qwen3.6-35b-a3b", "effort": "on", "provider": "akashml/fp8", "surface": "OpenRouter · akashml/fp8", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 96450, "output": 67064, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0668346, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/additional-hosted-fresh-repeats.json", "sourceRecordSha256": "cfd11bb576566097c6d351896e05578ffd6e1a35014011194d0d06fee0e85cf4", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/additional-hosted-fresh-repeats.json", "sourceFamily": "additional-hosted-fresh-repeats", "sourceStage": "openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2/fresh3/P1" }, { "id": "extended-openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2-fresh3-p2", "experimentId": "extended-openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2-fresh3-p0", "parentBaselineId": "extended-openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2-fresh3-p0", "protocolId": "report-only-additional-hosted-fresh-repeats-v1", "repeatPass": "fresh3", "model": "qwen/qwen3.6-35b-a3b", "effort": "on", "provider": "akashml/fp8", "surface": "OpenRouter · akashml/fp8", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 54, "sentiment": 57, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "completed", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 151830, "output": 63399, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.0660117, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/additional-hosted-fresh-repeats.json", "sourceRecordSha256": "cfd11bb576566097c6d351896e05578ffd6e1a35014011194d0d06fee0e85cf4", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/additional-hosted-fresh-repeats.json", "sourceFamily": "additional-hosted-fresh-repeats", "sourceStage": "openrouter-paid-qwen36-35b-a3b-on-authority-v3-hosted-v2/fresh3/P2" }, { "id": "extended-opus5-high-phase2-batch10-p0-repeat2-p0", "experimentId": "extended-opus5-high-phase2-batch10-p0-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-opus-5", "effort": "high", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 102.04576070801704, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 9094, "cachedInput": 4884, "cacheWrite": 21173, "reasoning": 5253, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.44158200000000003, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus5-high-phase2-batch10-p0/repeat2/P0" }, { "id": "extended-opus5-high-phase2-batch10-p0-repeat2-p1", "experimentId": "extended-opus5-high-phase2-batch10-p0-repeat2-p0", "parentBaselineId": "extended-opus5-high-phase2-batch10-p0-repeat2-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-opus-5", "effort": "high", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 114.29917045900947, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 9151, "cachedInput": 4884, "cacheWrite": 22974, "reasoning": 5359, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.461017, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus5-high-phase2-batch10-p0/repeat2/P1" }, { "id": "extended-opus5-high-phase2-batch10-p0-repeat2-p2", "experimentId": "extended-opus5-high-phase2-batch10-p0-repeat2-p0", "parentBaselineId": "extended-opus5-high-phase2-batch10-p0-repeat2-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-opus-5", "effort": "high", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 106.05118050097371, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 9224, "cachedInput": 0, "cacheWrite": 38063, "reasoning": 5333, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.61129, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus5-high-phase2-batch10-p0/repeat2/P2" }, { "id": "extended-opus5-high-phase2-batch10-p0-repeat3-p0", "experimentId": "extended-opus5-high-phase2-batch10-p0-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-opus-5", "effort": "high", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 105.42716220903094, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 9724, "cachedInput": 19680, "cacheWrite": 6380, "reasoning": 4905, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.3168, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus5-high-phase2-batch10-p0/repeat3/P0" }, { "id": "extended-opus5-high-phase2-batch10-p0-repeat3-p1", "experimentId": "extended-opus5-high-phase2-batch10-p0-repeat3-p0", "parentBaselineId": "extended-opus5-high-phase2-batch10-p0-repeat3-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-opus-5", "effort": "high", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 60, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 106.14609700001893, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 9072, "cachedInput": 21486, "cacheWrite": 6365, "reasoning": 5181, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.301253, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus5-high-phase2-batch10-p0/repeat3/P1" }, { "id": "extended-opus5-high-phase2-batch10-p0-repeat3-p2", "experimentId": "extended-opus5-high-phase2-batch10-p0-repeat3-p0", "parentBaselineId": "extended-opus5-high-phase2-batch10-p0-repeat3-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-opus-5", "effort": "high", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 159.36648875000537, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 9356, "cachedInput": 31698, "cacheWrite": 6372, "reasoning": 5515, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.313529, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus5-high-phase2-batch10-p0/repeat3/P2" }, { "id": "extended-opus5-low-phase2-batch10-p0-repeat2-p0", "experimentId": "extended-opus5-low-phase2-batch10-p0-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-opus-5", "effort": "low", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 55, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 52.82799683502526, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 4248, "cachedInput": 4884, "cacheWrite": 21175, "reasoning": 481, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.320452, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus5-low-phase2-batch10-p0/repeat2/P0" }, { "id": "extended-opus5-low-phase2-batch10-p0-repeat2-p1", "experimentId": "extended-opus5-low-phase2-batch10-p0-repeat2-p0", "parentBaselineId": "extended-opus5-low-phase2-batch10-p0-repeat2-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-opus-5", "effort": "low", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 55, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 50.746723917050986, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 3749, "cachedInput": 4884, "cacheWrite": 22975, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.325977, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus5-low-phase2-batch10-p0/repeat2/P1" }, { "id": "extended-opus5-low-phase2-batch10-p0-repeat2-p2", "experimentId": "extended-opus5-low-phase2-batch10-p0-repeat2-p0", "parentBaselineId": "extended-opus5-low-phase2-batch10-p0-repeat2-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-opus-5", "effort": "low", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 55, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 48.86669675100711, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 3746, "cachedInput": 0, "cacheWrite": 38066, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.47436999999999996, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus5-low-phase2-batch10-p0/repeat2/P2" }, { "id": "extended-opus5-low-phase2-batch10-p0-repeat3-p0", "experimentId": "extended-opus5-low-phase2-batch10-p0-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-opus-5", "effort": "low", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 51.68380433303537, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 3842, "cachedInput": 19680, "cacheWrite": 6381, "reasoning": 91, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.16976, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus5-low-phase2-batch10-p0/repeat3/P0" }, { "id": "extended-opus5-low-phase2-batch10-p0-repeat3-p1", "experimentId": "extended-opus5-low-phase2-batch10-p0-repeat3-p0", "parentBaselineId": "extended-opus5-low-phase2-batch10-p0-repeat3-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-opus-5", "effort": "low", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 78.78485370994895, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 3750, "cachedInput": 21486, "cacheWrite": 6370, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.16825299999999999, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus5-low-phase2-batch10-p0/repeat3/P1" }, { "id": "extended-opus5-low-phase2-batch10-p0-repeat3-p2", "experimentId": "extended-opus5-low-phase2-batch10-p0-repeat3-p0", "parentBaselineId": "extended-opus5-low-phase2-batch10-p0-repeat3-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-opus-5", "effort": "low", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 55, "sentiment": 57, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 43.73642258197651, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 3747, "cachedInput": 31698, "cacheWrite": 6367, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.173254, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus5-low-phase2-batch10-p0/repeat3/P2" }, { "id": "extended-opus5-medium-phase2-batch10-p0-repeat2-p0", "experimentId": "extended-opus5-medium-phase2-batch10-p0-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-opus-5", "effort": "medium", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 78.32838045802782, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 6774, "cachedInput": 4884, "cacheWrite": 21171, "reasoning": 3027, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.383562, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus5-medium-phase2-batch10-p0/repeat2/P0" }, { "id": "extended-opus5-medium-phase2-batch10-p0-repeat2-p1", "experimentId": "extended-opus5-medium-phase2-batch10-p0-repeat2-p0", "parentBaselineId": "extended-opus5-medium-phase2-batch10-p0-repeat2-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-opus-5", "effort": "medium", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 74.50842787500005, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 6108, "cachedInput": 0, "cacheWrite": 27856, "reasoning": 2355, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.43132, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus5-medium-phase2-batch10-p0/repeat2/P1" }, { "id": "extended-opus5-medium-phase2-batch10-p0-repeat2-p2", "experimentId": "extended-opus5-medium-phase2-batch10-p0-repeat2-p0", "parentBaselineId": "extended-opus5-medium-phase2-batch10-p0-repeat2-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-opus-5", "effort": "medium", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 81.74714266796946, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 6686, "cachedInput": 4884, "cacheWrite": 33184, "reasoning": 2942, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.501492, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus5-medium-phase2-batch10-p0/repeat2/P2" }, { "id": "extended-opus5-medium-phase2-batch10-p0-repeat3-p0", "experimentId": "extended-opus5-medium-phase2-batch10-p0-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-opus-5", "effort": "medium", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 74.86745858399081, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 6476, "cachedInput": 19680, "cacheWrite": 6379, "reasoning": 2723, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.23559, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus5-medium-phase2-batch10-p0/repeat3/P0" }, { "id": "extended-opus5-medium-phase2-batch10-p0-repeat3-p1", "experimentId": "extended-opus5-medium-phase2-batch10-p0-repeat3-p0", "parentBaselineId": "extended-opus5-medium-phase2-batch10-p0-repeat3-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-opus-5", "effort": "medium", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 55, "sentiment": 57, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 73.67982400002074, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 6243, "cachedInput": 21486, "cacheWrite": 6373, "reasoning": 2496, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.230608, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus5-medium-phase2-batch10-p0/repeat3/P1" }, { "id": "extended-opus5-medium-phase2-batch10-p0-repeat3-p2", "experimentId": "extended-opus5-medium-phase2-batch10-p0-repeat3-p0", "parentBaselineId": "extended-opus5-medium-phase2-batch10-p0-repeat3-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-opus-5", "effort": "medium", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 55, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 77.10674150002887, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 6558, "cachedInput": 31698, "cacheWrite": 6371, "reasoning": 2811, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.243569, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus5-medium-phase2-batch10-p0/repeat3/P2" }, { "id": "extended-opus5-xhigh-phase2-batch10-p0-repeat2-p0", "experimentId": "extended-opus5-xhigh-phase2-batch10-p0-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-opus-5", "effort": "xhigh", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 171.76608349799062, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 15899, "cachedInput": 4884, "cacheWrite": 21171, "reasoning": 9446, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.611687, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus5-xhigh-phase2-batch10-p0/repeat2/P0" }, { "id": "extended-opus5-xhigh-phase2-batch10-p0-repeat2-p1", "experimentId": "extended-opus5-xhigh-phase2-batch10-p0-repeat2-p0", "parentBaselineId": "extended-opus5-xhigh-phase2-batch10-p0-repeat2-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-opus-5", "effort": "xhigh", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 151.9952381250332, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 12024, "cachedInput": 0, "cacheWrite": 27858, "reasoning": 7986, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.57924, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus5-xhigh-phase2-batch10-p0/repeat2/P1" }, { "id": "extended-opus5-xhigh-phase2-batch10-p0-repeat2-p2", "experimentId": "extended-opus5-xhigh-phase2-batch10-p0-repeat2-p0", "parentBaselineId": "extended-opus5-xhigh-phase2-batch10-p0-repeat2-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-opus-5", "effort": "xhigh", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 124.54641595701105, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 11167, "cachedInput": 4884, "cacheWrite": 33188, "reasoning": 7131, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.613557, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus5-xhigh-phase2-batch10-p0/repeat2/P2" }, { "id": "extended-opus5-xhigh-phase2-batch10-p0-repeat3-p0", "experimentId": "extended-opus5-xhigh-phase2-batch10-p0-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-opus-5", "effort": "xhigh", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 156.34940266504418, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 13605, "cachedInput": 19680, "cacheWrite": 6375, "reasoning": 8444, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.413775, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus5-xhigh-phase2-batch10-p0/repeat3/P0" }, { "id": "extended-opus5-xhigh-phase2-batch10-p0-repeat3-p1", "experimentId": "extended-opus5-xhigh-phase2-batch10-p0-repeat3-p0", "parentBaselineId": "extended-opus5-xhigh-phase2-batch10-p0-repeat3-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-opus-5", "effort": "xhigh", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 131.1806115829968, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 12080, "cachedInput": 21486, "cacheWrite": 6371, "reasoning": 8091, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.376513, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus5-xhigh-phase2-batch10-p0/repeat3/P1" }, { "id": "extended-opus5-xhigh-phase2-batch10-p0-repeat3-p2", "experimentId": "extended-opus5-xhigh-phase2-batch10-p0-repeat3-p0", "parentBaselineId": "extended-opus5-xhigh-phase2-batch10-p0-repeat3-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-opus-5", "effort": "xhigh", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 125.83242354297545, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 11759, "cachedInput": 31698, "cacheWrite": 6374, "reasoning": 7771, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.373624, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus5-xhigh-phase2-batch10-p0/repeat3/P2" }, { "id": "extended-opus55-high-batch10-repeat2-p0", "experimentId": "extended-opus55-high-batch10-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-opus-5-5", "effort": "high", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 60, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 75.95529937604442, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 7854, "cachedInput": 17214, "cacheWrite": 8866, "reasoning": 3144, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.23149879999999998, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus55-high-batch10/repeat2/P0" }, { "id": "extended-opus55-high-batch10-repeat2-p1", "experimentId": "extended-opus55-high-batch10-repeat2-p0", "parentBaselineId": "extended-opus55-high-batch10-repeat2-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-opus-5-5", "effort": "high", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 59, "sentiment": 60, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 76.84967362499447, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 6987, "cachedInput": 21486, "cacheWrite": 6402, "reasoning": 3237, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.1953012, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus55-high-batch10/repeat2/P1" }, { "id": "extended-opus55-high-batch10-repeat2-p2", "experimentId": "extended-opus55-high-batch10-repeat2-p0", "parentBaselineId": "extended-opus55-high-batch10-repeat2-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-opus-5-5", "effort": "high", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 83.57342870699358, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 7550, "cachedInput": 31698, "cacheWrite": 6401, "reasoning": 3801, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.2085956, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus55-high-batch10/repeat2/P2" }, { "id": "extended-opus55-high-batch10-repeat3-p0", "experimentId": "extended-opus55-high-batch10-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-opus-5-5", "effort": "high", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 72.4936976240133, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 7599, "cachedInput": 19680, "cacheWrite": 6408, "reasoning": 3058, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.20722800000000002, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus55-high-batch10/repeat3/P0" }, { "id": "extended-opus55-high-batch10-repeat3-p1", "experimentId": "extended-opus55-high-batch10-repeat3-p0", "parentBaselineId": "extended-opus55-high-batch10-repeat3-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-opus-5-5", "effort": "high", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 113.5377515819855, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 7180, "cachedInput": 21486, "cacheWrite": 6403, "reasoning": 3147, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.19916920000000002, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus55-high-batch10/repeat3/P1" }, { "id": "extended-opus55-high-batch10-repeat3-p2", "experimentId": "extended-opus55-high-batch10-repeat3-p0", "parentBaselineId": "extended-opus55-high-batch10-repeat3-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-opus-5-5", "effort": "high", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 60, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 67.38733454199973, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 6918, "cachedInput": 31698, "cacheWrite": 6398, "reasoning": 3169, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.1959316, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus55-high-batch10/repeat3/P2" }, { "id": "extended-opus55-low-batch10-repeat2-p0", "experimentId": "extended-opus55-low-batch10-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-opus-5-5", "effort": "low", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 59.361560832039686, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 5815, "cachedInput": 4884, "cacheWrite": 21200, "reasoning": 1382, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.2869248, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus55-low-batch10/repeat2/P0" }, { "id": "extended-opus55-low-batch10-repeat2-p1", "experimentId": "extended-opus55-low-batch10-repeat2-p0", "parentBaselineId": "extended-opus55-low-batch10-repeat2-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-opus-5-5", "effort": "low", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 59, "sentiment": 60, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 57.52336133402423, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 5187, "cachedInput": 0, "cacheWrite": 27885, "reasoning": 1418, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.326868, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus55-low-batch10/repeat2/P1" }, { "id": "extended-opus55-low-batch10-repeat2-p2", "experimentId": "extended-opus55-low-batch10-repeat2-p0", "parentBaselineId": "extended-opus55-low-batch10-repeat2-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-opus-5-5", "effort": "low", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 61.943264124012785, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 5003, "cachedInput": 31698, "cacheWrite": 6400, "reasoning": 1256, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.1576476, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus55-low-batch10/repeat2/P2" }, { "id": "extended-opus55-low-batch10-repeat3-p0", "experimentId": "extended-opus55-low-batch10-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-opus-5-5", "effort": "low", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 61.22685375099536, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 5937, "cachedInput": 19680, "cacheWrite": 6405, "reasoning": 1531, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.173964, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus55-low-batch10/repeat3/P0" }, { "id": "extended-opus55-low-batch10-repeat3-p1", "experimentId": "extended-opus55-low-batch10-repeat3-p0", "parentBaselineId": "extended-opus55-low-batch10-repeat3-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-opus-5-5", "effort": "low", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 59, "sentiment": 60, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 56.581009624002036, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 14, "output": 5564, "cachedInput": 26130, "cacheWrite": 7551, "reasoning": 1177, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.17697000000000002, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus55-low-batch10/repeat3/P1" }, { "id": "extended-opus55-low-batch10-repeat3-p2", "experimentId": "extended-opus55-low-batch10-repeat3-p0", "parentBaselineId": "extended-opus55-low-batch10-repeat3-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-opus-5-5", "effort": "low", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 60, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 50.85654379200423, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 4911, "cachedInput": 31698, "cacheWrite": 6400, "reasoning": 1168, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.1558076, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus55-low-batch10/repeat3/P2" }, { "id": "extended-opus55-medium-batch10-repeat2-p0", "experimentId": "extended-opus55-medium-batch10-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-claude-repeats-v1", "repeatPass": "repeat2", "model": "claude-opus-5-5", "effort": "medium", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 65.85350325101172, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 6500, "cachedInput": 4884, "cacheWrite": 21203, "reasoning": 2461, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.30064880000000005, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-repeats.json", "sourceRecordSha256": "e2da6c5e3dc75b1673d1682a62b5c8a7bbe9fad87ab53e47412b4c4c3f368feb", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-repeats.json", "sourceFamily": "claude-repeats", "sourceStage": "opus55-medium-batch10/repeat2/P0" }, { "id": "extended-opus55-medium-batch10-repeat2-p1", "experimentId": "extended-opus55-medium-batch10-repeat2-p0", "parentBaselineId": "extended-opus55-medium-batch10-repeat2-p0", "protocolId": "report-only-claude-repeats-v1", "repeatPass": "repeat2", "model": "claude-opus-5-5", "effort": "medium", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 64.98174929100787, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 6423, "cachedInput": 4884, "cacheWrite": 23002, "reasoning": 2345, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.3135008, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-repeats.json", "sourceRecordSha256": "e2da6c5e3dc75b1673d1682a62b5c8a7bbe9fad87ab53e47412b4c4c3f368feb", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-repeats.json", "sourceFamily": "claude-repeats", "sourceStage": "opus55-medium-batch10/repeat2/P1" }, { "id": "extended-opus55-medium-batch10-repeat2-p2", "experimentId": "extended-opus55-medium-batch10-repeat2-p0", "parentBaselineId": "extended-opus55-medium-batch10-repeat2-p0", "protocolId": "report-only-claude-repeats-v1", "repeatPass": "repeat2", "model": "claude-opus-5-5", "effort": "medium", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 60, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 69.40425654200953, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 6880, "cachedInput": 0, "cacheWrite": 38099, "reasoning": 2798, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.44244, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-repeats.json", "sourceRecordSha256": "e2da6c5e3dc75b1673d1682a62b5c8a7bbe9fad87ab53e47412b4c4c3f368feb", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-repeats.json", "sourceFamily": "claude-repeats", "sourceStage": "opus55-medium-batch10/repeat2/P2" }, { "id": "extended-opus55-medium-batch10-repeat3-p0", "experimentId": "extended-opus55-medium-batch10-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-claude-repeats-v1", "repeatPass": "repeat3", "model": "claude-opus-5-5", "effort": "medium", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 66.22677320896764, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 6410, "cachedInput": 0, "cacheWrite": 26083, "reasoning": 2662, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.336912, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-repeats.json", "sourceRecordSha256": "e2da6c5e3dc75b1673d1682a62b5c8a7bbe9fad87ab53e47412b4c4c3f368feb", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-repeats.json", "sourceFamily": "claude-repeats", "sourceStage": "opus55-medium-batch10/repeat3/P0" }, { "id": "extended-opus55-medium-batch10-repeat3-p1", "experimentId": "extended-opus55-medium-batch10-repeat3-p0", "parentBaselineId": "extended-opus55-medium-batch10-repeat3-p0", "protocolId": "report-only-claude-repeats-v1", "repeatPass": "repeat3", "model": "claude-opus-5-5", "effort": "medium", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 64.46829624999373, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 6420, "cachedInput": 21486, "cacheWrite": 6400, "reasoning": 2671, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.1839452, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-repeats.json", "sourceRecordSha256": "e2da6c5e3dc75b1673d1682a62b5c8a7bbe9fad87ab53e47412b4c4c3f368feb", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-repeats.json", "sourceFamily": "claude-repeats", "sourceStage": "opus55-medium-batch10/repeat3/P1" }, { "id": "extended-opus55-medium-batch10-repeat3-p2", "experimentId": "extended-opus55-medium-batch10-repeat3-p0", "parentBaselineId": "extended-opus55-medium-batch10-repeat3-p0", "protocolId": "report-only-claude-repeats-v1", "repeatPass": "repeat3", "model": "claude-opus-5-5", "effort": "medium", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 65.64715458199498, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 6334, "cachedInput": 4884, "cacheWrite": 33215, "reasoning": 2591, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.39342479999999996, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-repeats.json", "sourceRecordSha256": "e2da6c5e3dc75b1673d1682a62b5c8a7bbe9fad87ab53e47412b4c4c3f368feb", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-repeats.json", "sourceFamily": "claude-repeats", "sourceStage": "opus55-medium-batch10/repeat3/P2" }, { "id": "extended-opus55-xhigh-batch10-repeat2-p0", "experimentId": "extended-opus55-xhigh-batch10-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-opus-5-5", "effort": "xhigh", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 84.52049950000946, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 8927, "cachedInput": 17214, "cacheWrite": 8871, "reasoning": 5130, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.25299879999999997, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus55-xhigh-batch10/repeat2/P0" }, { "id": "extended-opus55-xhigh-batch10-repeat2-p1", "experimentId": "extended-opus55-xhigh-batch10-repeat2-p0", "parentBaselineId": "extended-opus55-xhigh-batch10-repeat2-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-opus-5-5", "effort": "xhigh", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 95.98660266702063, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 9305, "cachedInput": 21486, "cacheWrite": 6395, "reasoning": 4988, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.2416052, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus55-xhigh-batch10/repeat2/P1" }, { "id": "extended-opus55-xhigh-batch10-repeat2-p2", "experimentId": "extended-opus55-xhigh-batch10-repeat2-p0", "parentBaselineId": "extended-opus55-xhigh-batch10-repeat2-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-opus-5-5", "effort": "xhigh", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 91.34219212597236, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 9118, "cachedInput": 4884, "cacheWrite": 33214, "reasoning": 4924, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.44909679999999996, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus55-xhigh-batch10/repeat2/P2" }, { "id": "extended-opus55-xhigh-batch10-repeat3-p0", "experimentId": "extended-opus55-xhigh-batch10-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-opus-5-5", "effort": "xhigh", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 83.33758212602697, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 8947, "cachedInput": 19680, "cacheWrite": 6408, "reasoning": 4699, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.234188, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus55-xhigh-batch10/repeat3/P0" }, { "id": "extended-opus55-xhigh-batch10-repeat3-p1", "experimentId": "extended-opus55-xhigh-batch10-repeat3-p0", "parentBaselineId": "extended-opus55-xhigh-batch10-repeat3-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-opus-5-5", "effort": "xhigh", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 82.6357018740382, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 9017, "cachedInput": 21486, "cacheWrite": 6399, "reasoning": 4776, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.2358772, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus55-xhigh-batch10/repeat3/P1" }, { "id": "extended-opus55-xhigh-batch10-repeat3-p2", "experimentId": "extended-opus55-xhigh-batch10-repeat3-p0", "parentBaselineId": "extended-opus55-xhigh-batch10-repeat3-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-opus-5-5", "effort": "xhigh", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 128.41681133498787, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 9204, "cachedInput": 31698, "cacheWrite": 6396, "reasoning": 5406, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.2416356, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "opus55-xhigh-batch10/repeat3/P2" }, { "id": "extended-qwen3-0.6b-q4km-nonthinking-fresh1-p0", "experimentId": "extended-qwen3-0.6b-q4km-nonthinking-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh1", "model": "qwen3-0.6b-q4km-nonthinking", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 0, "sentiment": 37, "follow_up_needed": 54, "serious_concern_reported": 13, "testimonial_potential": 9 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 22.530319667, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 83190, "output": 2498, "cachedInput": null, "cacheWrite": null, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-0.6b-q4km-nonthinking/fresh1/P0" }, { "id": "extended-qwen3-0.6b-q4km-nonthinking-fresh1-p1", "experimentId": "extended-qwen3-0.6b-q4km-nonthinking-fresh1-p0", "parentBaselineId": "extended-qwen3-0.6b-q4km-nonthinking-fresh1-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh1", "model": "qwen3-0.6b-q4km-nonthinking", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 0, "sentiment": 43, "follow_up_needed": 43, "serious_concern_reported": 11, "testimonial_potential": 11 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 22.685307998, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 93630, "output": 2532, "cachedInput": null, "cacheWrite": null, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-0.6b-q4km-nonthinking/fresh1/P1" }, { "id": "extended-qwen3-0.6b-q4km-nonthinking-fresh1-p2", "experimentId": "extended-qwen3-0.6b-q4km-nonthinking-fresh1-p0", "parentBaselineId": "extended-qwen3-0.6b-q4km-nonthinking-fresh1-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh1", "model": "qwen3-0.6b-q4km-nonthinking", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 0, "sentiment": 19, "follow_up_needed": 38, "serious_concern_reported": 15, "testimonial_potential": 15 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 25.57704362, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 147930, "output": 2540, "cachedInput": null, "cacheWrite": null, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-0.6b-q4km-nonthinking/fresh1/P2" }, { "id": "extended-qwen3-0.6b-q4km-nonthinking-fresh2-p0", "experimentId": "extended-qwen3-0.6b-q4km-nonthinking-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh2", "model": "qwen3-0.6b-q4km-nonthinking", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 0, "sentiment": 37, "follow_up_needed": 54, "serious_concern_reported": 13, "testimonial_potential": 9 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 18.798107875, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 83190, "output": 2498, "cachedInput": null, "cacheWrite": null, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-0.6b-q4km-nonthinking/fresh2/P0" }, { "id": "extended-qwen3-0.6b-q4km-nonthinking-fresh2-p1", "experimentId": "extended-qwen3-0.6b-q4km-nonthinking-fresh2-p0", "parentBaselineId": "extended-qwen3-0.6b-q4km-nonthinking-fresh2-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh2", "model": "qwen3-0.6b-q4km-nonthinking", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 0, "sentiment": 43, "follow_up_needed": 43, "serious_concern_reported": 11, "testimonial_potential": 11 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 25.45147821, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 93630, "output": 2532, "cachedInput": null, "cacheWrite": null, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-0.6b-q4km-nonthinking/fresh2/P1" }, { "id": "extended-qwen3-0.6b-q4km-nonthinking-fresh2-p2", "experimentId": "extended-qwen3-0.6b-q4km-nonthinking-fresh2-p0", "parentBaselineId": "extended-qwen3-0.6b-q4km-nonthinking-fresh2-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh2", "model": "qwen3-0.6b-q4km-nonthinking", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 0, "sentiment": 19, "follow_up_needed": 38, "serious_concern_reported": 15, "testimonial_potential": 15 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 22.487261541, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 147930, "output": 2540, "cachedInput": null, "cacheWrite": null, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-0.6b-q4km-nonthinking/fresh2/P2" }, { "id": "extended-qwen3-0.6b-q4km-nonthinking-fresh3-p0", "experimentId": "extended-qwen3-0.6b-q4km-nonthinking-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh3", "model": "qwen3-0.6b-q4km-nonthinking", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 0, "sentiment": 37, "follow_up_needed": 54, "serious_concern_reported": 13, "testimonial_potential": 9 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 21.576988412, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 83190, "output": 2498, "cachedInput": null, "cacheWrite": null, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-0.6b-q4km-nonthinking/fresh3/P0" }, { "id": "extended-qwen3-0.6b-q4km-nonthinking-fresh3-p1", "experimentId": "extended-qwen3-0.6b-q4km-nonthinking-fresh3-p0", "parentBaselineId": "extended-qwen3-0.6b-q4km-nonthinking-fresh3-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh3", "model": "qwen3-0.6b-q4km-nonthinking", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 0, "sentiment": 43, "follow_up_needed": 43, "serious_concern_reported": 11, "testimonial_potential": 11 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 18.455541125, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 93630, "output": 2532, "cachedInput": null, "cacheWrite": null, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-0.6b-q4km-nonthinking/fresh3/P1" }, { "id": "extended-qwen3-0.6b-q4km-nonthinking-fresh3-p2", "experimentId": "extended-qwen3-0.6b-q4km-nonthinking-fresh3-p0", "parentBaselineId": "extended-qwen3-0.6b-q4km-nonthinking-fresh3-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh3", "model": "qwen3-0.6b-q4km-nonthinking", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 0, "sentiment": 19, "follow_up_needed": 38, "serious_concern_reported": 15, "testimonial_potential": 15 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 26.530995204, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 147930, "output": 2540, "cachedInput": null, "cacheWrite": null, "reasoning": 0, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-0.6b-q4km-nonthinking/fresh3/P2" }, { "id": "extended-qwen3-0.6b-sdk-thinking-off-fresh1-p0", "experimentId": "extended-qwen3-0.6b-sdk-thinking-off-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh1", "model": "qwen3-0.6b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 1, "metrics": { "all_four": 0, "sentiment": 1, "follow_up_needed": 1, "serious_concern_reported": 0, "testimonial_potential": 0 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 22.97576754, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 93210, "output": 2724, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-0.6b-sdk-thinking-off/fresh1/P0" }, { "id": "extended-qwen3-0.6b-sdk-thinking-off-fresh1-p1", "experimentId": "extended-qwen3-0.6b-sdk-thinking-off-fresh1-p0", "parentBaselineId": "extended-qwen3-0.6b-sdk-thinking-off-fresh1-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh1", "model": "qwen3-0.6b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 4, "metrics": { "all_four": 0, "sentiment": 1, "follow_up_needed": 2, "serious_concern_reported": 1, "testimonial_potential": 1 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 28.78640838, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 103710, "output": 2718, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-0.6b-sdk-thinking-off/fresh1/P1" }, { "id": "extended-qwen3-0.6b-sdk-thinking-off-fresh1-p2", "experimentId": "extended-qwen3-0.6b-sdk-thinking-off-fresh1-p0", "parentBaselineId": "extended-qwen3-0.6b-sdk-thinking-off-fresh1-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh1", "model": "qwen3-0.6b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 1, "metrics": { "all_four": 0, "sentiment": 0, "follow_up_needed": 1, "serious_concern_reported": 0, "testimonial_potential": 1 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 27.497086417, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 158010, "output": 2740, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-0.6b-sdk-thinking-off/fresh1/P2" }, { "id": "extended-qwen3-0.6b-sdk-thinking-off-fresh2-p0", "experimentId": "extended-qwen3-0.6b-sdk-thinking-off-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh2", "model": "qwen3-0.6b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 0, "metrics": { "all_four": 0, "sentiment": 0, "follow_up_needed": 0, "serious_concern_reported": 0, "testimonial_potential": 0 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 25.808884253, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 93210, "output": 2724, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-0.6b-sdk-thinking-off/fresh2/P0" }, { "id": "extended-qwen3-0.6b-sdk-thinking-off-fresh2-p1", "experimentId": "extended-qwen3-0.6b-sdk-thinking-off-fresh2-p0", "parentBaselineId": "extended-qwen3-0.6b-sdk-thinking-off-fresh2-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh2", "model": "qwen3-0.6b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 1, "metrics": { "all_four": 0, "sentiment": 0, "follow_up_needed": 0, "serious_concern_reported": 0, "testimonial_potential": 0 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 28.876665668, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 103710, "output": 2728, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-0.6b-sdk-thinking-off/fresh2/P1" }, { "id": "extended-qwen3-0.6b-sdk-thinking-off-fresh2-p2", "experimentId": "extended-qwen3-0.6b-sdk-thinking-off-fresh2-p0", "parentBaselineId": "extended-qwen3-0.6b-sdk-thinking-off-fresh2-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh2", "model": "qwen3-0.6b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 4, "metrics": { "all_four": 0, "sentiment": 3, "follow_up_needed": 3, "serious_concern_reported": 2, "testimonial_potential": 1 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 32.432825994, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 158010, "output": 2720, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-0.6b-sdk-thinking-off/fresh2/P2" }, { "id": "extended-qwen3-0.6b-sdk-thinking-off-fresh3-p0", "experimentId": "extended-qwen3-0.6b-sdk-thinking-off-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh3", "model": "qwen3-0.6b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 1, "metrics": { "all_four": 0, "sentiment": 1, "follow_up_needed": 1, "serious_concern_reported": 0, "testimonial_potential": 1 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 26.15775208, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 93210, "output": 2716, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-0.6b-sdk-thinking-off/fresh3/P0" }, { "id": "extended-qwen3-0.6b-sdk-thinking-off-fresh3-p1", "experimentId": "extended-qwen3-0.6b-sdk-thinking-off-fresh3-p0", "parentBaselineId": "extended-qwen3-0.6b-sdk-thinking-off-fresh3-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh3", "model": "qwen3-0.6b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 3, "metrics": { "all_four": 0, "sentiment": 2, "follow_up_needed": 2, "serious_concern_reported": 0, "testimonial_potential": 1 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 24.660627753, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 103710, "output": 2708, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-0.6b-sdk-thinking-off/fresh3/P1" }, { "id": "extended-qwen3-0.6b-sdk-thinking-off-fresh3-p2", "experimentId": "extended-qwen3-0.6b-sdk-thinking-off-fresh3-p0", "parentBaselineId": "extended-qwen3-0.6b-sdk-thinking-off-fresh3-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh3", "model": "qwen3-0.6b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 5, "metrics": { "all_four": 0, "sentiment": 4, "follow_up_needed": 2, "serious_concern_reported": 2, "testimonial_potential": 2 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 22.997786501, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 158010, "output": 2728, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-0.6b-sdk-thinking-off/fresh3/P2" }, { "id": "extended-qwen3-0.6b-sdk-thinking-on-fresh1-p0", "experimentId": "extended-qwen3-0.6b-sdk-thinking-on-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh1", "model": "qwen3-0.6b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 27, "metrics": { "all_four": 0, "sentiment": 15, "follow_up_needed": 22, "serious_concern_reported": 12, "testimonial_potential": 4 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 128.442207584, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 92970, "output": 15395, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-0.6b-sdk-thinking-on/fresh1/P0" }, { "id": "extended-qwen3-0.6b-sdk-thinking-on-fresh1-p1", "experimentId": "extended-qwen3-0.6b-sdk-thinking-on-fresh1-p0", "parentBaselineId": "extended-qwen3-0.6b-sdk-thinking-on-fresh1-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh1", "model": "qwen3-0.6b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 53, "metrics": { "all_four": 1, "sentiment": 28, "follow_up_needed": 43, "serious_concern_reported": 17, "testimonial_potential": 12 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 169.951753207, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 103470, "output": 16997, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-0.6b-sdk-thinking-on/fresh1/P1" }, { "id": "extended-qwen3-0.6b-sdk-thinking-on-fresh1-p2", "experimentId": "extended-qwen3-0.6b-sdk-thinking-on-fresh1-p0", "parentBaselineId": "extended-qwen3-0.6b-sdk-thinking-on-fresh1-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh1", "model": "qwen3-0.6b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 56, "metrics": { "all_four": 3, "sentiment": 28, "follow_up_needed": 37, "serious_concern_reported": 29, "testimonial_potential": 11 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 203.065629419, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 157770, "output": 19974, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-0.6b-sdk-thinking-on/fresh1/P2" }, { "id": "extended-qwen3-0.6b-sdk-thinking-on-fresh2-p0", "experimentId": "extended-qwen3-0.6b-sdk-thinking-on-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh2", "model": "qwen3-0.6b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 31, "metrics": { "all_four": 0, "sentiment": 18, "follow_up_needed": 20, "serious_concern_reported": 11, "testimonial_potential": 7 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 138.570719627, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 92970, "output": 16285, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-0.6b-sdk-thinking-on/fresh2/P0" }, { "id": "extended-qwen3-0.6b-sdk-thinking-on-fresh2-p1", "experimentId": "extended-qwen3-0.6b-sdk-thinking-on-fresh2-p0", "parentBaselineId": "extended-qwen3-0.6b-sdk-thinking-on-fresh2-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh2", "model": "qwen3-0.6b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 55, "metrics": { "all_four": 3, "sentiment": 30, "follow_up_needed": 42, "serious_concern_reported": 23, "testimonial_potential": 15 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 175.433844877, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 103470, "output": 17763, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-0.6b-sdk-thinking-on/fresh2/P1" }, { "id": "extended-qwen3-0.6b-sdk-thinking-on-fresh2-p2", "experimentId": "extended-qwen3-0.6b-sdk-thinking-on-fresh2-p0", "parentBaselineId": "extended-qwen3-0.6b-sdk-thinking-on-fresh2-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh2", "model": "qwen3-0.6b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 58, "metrics": { "all_four": 1, "sentiment": 31, "follow_up_needed": 42, "serious_concern_reported": 31, "testimonial_potential": 11 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 209.858080041, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 157770, "output": 19965, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-0.6b-sdk-thinking-on/fresh2/P2" }, { "id": "extended-qwen3-0.6b-sdk-thinking-on-fresh3-p0", "experimentId": "extended-qwen3-0.6b-sdk-thinking-on-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh3", "model": "qwen3-0.6b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 30, "metrics": { "all_four": 0, "sentiment": 12, "follow_up_needed": 20, "serious_concern_reported": 10, "testimonial_potential": 6 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 157.797597751, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 92970, "output": 16409, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-0.6b-sdk-thinking-on/fresh3/P0" }, { "id": "extended-qwen3-0.6b-sdk-thinking-on-fresh3-p1", "experimentId": "extended-qwen3-0.6b-sdk-thinking-on-fresh3-p0", "parentBaselineId": "extended-qwen3-0.6b-sdk-thinking-on-fresh3-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh3", "model": "qwen3-0.6b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 48, "metrics": { "all_four": 2, "sentiment": 30, "follow_up_needed": 34, "serious_concern_reported": 22, "testimonial_potential": 11 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 166.763660834, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 103470, "output": 17093, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-0.6b-sdk-thinking-on/fresh3/P1" }, { "id": "extended-qwen3-0.6b-sdk-thinking-on-fresh3-p2", "experimentId": "extended-qwen3-0.6b-sdk-thinking-on-fresh3-p0", "parentBaselineId": "extended-qwen3-0.6b-sdk-thinking-on-fresh3-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh3", "model": "qwen3-0.6b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 58, "metrics": { "all_four": 1, "sentiment": 37, "follow_up_needed": 44, "serious_concern_reported": 21, "testimonial_potential": 13 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 178.159802581, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 157770, "output": 18622, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-0.6b-sdk-thinking-on/fresh3/P2" }, { "id": "extended-qwen3-1.7b-sdk-thinking-off-fresh1-p0", "experimentId": "extended-qwen3-1.7b-sdk-thinking-off-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh1", "model": "qwen3-1.7b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 28, "sentiment": 51, "follow_up_needed": 55, "serious_concern_reported": 45, "testimonial_potential": 43 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 30.12634213, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 93210, "output": 2418, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-1.7b-sdk-thinking-off/fresh1/P0" }, { "id": "extended-qwen3-1.7b-sdk-thinking-off-fresh1-p1", "experimentId": "extended-qwen3-1.7b-sdk-thinking-off-fresh1-p0", "parentBaselineId": "extended-qwen3-1.7b-sdk-thinking-off-fresh1-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh1", "model": "qwen3-1.7b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 59, "metrics": { "all_four": 25, "sentiment": 48, "follow_up_needed": 56, "serious_concern_reported": 43, "testimonial_potential": 44 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 39.759520089, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 103710, "output": 2420, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-1.7b-sdk-thinking-off/fresh1/P1" }, { "id": "extended-qwen3-1.7b-sdk-thinking-off-fresh1-p2", "experimentId": "extended-qwen3-1.7b-sdk-thinking-off-fresh1-p0", "parentBaselineId": "extended-qwen3-1.7b-sdk-thinking-off-fresh1-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh1", "model": "qwen3-1.7b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 57, "metrics": { "all_four": 32, "sentiment": 49, "follow_up_needed": 51, "serious_concern_reported": 37, "testimonial_potential": 54 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 44.707124126, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 158010, "output": 2436, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-1.7b-sdk-thinking-off/fresh1/P2" }, { "id": "extended-qwen3-1.7b-sdk-thinking-off-fresh2-p0", "experimentId": "extended-qwen3-1.7b-sdk-thinking-off-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh2", "model": "qwen3-1.7b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 26, "sentiment": 49, "follow_up_needed": 55, "serious_concern_reported": 45, "testimonial_potential": 42 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 35.284595667, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 93210, "output": 2420, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-1.7b-sdk-thinking-off/fresh2/P0" }, { "id": "extended-qwen3-1.7b-sdk-thinking-off-fresh2-p1", "experimentId": "extended-qwen3-1.7b-sdk-thinking-off-fresh2-p0", "parentBaselineId": "extended-qwen3-1.7b-sdk-thinking-off-fresh2-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh2", "model": "qwen3-1.7b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 26, "sentiment": 48, "follow_up_needed": 56, "serious_concern_reported": 45, "testimonial_potential": 44 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 30.268265211, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 103710, "output": 2416, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-1.7b-sdk-thinking-off/fresh2/P1" }, { "id": "extended-qwen3-1.7b-sdk-thinking-off-fresh2-p2", "experimentId": "extended-qwen3-1.7b-sdk-thinking-off-fresh2-p0", "parentBaselineId": "extended-qwen3-1.7b-sdk-thinking-off-fresh2-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh2", "model": "qwen3-1.7b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 56, "metrics": { "all_four": 30, "sentiment": 43, "follow_up_needed": 49, "serious_concern_reported": 39, "testimonial_potential": 53 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 36.891121336, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 158010, "output": 2436, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-1.7b-sdk-thinking-off/fresh2/P2" }, { "id": "extended-qwen3-1.7b-sdk-thinking-off-fresh3-p0", "experimentId": "extended-qwen3-1.7b-sdk-thinking-off-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh3", "model": "qwen3-1.7b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 26, "sentiment": 50, "follow_up_needed": 55, "serious_concern_reported": 45, "testimonial_potential": 39 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 31.226420211, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 93210, "output": 2422, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-1.7b-sdk-thinking-off/fresh3/P0" }, { "id": "extended-qwen3-1.7b-sdk-thinking-off-fresh3-p1", "experimentId": "extended-qwen3-1.7b-sdk-thinking-off-fresh3-p0", "parentBaselineId": "extended-qwen3-1.7b-sdk-thinking-off-fresh3-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh3", "model": "qwen3-1.7b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 25, "sentiment": 49, "follow_up_needed": 56, "serious_concern_reported": 45, "testimonial_potential": 44 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 35.170392753, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 103710, "output": 2414, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-1.7b-sdk-thinking-off/fresh3/P1" }, { "id": "extended-qwen3-1.7b-sdk-thinking-off-fresh3-p2", "experimentId": "extended-qwen3-1.7b-sdk-thinking-off-fresh3-p0", "parentBaselineId": "extended-qwen3-1.7b-sdk-thinking-off-fresh3-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh3", "model": "qwen3-1.7b-sdk-thinking-off", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 55, "metrics": { "all_four": 30, "sentiment": 44, "follow_up_needed": 49, "serious_concern_reported": 36, "testimonial_potential": 51 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 33.744259578, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 158010, "output": 2442, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-1.7b-sdk-thinking-off/fresh3/P2" }, { "id": "extended-qwen3-1.7b-sdk-thinking-on-fresh1-p0", "experimentId": "extended-qwen3-1.7b-sdk-thinking-on-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh1", "model": "qwen3-1.7b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 24, "sentiment": 49, "follow_up_needed": 55, "serious_concern_reported": 45, "testimonial_potential": 38 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 62.581037208, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 92970, "output": 5165, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-1.7b-sdk-thinking-on/fresh1/P0" }, { "id": "extended-qwen3-1.7b-sdk-thinking-on-fresh1-p1", "experimentId": "extended-qwen3-1.7b-sdk-thinking-on-fresh1-p0", "parentBaselineId": "extended-qwen3-1.7b-sdk-thinking-on-fresh1-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh1", "model": "qwen3-1.7b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 12, "sentiment": 43, "follow_up_needed": 55, "serious_concern_reported": 44, "testimonial_potential": 19 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 205.067266372, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 103470, "output": 15396, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-1.7b-sdk-thinking-on/fresh1/P1" }, { "id": "extended-qwen3-1.7b-sdk-thinking-on-fresh1-p2", "experimentId": "extended-qwen3-1.7b-sdk-thinking-on-fresh1-p0", "parentBaselineId": "extended-qwen3-1.7b-sdk-thinking-on-fresh1-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh1", "model": "qwen3-1.7b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 59, "metrics": { "all_four": 8, "sentiment": 39, "follow_up_needed": 50, "serious_concern_reported": 39, "testimonial_potential": 13 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 299.53782754, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 157770, "output": 22083, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-1.7b-sdk-thinking-on/fresh1/P2" }, { "id": "extended-qwen3-1.7b-sdk-thinking-on-fresh2-p0", "experimentId": "extended-qwen3-1.7b-sdk-thinking-on-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh2", "model": "qwen3-1.7b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 23, "sentiment": 51, "follow_up_needed": 56, "serious_concern_reported": 46, "testimonial_potential": 36 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 71.679114543, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 92970, "output": 5054, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-1.7b-sdk-thinking-on/fresh2/P0" }, { "id": "extended-qwen3-1.7b-sdk-thinking-on-fresh2-p1", "experimentId": "extended-qwen3-1.7b-sdk-thinking-on-fresh2-p0", "parentBaselineId": "extended-qwen3-1.7b-sdk-thinking-on-fresh2-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh2", "model": "qwen3-1.7b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 11, "sentiment": 44, "follow_up_needed": 57, "serious_concern_reported": 46, "testimonial_potential": 18 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 195.237012709, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 103470, "output": 15743, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-1.7b-sdk-thinking-on/fresh2/P1" }, { "id": "extended-qwen3-1.7b-sdk-thinking-on-fresh2-p2", "experimentId": "extended-qwen3-1.7b-sdk-thinking-on-fresh2-p0", "parentBaselineId": "extended-qwen3-1.7b-sdk-thinking-on-fresh2-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh2", "model": "qwen3-1.7b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 59, "metrics": { "all_four": 9, "sentiment": 35, "follow_up_needed": 52, "serious_concern_reported": 42, "testimonial_potential": 14 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 309.51517649699997, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 157770, "output": 22117, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-1.7b-sdk-thinking-on/fresh2/P2" }, { "id": "extended-qwen3-1.7b-sdk-thinking-on-fresh3-p0", "experimentId": "extended-qwen3-1.7b-sdk-thinking-on-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh3", "model": "qwen3-1.7b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 24, "sentiment": 46, "follow_up_needed": 55, "serious_concern_reported": 44, "testimonial_potential": 41 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 87.480106503, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 92970, "output": 6579, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-1.7b-sdk-thinking-on/fresh3/P0" }, { "id": "extended-qwen3-1.7b-sdk-thinking-on-fresh3-p1", "experimentId": "extended-qwen3-1.7b-sdk-thinking-on-fresh3-p0", "parentBaselineId": "extended-qwen3-1.7b-sdk-thinking-on-fresh3-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh3", "model": "qwen3-1.7b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 16, "sentiment": 45, "follow_up_needed": 55, "serious_concern_reported": 49, "testimonial_potential": 21 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 198.839636125, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 103470, "output": 14543, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-1.7b-sdk-thinking-on/fresh3/P1" }, { "id": "extended-qwen3-1.7b-sdk-thinking-on-fresh3-p2", "experimentId": "extended-qwen3-1.7b-sdk-thinking-on-fresh3-p0", "parentBaselineId": "extended-qwen3-1.7b-sdk-thinking-on-fresh3-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh3", "model": "qwen3-1.7b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 8, "sentiment": 41, "follow_up_needed": 52, "serious_concern_reported": 42, "testimonial_potential": 14 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 333.187875168, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 157770, "output": 21946, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3-1.7b-sdk-thinking-on/fresh3/P2" }, { "id": "extended-qwen3.5-4b-sdk-thinking-on-fresh1-p1", "experimentId": "extended-qwen3.5-4b-sdk-thinking-on-fresh1-p0", "parentBaselineId": "extended-qwen3.5-4b-sdk-thinking-on-fresh1-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh1", "model": "qwen3.5-4b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 51, "metrics": { "all_four": 47, "sentiment": 49, "follow_up_needed": 51, "serious_concern_reported": 49, "testimonial_potential": 51 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 3772.666249587, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 106290, "output": 127480, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3.5-4b-sdk-thinking-on/fresh1/P1" }, { "id": "extended-qwen3.5-4b-sdk-thinking-on-fresh1-p2", "experimentId": "extended-qwen3.5-4b-sdk-thinking-on-fresh1-p0", "parentBaselineId": "extended-qwen3.5-4b-sdk-thinking-on-fresh1-p0", "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh1", "model": "qwen3.5-4b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 51, "metrics": { "all_four": 50, "sentiment": 51, "follow_up_needed": 51, "serious_concern_reported": 50, "testimonial_potential": 51 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 4845.770510167, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 161670, "output": 141624, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3.5-4b-sdk-thinking-on/fresh1/P2" }, { "id": "extended-qwen3.5-4b-sdk-thinking-on-fresh2-p0", "experimentId": "extended-qwen3.5-4b-sdk-thinking-on-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-legacy-qwen-repeats-v1", "repeatPass": "fresh2", "model": "qwen3.5-4b-sdk-thinking-on", "effort": null, "provider": null, "surface": "Local execution (see linked report)", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 52, "metrics": { "all_four": 48, "sentiment": 51, "follow_up_needed": 52, "serious_concern_reported": 50, "testimonial_potential": 51 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "client_observed_wall_clock", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 4631.087849917, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 95670, "output": 131533, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Report-only accounting; null means unavailable, not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceRecordSha256": "c05ecd27ee797c1fed81e0e989891ee1c64df15327b15dfae489b6f285c0c9f7", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/legacy-qwen-repeats.json", "sourceFamily": "legacy-qwen-repeats", "sourceStage": "qwen3.5-4b-sdk-thinking-on/fresh2/P0" }, { "id": "extended-semif-direct-repeat2-p0", "experimentId": "extended-semif-direct-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-semif-repeats-v1", "repeatPass": "repeat2", "model": "semif-direct", "effort": null, "provider": "Local native MLX", "surface": "Local native MLX", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 36, "sentiment": 50, "follow_up_needed": 56, "serious_concern_reported": 50, "testimonial_potential": 54 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 716.9428988339496, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 389584, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/semif-repeats.json", "sourceRecordSha256": "4bf539ce413e773bfec09c30fda8b502bd6300fe8b43cb85a41e922ca92c2e34", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/semif-repeats.json", "sourceFamily": "semif-repeats", "sourceStage": "semif-direct/repeat2/P0" }, { "id": "extended-semif-direct-repeat3-p0", "experimentId": "extended-semif-direct-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-semif-repeats-v1", "repeatPass": "repeat3", "model": "semif-direct", "effort": null, "provider": "Local native MLX", "surface": "Local native MLX", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 36, "sentiment": 50, "follow_up_needed": 56, "serious_concern_reported": 50, "testimonial_potential": 54 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 1048.263786584168, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 389584, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/semif-repeats.json", "sourceRecordSha256": "4bf539ce413e773bfec09c30fda8b502bd6300fe8b43cb85a41e922ca92c2e34", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/semif-repeats.json", "sourceFamily": "semif-repeats", "sourceStage": "semif-direct/repeat3/P0" }, { "id": "extended-semif-generated-fresh-v1-fresh1-p0", "experimentId": "extended-semif-generated-fresh-v1-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-semif-generated-repeats-v1", "repeatPass": "fresh1", "model": "semif-generated-bf16", "effort": null, "provider": "Local native MLX", "surface": "Local native MLX", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 52, "metrics": { "all_four": 35, "sentiment": 46, "follow_up_needed": 51, "serious_concern_reported": 47, "testimonial_potential": 46 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 616.328319953871, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 96930, "output": 4680, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/semif-generated-repeats.json", "sourceRecordSha256": "4e6b1b04ff427bc7ff970845b2138d06a79f9309fcb751dca40b90b9f30b07fc", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/semif-generated-repeats.json", "sourceFamily": "semif-generated-repeats", "sourceStage": "semif-generated-fresh-v1/fresh1/P0" }, { "id": "extended-semif-generated-fresh-v1-fresh1-p1", "experimentId": "extended-semif-generated-fresh-v1-fresh1-p0", "parentBaselineId": "extended-semif-generated-fresh-v1-fresh1-p0", "protocolId": "report-only-semif-generated-repeats-v1", "repeatPass": "fresh1", "model": "semif-generated-bf16", "effort": null, "provider": "Local native MLX", "surface": "Local native MLX", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 38, "metrics": { "all_four": 26, "sentiment": 33, "follow_up_needed": 38, "serious_concern_reported": 36, "testimonial_potential": 32 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 742.8316998768132, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 107550, "output": 8070, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/semif-generated-repeats.json", "sourceRecordSha256": "4e6b1b04ff427bc7ff970845b2138d06a79f9309fcb751dca40b90b9f30b07fc", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/semif-generated-repeats.json", "sourceFamily": "semif-generated-repeats", "sourceStage": "semif-generated-fresh-v1/fresh1/P1" }, { "id": "extended-semif-generated-fresh-v1-fresh1-p2", "experimentId": "extended-semif-generated-fresh-v1-fresh1-p0", "parentBaselineId": "extended-semif-generated-fresh-v1-fresh1-p0", "protocolId": "report-only-semif-generated-repeats-v1", "repeatPass": "fresh1", "model": "semif-generated-bf16", "effort": null, "provider": "Local native MLX", "surface": "Local native MLX", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 58, "metrics": { "all_four": 43, "sentiment": 51, "follow_up_needed": 57, "serious_concern_reported": 53, "testimonial_potential": 53 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 506.1932999540004, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 162930, "output": 3204, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/semif-generated-repeats.json", "sourceRecordSha256": "4e6b1b04ff427bc7ff970845b2138d06a79f9309fcb751dca40b90b9f30b07fc", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/semif-generated-repeats.json", "sourceFamily": "semif-generated-repeats", "sourceStage": "semif-generated-fresh-v1/fresh1/P2" }, { "id": "extended-semif-generated-fresh-v1-fresh2-p0", "experimentId": "extended-semif-generated-fresh-v1-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-semif-generated-repeats-v1", "repeatPass": "fresh2", "model": "semif-generated-bf16", "effort": null, "provider": "Local native MLX", "surface": "Local native MLX", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 52, "metrics": { "all_four": 35, "sentiment": 46, "follow_up_needed": 51, "serious_concern_reported": 47, "testimonial_potential": 46 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 427.2997071253485, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 96930, "output": 4680, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/semif-generated-repeats.json", "sourceRecordSha256": "4e6b1b04ff427bc7ff970845b2138d06a79f9309fcb751dca40b90b9f30b07fc", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/semif-generated-repeats.json", "sourceFamily": "semif-generated-repeats", "sourceStage": "semif-generated-fresh-v1/fresh2/P0" }, { "id": "extended-semif-generated-fresh-v1-fresh2-p1", "experimentId": "extended-semif-generated-fresh-v1-fresh2-p0", "parentBaselineId": "extended-semif-generated-fresh-v1-fresh2-p0", "protocolId": "report-only-semif-generated-repeats-v1", "repeatPass": "fresh2", "model": "semif-generated-bf16", "effort": null, "provider": "Local native MLX", "surface": "Local native MLX", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 38, "metrics": { "all_four": 26, "sentiment": 33, "follow_up_needed": 38, "serious_concern_reported": 36, "testimonial_potential": 32 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 876.2724468350643, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 107550, "output": 8070, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/semif-generated-repeats.json", "sourceRecordSha256": "4e6b1b04ff427bc7ff970845b2138d06a79f9309fcb751dca40b90b9f30b07fc", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/semif-generated-repeats.json", "sourceFamily": "semif-generated-repeats", "sourceStage": "semif-generated-fresh-v1/fresh2/P1" }, { "id": "extended-semif-generated-fresh-v1-fresh2-p2", "experimentId": "extended-semif-generated-fresh-v1-fresh2-p0", "parentBaselineId": "extended-semif-generated-fresh-v1-fresh2-p0", "protocolId": "report-only-semif-generated-repeats-v1", "repeatPass": "fresh2", "model": "semif-generated-bf16", "effort": null, "provider": "Local native MLX", "surface": "Local native MLX", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 58, "metrics": { "all_four": 43, "sentiment": 51, "follow_up_needed": 57, "serious_concern_reported": 53, "testimonial_potential": 53 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 389.8651375391055, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 162930, "output": 3204, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/semif-generated-repeats.json", "sourceRecordSha256": "4e6b1b04ff427bc7ff970845b2138d06a79f9309fcb751dca40b90b9f30b07fc", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/semif-generated-repeats.json", "sourceFamily": "semif-generated-repeats", "sourceStage": "semif-generated-fresh-v1/fresh2/P2" }, { "id": "extended-semif-generated-fresh-v1-fresh3-p0", "experimentId": "extended-semif-generated-fresh-v1-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-semif-generated-repeats-v1", "repeatPass": "fresh3", "model": "semif-generated-bf16", "effort": null, "provider": "Local native MLX", "surface": "Local native MLX", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 52, "metrics": { "all_four": 35, "sentiment": 46, "follow_up_needed": 51, "serious_concern_reported": 47, "testimonial_potential": 46 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 377.5668221222586, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 96930, "output": 4680, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/semif-generated-repeats.json", "sourceRecordSha256": "4e6b1b04ff427bc7ff970845b2138d06a79f9309fcb751dca40b90b9f30b07fc", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/semif-generated-repeats.json", "sourceFamily": "semif-generated-repeats", "sourceStage": "semif-generated-fresh-v1/fresh3/P0" }, { "id": "extended-semif-generated-fresh-v1-fresh3-p1", "experimentId": "extended-semif-generated-fresh-v1-fresh3-p0", "parentBaselineId": "extended-semif-generated-fresh-v1-fresh3-p0", "protocolId": "report-only-semif-generated-repeats-v1", "repeatPass": "fresh3", "model": "semif-generated-bf16", "effort": null, "provider": "Local native MLX", "surface": "Local native MLX", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 38, "metrics": { "all_four": 26, "sentiment": 33, "follow_up_needed": 38, "serious_concern_reported": 36, "testimonial_potential": 32 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 547.8781193722971, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 107550, "output": 8070, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/semif-generated-repeats.json", "sourceRecordSha256": "4e6b1b04ff427bc7ff970845b2138d06a79f9309fcb751dca40b90b9f30b07fc", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/semif-generated-repeats.json", "sourceFamily": "semif-generated-repeats", "sourceStage": "semif-generated-fresh-v1/fresh3/P1" }, { "id": "extended-semif-generated-fresh-v1-fresh3-p2", "experimentId": "extended-semif-generated-fresh-v1-fresh3-p0", "parentBaselineId": "extended-semif-generated-fresh-v1-fresh3-p0", "protocolId": "report-only-semif-generated-repeats-v1", "repeatPass": "fresh3", "model": "semif-generated-bf16", "effort": null, "provider": "Local native MLX", "surface": "Local native MLX", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 58, "metrics": { "all_four": 43, "sentiment": 51, "follow_up_needed": 57, "serious_concern_reported": 53, "testimonial_potential": 53 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 385.3376611220883, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 162930, "output": 3204, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/semif-generated-repeats.json", "sourceRecordSha256": "4e6b1b04ff427bc7ff970845b2138d06a79f9309fcb751dca40b90b9f30b07fc", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/semif-generated-repeats.json", "sourceFamily": "semif-generated-repeats", "sourceStage": "semif-generated-fresh-v1/fresh3/P2" }, { "id": "extended-semif-serial-repeat2-p0", "experimentId": "extended-semif-serial-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-semif-repeats-v1", "repeatPass": "repeat2", "model": "semif-serial", "effort": null, "provider": "Local native MLX", "surface": "Local native MLX", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 35, "sentiment": 50, "follow_up_needed": 56, "serious_concern_reported": 49, "testimonial_potential": 54 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 249.34268049991806, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 389584, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/semif-repeats.json", "sourceRecordSha256": "4bf539ce413e773bfec09c30fda8b502bd6300fe8b43cb85a41e922ca92c2e34", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/semif-repeats.json", "sourceFamily": "semif-repeats", "sourceStage": "semif-serial/repeat2/P0" }, { "id": "extended-semif-serial-repeat3-p0", "experimentId": "extended-semif-serial-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-semif-repeats-v1", "repeatPass": "repeat3", "model": "semif-serial", "effort": null, "provider": "Local native MLX", "surface": "Local native MLX", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 35, "sentiment": 50, "follow_up_needed": 56, "serious_concern_reported": 49, "testimonial_potential": 54 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 553.1637961668312, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 389584, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/semif-repeats.json", "sourceRecordSha256": "4bf539ce413e773bfec09c30fda8b502bd6300fe8b43cb85a41e922ca92c2e34", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/semif-repeats.json", "sourceFamily": "semif-repeats", "sourceStage": "semif-serial/repeat3/P0" }, { "id": "extended-semif-shared-repeat2-p0", "experimentId": "extended-semif-shared-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-semif-repeats-v1", "repeatPass": "repeat2", "model": "semif-shared", "effort": null, "provider": "Local native MLX", "surface": "Local native MLX", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 35, "sentiment": 50, "follow_up_needed": 56, "serious_concern_reported": 49, "testimonial_potential": 54 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 241.80881937491358, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 389584, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/semif-repeats.json", "sourceRecordSha256": "4bf539ce413e773bfec09c30fda8b502bd6300fe8b43cb85a41e922ca92c2e34", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/semif-repeats.json", "sourceFamily": "semif-repeats", "sourceStage": "semif-shared/repeat2/P0" }, { "id": "extended-semif-shared-repeat3-p0", "experimentId": "extended-semif-shared-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-semif-repeats-v1", "repeatPass": "repeat3", "model": "semif-shared", "effort": null, "provider": "Local native MLX", "surface": "Local native MLX", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 35, "sentiment": 50, "follow_up_needed": 56, "serious_concern_reported": 49, "testimonial_potential": 54 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 303.5073877060786, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 389584, "output": null, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": null, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "Local hardware and electricity cost not measured." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/semif-repeats.json", "sourceRecordSha256": "4bf539ce413e773bfec09c30fda8b502bd6300fe8b43cb85a41e922ca92c2e34", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/semif-repeats.json", "sourceFamily": "semif-repeats", "sourceStage": "semif-shared/repeat3/P0" }, { "id": "extended-sonnet5-high-phase2-batch10-p0-repeat2-p0", "experimentId": "extended-sonnet5-high-phase2-batch10-p0-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-sonnet-5", "effort": "high", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 133.18262066601892, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 14, "output": 13422, "cachedInput": 4355, "cacheWrite": 28007, "reasoning": 8938, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.24714699999999998, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "sonnet5-high-phase2-batch10-p0/repeat2/P0" }, { "id": "extended-sonnet5-high-phase2-batch10-p0-repeat2-p1", "experimentId": "extended-sonnet5-high-phase2-batch10-p0-repeat2-p0", "parentBaselineId": "extended-sonnet5-high-phase2-batch10-p0-repeat2-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-sonnet-5", "effort": "high", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 57, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 116.0833671670116, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 12344, "cachedInput": 0, "cacheWrite": 28116, "reasoning": 8549, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.235928, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "sonnet5-high-phase2-batch10-p0/repeat2/P1" }, { "id": "extended-sonnet5-high-phase2-batch10-p0-repeat2-p2", "experimentId": "extended-sonnet5-high-phase2-batch10-p0-repeat2-p0", "parentBaselineId": "extended-sonnet5-high-phase2-batch10-p0-repeat2-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-sonnet-5", "effort": "high", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 120.18653154096683, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 12716, "cachedInput": 0, "cacheWrite": 38326, "reasoning": 8804, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.280488, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "sonnet5-high-phase2-batch10-p0/repeat2/P2" }, { "id": "extended-sonnet5-high-phase2-batch10-p0-repeat3-p0", "experimentId": "extended-sonnet5-high-phase2-batch10-p0-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-sonnet-5", "effort": "high", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 112.27298429197981, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 16, "output": 13177, "cachedInput": 28335, "cacheWrite": 11001, "reasoning": 7910, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.181473, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "sonnet5-high-phase2-batch10-p0/repeat3/P0" }, { "id": "extended-sonnet5-high-phase2-batch10-p0-repeat3-p1", "experimentId": "extended-sonnet5-high-phase2-batch10-p0-repeat3-p0", "parentBaselineId": "extended-sonnet5-high-phase2-batch10-p0-repeat3-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-sonnet-5", "effort": "high", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 111.04303950001486, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 14, "output": 12858, "cachedInput": 26049, "cacheWrite": 9753, "reasoning": 8269, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.17282979999999998, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "sonnet5-high-phase2-batch10-p0/repeat3/P1" }, { "id": "extended-sonnet5-high-phase2-batch10-p0-repeat3-p2", "experimentId": "extended-sonnet5-high-phase2-batch10-p0-repeat3-p0", "parentBaselineId": "extended-sonnet5-high-phase2-batch10-p0-repeat3-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-sonnet-5", "effort": "high", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 57, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 125.09921091698925, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 12494, "cachedInput": 31548, "cacheWrite": 6777, "reasoning": 8586, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.1583816, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "sonnet5-high-phase2-batch10-p0/repeat3/P2" }, { "id": "extended-sonnet5-low-first-pass-phase2-batch10-p0-repeat2-p0", "experimentId": "extended-sonnet5-low-first-pass-phase2-batch10-p0-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-sonnet-5", "effort": "low", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 70.9413867930125, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 6953, "cachedInput": 0, "cacheWrite": 26314, "reasoning": 3179, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.17481, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "sonnet5-low-first-pass-phase2-batch10-p0/repeat2/P0" }, { "id": "extended-sonnet5-low-first-pass-phase2-batch10-p0-repeat2-p1", "experimentId": "extended-sonnet5-low-first-pass-phase2-batch10-p0-repeat2-p0", "parentBaselineId": "extended-sonnet5-low-first-pass-phase2-batch10-p0-repeat2-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-sonnet-5", "effort": "low", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 60.557100082951365, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 6163, "cachedInput": 0, "cacheWrite": 28113, "reasoning": 2388, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.174106, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "sonnet5-low-first-pass-phase2-batch10-p0/repeat2/P1" }, { "id": "extended-sonnet5-low-first-pass-phase2-batch10-p0-repeat2-p2", "experimentId": "extended-sonnet5-low-first-pass-phase2-batch10-p0-repeat2-p0", "parentBaselineId": "extended-sonnet5-low-first-pass-phase2-batch10-p0-repeat2-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-sonnet-5", "effort": "low", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 54, "sentiment": 58, "follow_up_needed": 58, "serious_concern_reported": 58, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 59.086245581973344, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 6272, "cachedInput": 0, "cacheWrite": 38325, "reasoning": 2470, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.216044, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "sonnet5-low-first-pass-phase2-batch10-p0/repeat2/P2" }, { "id": "extended-sonnet5-low-first-pass-phase2-batch10-p0-repeat3-p0", "experimentId": "extended-sonnet5-low-first-pass-phase2-batch10-p0-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-sonnet-5", "effort": "low", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 54, "sentiment": 57, "follow_up_needed": 58, "serious_concern_reported": 58, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 108.4758306670119, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 5437, "cachedInput": 19530, "cacheWrite": 6786, "reasoning": 1652, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.085444, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "sonnet5-low-first-pass-phase2-batch10-p0/repeat3/P0" }, { "id": "extended-sonnet5-low-first-pass-phase2-batch10-p0-repeat3-p1", "experimentId": "extended-sonnet5-low-first-pass-phase2-batch10-p0-repeat3-p0", "parentBaselineId": "extended-sonnet5-low-first-pass-phase2-batch10-p0-repeat3-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-sonnet-5", "effort": "low", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 57, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 56.09264616895234, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 5702, "cachedInput": 21336, "cacheWrite": 6779, "reasoning": 1931, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.08842720000000001, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "sonnet5-low-first-pass-phase2-batch10-p0/repeat3/P1" }, { "id": "extended-sonnet5-low-first-pass-phase2-batch10-p0-repeat3-p2", "experimentId": "extended-sonnet5-low-first-pass-phase2-batch10-p0-repeat3-p0", "parentBaselineId": "extended-sonnet5-low-first-pass-phase2-batch10-p0-repeat3-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-sonnet-5", "effort": "low", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 60, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 83.34943937504431, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 7548, "cachedInput": 31548, "cacheWrite": 6779, "reasoning": 3773, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.1089296, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "sonnet5-low-first-pass-phase2-batch10-p0/repeat3/P2" }, { "id": "extended-sonnet5-medium-phase2-batch10-p0-repeat2-p0", "experimentId": "extended-sonnet5-medium-phase2-batch10-p0-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-sonnet-5", "effort": "medium", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 55, "sentiment": 57, "follow_up_needed": 59, "serious_concern_reported": 60, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 86.72165520800627, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 9176, "cachedInput": 0, "cacheWrite": 26314, "reasoning": 5373, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.19704, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "sonnet5-medium-phase2-batch10-p0/repeat2/P0" }, { "id": "extended-sonnet5-medium-phase2-batch10-p0-repeat2-p1", "experimentId": "extended-sonnet5-medium-phase2-batch10-p0-repeat2-p0", "parentBaselineId": "extended-sonnet5-medium-phase2-batch10-p0-repeat2-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-sonnet-5", "effort": "medium", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 57, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 79.70686987397494, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 8944, "cachedInput": 0, "cacheWrite": 28118, "reasoning": 5152, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.201936, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "sonnet5-medium-phase2-batch10-p0/repeat2/P1" }, { "id": "extended-sonnet5-medium-phase2-batch10-p0-repeat2-p2", "experimentId": "extended-sonnet5-medium-phase2-batch10-p0-repeat2-p0", "parentBaselineId": "extended-sonnet5-medium-phase2-batch10-p0-repeat2-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-sonnet-5", "effort": "medium", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 79.78559387600399, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 8900, "cachedInput": 0, "cacheWrite": 38327, "reasoning": 5135, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.242332, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "sonnet5-medium-phase2-batch10-p0/repeat2/P2" }, { "id": "extended-sonnet5-medium-phase2-batch10-p0-repeat3-p0", "experimentId": "extended-sonnet5-medium-phase2-batch10-p0-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-sonnet-5", "effort": "medium", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 84.5670228730014, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 9552, "cachedInput": 19530, "cacheWrite": 6783, "reasoning": 5765, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.126582, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "sonnet5-medium-phase2-batch10-p0/repeat3/P0" }, { "id": "extended-sonnet5-medium-phase2-batch10-p0-repeat3-p1", "experimentId": "extended-sonnet5-medium-phase2-batch10-p0-repeat3-p0", "parentBaselineId": "extended-sonnet5-medium-phase2-batch10-p0-repeat3-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-sonnet-5", "effort": "medium", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 53, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 57 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 95.5807142900303, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 8823, "cachedInput": 21336, "cacheWrite": 6776, "reasoning": 5073, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.11962519999999999, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "sonnet5-medium-phase2-batch10-p0/repeat3/P1" }, { "id": "extended-sonnet5-medium-phase2-batch10-p0-repeat3-p2", "experimentId": "extended-sonnet5-medium-phase2-batch10-p0-repeat3-p0", "parentBaselineId": "extended-sonnet5-medium-phase2-batch10-p0-repeat3-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-sonnet-5", "effort": "medium", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 55, "sentiment": 57, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 76.57748458301648, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 8691, "cachedInput": 31548, "cacheWrite": 6778, "reasoning": 4916, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.1203556, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "sonnet5-medium-phase2-batch10-p0/repeat3/P2" }, { "id": "extended-sonnet5-xhigh-phase2-batch10-p0-repeat2-p0", "experimentId": "extended-sonnet5-xhigh-phase2-batch10-p0-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-sonnet-5", "effort": "xhigh", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 177.05484321000404, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 16, "output": 20133, "cachedInput": 8769, "cacheWrite": 34012, "reasoning": 14832, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.3391638, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "sonnet5-xhigh-phase2-batch10-p0/repeat2/P0" }, { "id": "extended-sonnet5-xhigh-phase2-batch10-p0-repeat2-p1", "experimentId": "extended-sonnet5-xhigh-phase2-batch10-p0-repeat2-p0", "parentBaselineId": "extended-sonnet5-xhigh-phase2-batch10-p0-repeat2-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-sonnet-5", "effort": "xhigh", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 149.3009529580013, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 16622, "cachedInput": 0, "cacheWrite": 28117, "reasoning": 12684, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.27871199999999996, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "sonnet5-xhigh-phase2-batch10-p0/repeat2/P1" }, { "id": "extended-sonnet5-xhigh-phase2-batch10-p0-repeat2-p2", "experimentId": "extended-sonnet5-xhigh-phase2-batch10-p0-repeat2-p0", "parentBaselineId": "extended-sonnet5-xhigh-phase2-batch10-p0-repeat2-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat2", "model": "claude-sonnet-5", "effort": "xhigh", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 148.17296291698585, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 14, "output": 17310, "cachedInput": 6366, "cacheWrite": 41547, "reasoning": 12729, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.3405892, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "sonnet5-xhigh-phase2-batch10-p0/repeat2/P2" }, { "id": "extended-sonnet5-xhigh-phase2-batch10-p0-repeat3-p0", "experimentId": "extended-sonnet5-xhigh-phase2-batch10-p0-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-sonnet-5", "effort": "xhigh", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 158.5679731250275, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 14, "output": 19062, "cachedInput": 23895, "cacheWrite": 10180, "reasoning": 14497, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.236147, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "sonnet5-xhigh-phase2-batch10-p0/repeat3/P0" }, { "id": "extended-sonnet5-xhigh-phase2-batch10-p0-repeat3-p1", "experimentId": "extended-sonnet5-xhigh-phase2-batch10-p0-repeat3-p0", "parentBaselineId": "extended-sonnet5-xhigh-phase2-batch10-p0-repeat3-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-sonnet-5", "effort": "xhigh", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 55, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 57, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 166.44707787502557, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 18, "output": 18715, "cachedInput": 35407, "cacheWrite": 15952, "reasoning": 12679, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.2580754, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "sonnet5-xhigh-phase2-batch10-p0/repeat3/P1" }, { "id": "extended-sonnet5-xhigh-phase2-batch10-p0-repeat3-p2", "experimentId": "extended-sonnet5-xhigh-phase2-batch10-p0-repeat3-p0", "parentBaselineId": "extended-sonnet5-xhigh-phase2-batch10-p0-repeat3-p0", "protocolId": "report-only-claude-roster-repeats-v1", "repeatPass": "repeat3", "model": "claude-sonnet-5", "effort": "xhigh", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 157.72351800100296, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 16, "output": 19059, "cachedInput": 44348, "cacheWrite": 12034, "reasoning": 13774, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.2476276, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceRecordSha256": "11a44a7368695bb8f53961ba05b55b8eeca1701487ecd6036b9a110027af6a4d", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/claude-roster-repeats.json", "sourceFamily": "claude-roster-repeats", "sourceStage": "sonnet5-xhigh-phase2-batch10-p0/repeat3/P2" }, { "id": "extended-sonnet55-high-pass2-p0", "experimentId": "extended-sonnet55-high-pass2-p0", "parentBaselineId": null, "protocolId": "report-only-sonnet55-fresh-matched3-v1", "repeatPass": "pass2", "model": "claude-sonnet-5-5", "effort": "high", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 115.81429495802149, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 7126, "cachedInput": 19680, "cacheWrite": 6443, "reasoning": 3377, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.100992, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceRecordSha256": "ddcf0e523d49a5873285daa0c606d7e875251711670fc97ffb13d7d4c04b9f56", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceFamily": "sonnet55-fresh-matched3", "sourceStage": "sonnet55-high/pass2/P0" }, { "id": "extended-sonnet55-high-pass2-p1", "experimentId": "extended-sonnet55-high-pass2-p0", "parentBaselineId": "extended-sonnet55-high-pass2-p0", "protocolId": "report-only-sonnet55-fresh-matched3-v1", "repeatPass": "pass2", "model": "claude-sonnet-5-5", "effort": "high", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 61.44147383404197, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 7325, "cachedInput": 21486, "cacheWrite": 6434, "reasoning": 3576, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.1033072, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceRecordSha256": "ddcf0e523d49a5873285daa0c606d7e875251711670fc97ffb13d7d4c04b9f56", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceFamily": "sonnet55-fresh-matched3", "sourceStage": "sonnet55-high/pass2/P1" }, { "id": "extended-sonnet55-high-pass2-p2", "experimentId": "extended-sonnet55-high-pass2-p0", "parentBaselineId": "extended-sonnet55-high-pass2-p0", "protocolId": "report-only-sonnet55-fresh-matched3-v1", "repeatPass": "pass2", "model": "claude-sonnet-5-5", "effort": "high", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 83.5798405840178, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 7599, "cachedInput": 31698, "cacheWrite": 6435, "reasoning": 3850, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.1080936, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceRecordSha256": "ddcf0e523d49a5873285daa0c606d7e875251711670fc97ffb13d7d4c04b9f56", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceFamily": "sonnet55-fresh-matched3", "sourceStage": "sonnet55-high/pass2/P2" }, { "id": "extended-sonnet55-high-pass3-p0", "experimentId": "extended-sonnet55-high-pass3-p0", "parentBaselineId": null, "protocolId": "report-only-sonnet55-fresh-matched3-v1", "repeatPass": "pass3", "model": "claude-sonnet-5-5", "effort": "high", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 66.18971800094005, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 7378, "cachedInput": 19680, "cacheWrite": 6441, "reasoning": 3629, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.103504, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceRecordSha256": "ddcf0e523d49a5873285daa0c606d7e875251711670fc97ffb13d7d4c04b9f56", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceFamily": "sonnet55-fresh-matched3", "sourceStage": "sonnet55-high/pass3/P0" }, { "id": "extended-sonnet55-high-pass3-p1", "experimentId": "extended-sonnet55-high-pass3-p0", "parentBaselineId": "extended-sonnet55-high-pass3-p0", "protocolId": "report-only-sonnet55-fresh-matched3-v1", "repeatPass": "pass3", "model": "claude-sonnet-5-5", "effort": "high", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 112.33996779093286, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 7127, "cachedInput": 21486, "cacheWrite": 6436, "reasoning": 3378, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.1013352, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceRecordSha256": "ddcf0e523d49a5873285daa0c606d7e875251711670fc97ffb13d7d4c04b9f56", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceFamily": "sonnet55-fresh-matched3", "sourceStage": "sonnet55-high/pass3/P1" }, { "id": "extended-sonnet55-high-pass3-p2", "experimentId": "extended-sonnet55-high-pass3-p0", "parentBaselineId": "extended-sonnet55-high-pass3-p0", "protocolId": "report-only-sonnet55-fresh-matched3-v1", "repeatPass": "pass3", "model": "claude-sonnet-5-5", "effort": "high", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 68.4066152489977, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 7765, "cachedInput": 31698, "cacheWrite": 6435, "reasoning": 4025, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.1097536, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceRecordSha256": "ddcf0e523d49a5873285daa0c606d7e875251711670fc97ffb13d7d4c04b9f56", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceFamily": "sonnet55-fresh-matched3", "sourceStage": "sonnet55-high/pass3/P2" }, { "id": "extended-sonnet55-low-pass2-p0", "experimentId": "extended-sonnet55-low-pass2-p0", "parentBaselineId": null, "protocolId": "report-only-sonnet55-fresh-matched3-v1", "repeatPass": "pass2", "model": "claude-sonnet-5-5", "effort": "low", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 66.85611708305078, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 3738, "cachedInput": 19680, "cacheWrite": 6439, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.067096, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceRecordSha256": "ddcf0e523d49a5873285daa0c606d7e875251711670fc97ffb13d7d4c04b9f56", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceFamily": "sonnet55-fresh-matched3", "sourceStage": "sonnet55-low/pass2/P0" }, { "id": "extended-sonnet55-low-pass2-p1", "experimentId": "extended-sonnet55-low-pass2-p0", "parentBaselineId": "extended-sonnet55-low-pass2-p0", "protocolId": "report-only-sonnet55-fresh-matched3-v1", "repeatPass": "pass2", "model": "claude-sonnet-5-5", "effort": "low", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 40.52400224999292, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 3749, "cachedInput": 21486, "cacheWrite": 6438, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.0675632, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceRecordSha256": "ddcf0e523d49a5873285daa0c606d7e875251711670fc97ffb13d7d4c04b9f56", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceFamily": "sonnet55-fresh-matched3", "sourceStage": "sonnet55-low/pass2/P1" }, { "id": "extended-sonnet55-low-pass2-p2", "experimentId": "extended-sonnet55-low-pass2-p0", "parentBaselineId": "extended-sonnet55-low-pass2-p0", "protocolId": "report-only-sonnet55-fresh-matched3-v1", "repeatPass": "pass2", "model": "claude-sonnet-5-5", "effort": "low", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 92.91560487198876, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 3733, "cachedInput": 31698, "cacheWrite": 6433, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.0694256, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceRecordSha256": "ddcf0e523d49a5873285daa0c606d7e875251711670fc97ffb13d7d4c04b9f56", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceFamily": "sonnet55-fresh-matched3", "sourceStage": "sonnet55-low/pass2/P2" }, { "id": "extended-sonnet55-low-pass3-p0", "experimentId": "extended-sonnet55-low-pass3-p0", "parentBaselineId": null, "protocolId": "report-only-sonnet55-fresh-matched3-v1", "repeatPass": "pass3", "model": "claude-sonnet-5-5", "effort": "low", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 54.41092774900608, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 3744, "cachedInput": 19680, "cacheWrite": 6443, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.067172, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceRecordSha256": "ddcf0e523d49a5873285daa0c606d7e875251711670fc97ffb13d7d4c04b9f56", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceFamily": "sonnet55-fresh-matched3", "sourceStage": "sonnet55-low/pass3/P0" }, { "id": "extended-sonnet55-low-pass3-p1", "experimentId": "extended-sonnet55-low-pass3-p0", "parentBaselineId": "extended-sonnet55-low-pass3-p0", "protocolId": "report-only-sonnet55-fresh-matched3-v1", "repeatPass": "pass3", "model": "claude-sonnet-5-5", "effort": "low", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 60, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 49.287640082940925, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 3744, "cachedInput": 21486, "cacheWrite": 6438, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.0675132, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceRecordSha256": "ddcf0e523d49a5873285daa0c606d7e875251711670fc97ffb13d7d4c04b9f56", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceFamily": "sonnet55-fresh-matched3", "sourceStage": "sonnet55-low/pass3/P1" }, { "id": "extended-sonnet55-low-pass3-p2", "experimentId": "extended-sonnet55-low-pass3-p0", "parentBaselineId": "extended-sonnet55-low-pass3-p0", "protocolId": "report-only-sonnet55-fresh-matched3-v1", "repeatPass": "pass3", "model": "claude-sonnet-5-5", "effort": "low", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 56, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 59 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 62.38269233395113, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 3732, "cachedInput": 31698, "cacheWrite": 6434, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.0694196, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceRecordSha256": "ddcf0e523d49a5873285daa0c606d7e875251711670fc97ffb13d7d4c04b9f56", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceFamily": "sonnet55-fresh-matched3", "sourceStage": "sonnet55-low/pass3/P2" }, { "id": "extended-sonnet55-medium-pass2-p0", "experimentId": "extended-sonnet55-medium-pass2-p0", "parentBaselineId": null, "protocolId": "report-only-sonnet55-fresh-matched3-v1", "repeatPass": "pass2", "model": "claude-sonnet-5-5", "effort": "medium", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 64.01290579192573, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 4505, "cachedInput": 19680, "cacheWrite": 6440, "reasoning": 766, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.07477, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceRecordSha256": "ddcf0e523d49a5873285daa0c606d7e875251711670fc97ffb13d7d4c04b9f56", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceFamily": "sonnet55-fresh-matched3", "sourceStage": "sonnet55-medium/pass2/P0" }, { "id": "extended-sonnet55-medium-pass2-p1", "experimentId": "extended-sonnet55-medium-pass2-p0", "parentBaselineId": "extended-sonnet55-medium-pass2-p0", "protocolId": "report-only-sonnet55-fresh-matched3-v1", "repeatPass": "pass2", "model": "claude-sonnet-5-5", "effort": "medium", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 57, "follow_up_needed": 59, "serious_concern_reported": 60, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 93.55141858296702, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 3744, "cachedInput": 21486, "cacheWrite": 6435, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.0675012, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceRecordSha256": "ddcf0e523d49a5873285daa0c606d7e875251711670fc97ffb13d7d4c04b9f56", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceFamily": "sonnet55-fresh-matched3", "sourceStage": "sonnet55-medium/pass2/P1" }, { "id": "extended-sonnet55-medium-pass2-p2", "experimentId": "extended-sonnet55-medium-pass2-p0", "parentBaselineId": "extended-sonnet55-medium-pass2-p0", "protocolId": "report-only-sonnet55-fresh-matched3-v1", "repeatPass": "pass2", "model": "claude-sonnet-5-5", "effort": "medium", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 74.13302816601936, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 3733, "cachedInput": 31698, "cacheWrite": 6435, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.0694336, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceRecordSha256": "ddcf0e523d49a5873285daa0c606d7e875251711670fc97ffb13d7d4c04b9f56", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceFamily": "sonnet55-fresh-matched3", "sourceStage": "sonnet55-medium/pass2/P2" }, { "id": "extended-sonnet55-medium-pass3-p0", "experimentId": "extended-sonnet55-medium-pass3-p0", "parentBaselineId": null, "protocolId": "report-only-sonnet55-fresh-matched3-v1", "repeatPass": "pass3", "model": "claude-sonnet-5-5", "effort": "medium", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 48.53507916483795, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 3733, "cachedInput": 19680, "cacheWrite": 6441, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.067054, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceRecordSha256": "ddcf0e523d49a5873285daa0c606d7e875251711670fc97ffb13d7d4c04b9f56", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceFamily": "sonnet55-fresh-matched3", "sourceStage": "sonnet55-medium/pass3/P0" }, { "id": "extended-sonnet55-medium-pass3-p1", "experimentId": "extended-sonnet55-medium-pass3-p0", "parentBaselineId": "extended-sonnet55-medium-pass3-p0", "protocolId": "report-only-sonnet55-fresh-matched3-v1", "repeatPass": "pass3", "model": "claude-sonnet-5-5", "effort": "medium", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 59, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 47.62114091706462, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 4370, "cachedInput": 21486, "cacheWrite": 6439, "reasoning": 630, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.0737772, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceRecordSha256": "ddcf0e523d49a5873285daa0c606d7e875251711670fc97ffb13d7d4c04b9f56", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceFamily": "sonnet55-fresh-matched3", "sourceStage": "sonnet55-medium/pass3/P1" }, { "id": "extended-sonnet55-medium-pass3-p2", "experimentId": "extended-sonnet55-medium-pass3-p0", "parentBaselineId": "extended-sonnet55-medium-pass3-p0", "protocolId": "report-only-sonnet55-fresh-matched3-v1", "repeatPass": "pass3", "model": "claude-sonnet-5-5", "effort": "medium", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 57, "sentiment": 58, "follow_up_needed": 60, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 52.608155582041945, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 3733, "cachedInput": 31698, "cacheWrite": 6433, "reasoning": 0, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.0694256, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceRecordSha256": "ddcf0e523d49a5873285daa0c606d7e875251711670fc97ffb13d7d4c04b9f56", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceFamily": "sonnet55-fresh-matched3", "sourceStage": "sonnet55-medium/pass3/P2" }, { "id": "extended-sonnet55-xhigh-pass2-p0", "experimentId": "extended-sonnet55-xhigh-pass2-p0", "parentBaselineId": null, "protocolId": "report-only-sonnet55-fresh-matched3-v1", "repeatPass": "pass2", "model": "claude-sonnet-5-5", "effort": "xhigh", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 90.35186229291139, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 9168, "cachedInput": 19680, "cacheWrite": 6444, "reasoning": 5419, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.121416, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceRecordSha256": "ddcf0e523d49a5873285daa0c606d7e875251711670fc97ffb13d7d4c04b9f56", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceFamily": "sonnet55-fresh-matched3", "sourceStage": "sonnet55-xhigh/pass2/P0" }, { "id": "extended-sonnet55-xhigh-pass2-p1", "experimentId": "extended-sonnet55-xhigh-pass2-p0", "parentBaselineId": "extended-sonnet55-xhigh-pass2-p0", "protocolId": "report-only-sonnet55-fresh-matched3-v1", "repeatPass": "pass2", "model": "claude-sonnet-5-5", "effort": "xhigh", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 76.6885762080201, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 9428, "cachedInput": 21486, "cacheWrite": 6433, "reasoning": 5679, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.1243332, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceRecordSha256": "ddcf0e523d49a5873285daa0c606d7e875251711670fc97ffb13d7d4c04b9f56", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceFamily": "sonnet55-fresh-matched3", "sourceStage": "sonnet55-xhigh/pass2/P1" }, { "id": "extended-sonnet55-xhigh-pass2-p2", "experimentId": "extended-sonnet55-xhigh-pass2-p0", "parentBaselineId": "extended-sonnet55-xhigh-pass2-p0", "protocolId": "report-only-sonnet55-fresh-matched3-v1", "repeatPass": "pass2", "model": "claude-sonnet-5-5", "effort": "xhigh", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 96.11923187394859, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 9844, "cachedInput": 31698, "cacheWrite": 6440, "reasoning": 6095, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.1305636, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceRecordSha256": "ddcf0e523d49a5873285daa0c606d7e875251711670fc97ffb13d7d4c04b9f56", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceFamily": "sonnet55-fresh-matched3", "sourceStage": "sonnet55-xhigh/pass2/P2" }, { "id": "extended-sonnet55-xhigh-pass3-p0", "experimentId": "extended-sonnet55-xhigh-pass3-p0", "parentBaselineId": null, "protocolId": "report-only-sonnet55-fresh-matched3-v1", "repeatPass": "pass3", "model": "claude-sonnet-5-5", "effort": "xhigh", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 72.99803716607857, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 8694, "cachedInput": 19680, "cacheWrite": 6443, "reasoning": 4945, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.116672, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceRecordSha256": "ddcf0e523d49a5873285daa0c606d7e875251711670fc97ffb13d7d4c04b9f56", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceFamily": "sonnet55-fresh-matched3", "sourceStage": "sonnet55-xhigh/pass3/P0" }, { "id": "extended-sonnet55-xhigh-pass3-p1", "experimentId": "extended-sonnet55-xhigh-pass3-p0", "parentBaselineId": "extended-sonnet55-xhigh-pass3-p0", "protocolId": "report-only-sonnet55-fresh-matched3-v1", "repeatPass": "pass3", "model": "claude-sonnet-5-5", "effort": "xhigh", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 60, "serious_concern_reported": 59, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 87.94773270800943, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 9213, "cachedInput": 21486, "cacheWrite": 6437, "reasoning": 5468, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.1221992, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceRecordSha256": "ddcf0e523d49a5873285daa0c606d7e875251711670fc97ffb13d7d4c04b9f56", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceFamily": "sonnet55-fresh-matched3", "sourceStage": "sonnet55-xhigh/pass3/P1" }, { "id": "extended-sonnet55-xhigh-pass3-p2", "experimentId": "extended-sonnet55-xhigh-pass3-p0", "parentBaselineId": "extended-sonnet55-xhigh-pass3-p0", "protocolId": "report-only-sonnet55-fresh-matched3-v1", "repeatPass": "pass3", "model": "claude-sonnet-5-5", "effort": "xhigh", "provider": "Claude subscription", "surface": "Claude subscription", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 58, "sentiment": 59, "follow_up_needed": 59, "serious_concern_reported": 58, "testimonial_potential": 60 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "client_wall_clock", "requests": 6, "totalRequests": 6, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 73.16336962505011, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 12, "output": 9089, "cachedInput": 31698, "cacheWrite": 6436, "reasoning": 5345, "reportedRequests": 6, "totalRequests": 6, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.1229976, "unknownUpperBoundUsd": null, "unknownCostCount": null, "note": "CLI API-equivalent list-price estimate; subscription billing and quota consumed are unknown." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceRecordSha256": "ddcf0e523d49a5873285daa0c606d7e875251711670fc97ffb13d7d4c04b9f56", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/sonnet55-fresh-matched3.json", "sourceFamily": "sonnet55-fresh-matched3", "sourceStage": "sonnet55-xhigh/pass3/P2" }, { "id": "extended-typesafe-jev113-native-prompts-fresh1-p0", "experimentId": "extended-typesafe-jev113-native-prompts-fresh1-p0", "parentBaselineId": null, "protocolId": "report-only-jev-native-prompt-findings-v1", "repeatPass": "fresh1", "model": "jev-1.13.0", "effort": null, "provider": "TypeSafe", "surface": "OpenRouter native Choice", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 54, "sentiment": 56, "follow_up_needed": 58, "serious_concern_reported": 57, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 32.501095745, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 140260, "output": 11176, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.00589092, "estimatedUsd": null, "unknownUpperBoundUsd": 0.0, "unknownCostCount": null, "note": "Known OpenRouter charge: provider-reported usage.cost summed over saved responses. The unknown bound is the reservation for a request with no recorded charge." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/jev-native-prompt-findings.json", "sourceRecordSha256": "464943a09a6bfe0f73c5d81d1427ec43fcb759167d2a79d7ff3ddaa7c1af23cc", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/jev-native-prompt-findings.json", "sourceFamily": "jev-native-prompt-findings", "sourceStage": "typesafe-jev113-native-prompts/fresh1/P0" }, { "id": "extended-typesafe-jev113-native-prompts-fresh1-p1", "experimentId": "extended-typesafe-jev113-native-prompts-fresh1-p0", "parentBaselineId": "extended-typesafe-jev113-native-prompts-fresh1-p0", "protocolId": "report-only-jev-native-prompt-findings-v1", "repeatPass": "fresh1", "model": "jev-1.13.0", "effort": null, "provider": "TypeSafe", "surface": "OpenRouter native Choice", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 54, "sentiment": 56, "follow_up_needed": 58, "serious_concern_reported": 57, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 32.260497459999996, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 152500, "output": 11176, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.006405, "estimatedUsd": null, "unknownUpperBoundUsd": 0.0, "unknownCostCount": null, "note": "Known OpenRouter charge: provider-reported usage.cost summed over saved responses. The unknown bound is the reservation for a request with no recorded charge." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/jev-native-prompt-findings.json", "sourceRecordSha256": "464943a09a6bfe0f73c5d81d1427ec43fcb759167d2a79d7ff3ddaa7c1af23cc", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/jev-native-prompt-findings.json", "sourceFamily": "jev-native-prompt-findings", "sourceStage": "typesafe-jev113-native-prompts/fresh1/P1" }, { "id": "extended-typesafe-jev113-native-prompts-fresh1-p2", "experimentId": "extended-typesafe-jev113-native-prompts-fresh1-p0", "parentBaselineId": "extended-typesafe-jev113-native-prompts-fresh1-p0", "protocolId": "report-only-jev-native-prompt-findings-v1", "repeatPass": "fresh1", "model": "jev-1.13.0", "effort": null, "provider": "TypeSafe", "surface": "OpenRouter native Choice", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 54, "sentiment": 56, "follow_up_needed": 58, "serious_concern_reported": 57, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 32.840852914, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 163120, "output": 11176, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.00685104, "estimatedUsd": null, "unknownUpperBoundUsd": 0.0, "unknownCostCount": null, "note": "Known OpenRouter charge: provider-reported usage.cost summed over saved responses. The unknown bound is the reservation for a request with no recorded charge." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/jev-native-prompt-findings.json", "sourceRecordSha256": "464943a09a6bfe0f73c5d81d1427ec43fcb759167d2a79d7ff3ddaa7c1af23cc", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/jev-native-prompt-findings.json", "sourceFamily": "jev-native-prompt-findings", "sourceStage": "typesafe-jev113-native-prompts/fresh1/P2" }, { "id": "extended-typesafe-jev113-native-prompts-fresh2-p0", "experimentId": "extended-typesafe-jev113-native-prompts-fresh2-p0", "parentBaselineId": null, "protocolId": "report-only-jev-native-prompt-findings-v1", "repeatPass": "fresh2", "model": "jev-1.13.0", "effort": null, "provider": "TypeSafe", "surface": "OpenRouter native Choice", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 53, "sentiment": 57, "follow_up_needed": 57, "serious_concern_reported": 57, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 42.68306479, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 140260, "output": 11176, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.00589092, "estimatedUsd": null, "unknownUpperBoundUsd": 0.0, "unknownCostCount": null, "note": "Known OpenRouter charge: provider-reported usage.cost summed over saved responses. The unknown bound is the reservation for a request with no recorded charge." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/jev-native-prompt-findings.json", "sourceRecordSha256": "464943a09a6bfe0f73c5d81d1427ec43fcb759167d2a79d7ff3ddaa7c1af23cc", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/jev-native-prompt-findings.json", "sourceFamily": "jev-native-prompt-findings", "sourceStage": "typesafe-jev113-native-prompts/fresh2/P0" }, { "id": "extended-typesafe-jev113-native-prompts-fresh2-p1", "experimentId": "extended-typesafe-jev113-native-prompts-fresh2-p0", "parentBaselineId": "extended-typesafe-jev113-native-prompts-fresh2-p0", "protocolId": "report-only-jev-native-prompt-findings-v1", "repeatPass": "fresh2", "model": "jev-1.13.0", "effort": null, "provider": "TypeSafe", "surface": "OpenRouter native Choice", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": null, "valid": 59, "metrics": { "all_four": 53, "sentiment": 55, "follow_up_needed": 57, "serious_concern_reported": 56, "testimonial_potential": 57 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 35.985815126, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 152500, "output": 11176, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.006405, "estimatedUsd": null, "unknownUpperBoundUsd": 0.0, "unknownCostCount": null, "note": "Known OpenRouter charge: provider-reported usage.cost summed over saved responses. The unknown bound is the reservation for a request with no recorded charge." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/jev-native-prompt-findings.json", "sourceRecordSha256": "464943a09a6bfe0f73c5d81d1427ec43fcb759167d2a79d7ff3ddaa7c1af23cc", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/jev-native-prompt-findings.json", "sourceFamily": "jev-native-prompt-findings", "sourceStage": "typesafe-jev113-native-prompts/fresh2/P1" }, { "id": "extended-typesafe-jev113-native-prompts-fresh2-p2", "experimentId": "extended-typesafe-jev113-native-prompts-fresh2-p0", "parentBaselineId": "extended-typesafe-jev113-native-prompts-fresh2-p0", "protocolId": "report-only-jev-native-prompt-findings-v1", "repeatPass": "fresh2", "model": "jev-1.13.0", "effort": null, "provider": "TypeSafe", "surface": "OpenRouter native Choice", "condition": "P2", "complete": false, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": null, "valid": 17, "metrics": { "all_four": 15, "sentiment": 16, "follow_up_needed": 17, "serious_concern_reported": 16, "testimonial_potential": 17 }, "pairedEligible": false, "resultStatus": "stopped", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 10.295085001, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 46207, "output": 3166, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.001940694, "estimatedUsd": null, "unknownUpperBoundUsd": 0.001344, "unknownCostCount": null, "note": "Known OpenRouter charge: provider-reported usage.cost summed over saved responses. The unknown bound is the reservation for a request with no recorded charge." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/jev-native-prompt-findings.json", "sourceRecordSha256": "464943a09a6bfe0f73c5d81d1427ec43fcb759167d2a79d7ff3ddaa7c1af23cc", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/jev-native-prompt-findings.json", "sourceFamily": "jev-native-prompt-findings", "sourceStage": "typesafe-jev113-native-prompts/fresh2/P2" }, { "id": "extended-typesafe-jev113-native-prompts-fresh3-p0", "experimentId": "extended-typesafe-jev113-native-prompts-fresh3-p0", "parentBaselineId": null, "protocolId": "report-only-jev-native-prompt-findings-v1", "repeatPass": "fresh3", "model": "jev-1.13.0", "effort": null, "provider": "TypeSafe", "surface": "OpenRouter native Choice", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": null, "valid": 59, "metrics": { "all_four": 52, "sentiment": 55, "follow_up_needed": 56, "serious_concern_reported": 56, "testimonial_potential": 57 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 40.561939086, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 140260, "output": 11176, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.00589092, "estimatedUsd": null, "unknownUpperBoundUsd": 0.0, "unknownCostCount": null, "note": "Known OpenRouter charge: provider-reported usage.cost summed over saved responses. The unknown bound is the reservation for a request with no recorded charge." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/jev-native-prompt-findings.json", "sourceRecordSha256": "464943a09a6bfe0f73c5d81d1427ec43fcb759167d2a79d7ff3ddaa7c1af23cc", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/jev-native-prompt-findings.json", "sourceFamily": "jev-native-prompt-findings", "sourceStage": "typesafe-jev113-native-prompts/fresh3/P0" }, { "id": "extended-typesafe-jev113-native-prompts-fresh3-p1", "experimentId": "extended-typesafe-jev113-native-prompts-fresh3-p0", "parentBaselineId": "extended-typesafe-jev113-native-prompts-fresh3-p0", "protocolId": "report-only-jev-native-prompt-findings-v1", "repeatPass": "fresh3", "model": "jev-1.13.0", "effort": null, "provider": "TypeSafe", "surface": "OpenRouter native Choice", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 54, "sentiment": 56, "follow_up_needed": 58, "serious_concern_reported": 57, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 31.992508667, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 152500, "output": 11176, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.006405, "estimatedUsd": null, "unknownUpperBoundUsd": 0.0, "unknownCostCount": null, "note": "Known OpenRouter charge: provider-reported usage.cost summed over saved responses. The unknown bound is the reservation for a request with no recorded charge." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/jev-native-prompt-findings.json", "sourceRecordSha256": "464943a09a6bfe0f73c5d81d1427ec43fcb759167d2a79d7ff3ddaa7c1af23cc", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/jev-native-prompt-findings.json", "sourceFamily": "jev-native-prompt-findings", "sourceStage": "typesafe-jev113-native-prompts/fresh3/P1" }, { "id": "extended-typesafe-jev113-native-prompts-fresh3-p2", "experimentId": "extended-typesafe-jev113-native-prompts-fresh3-p0", "parentBaselineId": "extended-typesafe-jev113-native-prompts-fresh3-p0", "protocolId": "report-only-jev-native-prompt-findings-v1", "repeatPass": "fresh3", "model": "jev-1.13.0", "effort": null, "provider": "TypeSafe", "surface": "OpenRouter native Choice", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 54, "sentiment": 57, "follow_up_needed": 58, "serious_concern_reported": 57, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 0, "totalRequests": null, "medianSeconds": null, "p95Seconds": null, "totalSeconds": 35.909151751, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 163120, "output": 11176, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": null, "totalRequests": null, "complete": false, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": 0.00685104, "estimatedUsd": null, "unknownUpperBoundUsd": 0.0, "unknownCostCount": null, "note": "Known OpenRouter charge: provider-reported usage.cost summed over saved responses. The unknown bound is the reservation for a request with no recorded charge." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/jev-native-prompt-findings.json", "sourceRecordSha256": "464943a09a6bfe0f73c5d81d1427ec43fcb759167d2a79d7ff3ddaa7c1af23cc", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/jev-native-prompt-findings.json", "sourceFamily": "jev-native-prompt-findings", "sourceStage": "typesafe-jev113-native-prompts/fresh3/P2" }, { "id": "extended-typesafe-jev113-v2-repeat2-p0", "experimentId": "extended-typesafe-jev113-v2-repeat2-p0", "parentBaselineId": null, "protocolId": "report-only-typesafe-repeats-v1", "repeatPass": "repeat2", "model": "jev-1.13.0", "effort": null, "provider": "TypeSafe", "surface": "TypeSafe native Choice API", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 58, "metrics": { "all_four": 52, "sentiment": 54, "follow_up_needed": 56, "serious_concern_reported": 55, "testimonial_potential": 56 }, "pairedEligible": false, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 140260, "output": 11176, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.00589092, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Reported input tokens at the saved $0.042/M rate; actual provider invoice and server inference time unavailable. Unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/typesafe-repeats.json", "sourceRecordSha256": "664b298af5a4780fa97ccf58bdd89ab9c12fcf4801319db9bfbd3d7136d8ed3e", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/typesafe-repeats.json", "sourceFamily": "typesafe-repeats", "sourceStage": "typesafe-jev113-v2/repeat2/P0" }, { "id": "extended-typesafe-jev113-v2-repeat2-p1", "experimentId": "extended-typesafe-jev113-v2-repeat2-p0", "parentBaselineId": "extended-typesafe-jev113-v2-repeat2-p0", "protocolId": "report-only-typesafe-repeats-v1", "repeatPass": "repeat2", "model": "jev-1.13.0", "effort": null, "provider": "TypeSafe", "surface": "TypeSafe native Choice API", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 54, "sentiment": 56, "follow_up_needed": 58, "serious_concern_reported": 57, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 152500, "output": 11176, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.006405, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Reported input tokens at the saved $0.042/M rate; actual provider invoice and server inference time unavailable. Unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/typesafe-repeats.json", "sourceRecordSha256": "664b298af5a4780fa97ccf58bdd89ab9c12fcf4801319db9bfbd3d7136d8ed3e", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/typesafe-repeats.json", "sourceFamily": "typesafe-repeats", "sourceStage": "typesafe-jev113-v2/repeat2/P1" }, { "id": "extended-typesafe-jev113-v2-repeat2-p2", "experimentId": "extended-typesafe-jev113-v2-repeat2-p0", "parentBaselineId": "extended-typesafe-jev113-v2-repeat2-p0", "protocolId": "report-only-typesafe-repeats-v1", "repeatPass": "repeat2", "model": "jev-1.13.0", "effort": null, "provider": "TypeSafe", "surface": "TypeSafe native Choice API", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 54, "sentiment": 57, "follow_up_needed": 58, "serious_concern_reported": 57, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 163120, "output": 11180, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.00685104, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Reported input tokens at the saved $0.042/M rate; actual provider invoice and server inference time unavailable. Unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/typesafe-repeats.json", "sourceRecordSha256": "664b298af5a4780fa97ccf58bdd89ab9c12fcf4801319db9bfbd3d7136d8ed3e", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/typesafe-repeats.json", "sourceFamily": "typesafe-repeats", "sourceStage": "typesafe-jev113-v2/repeat2/P2" }, { "id": "extended-typesafe-jev113-v2-repeat3-p0", "experimentId": "extended-typesafe-jev113-v2-repeat3-p0", "parentBaselineId": null, "protocolId": "report-only-typesafe-repeats-v1", "repeatPass": "repeat3", "model": "jev-1.13.0", "effort": null, "provider": "TypeSafe", "surface": "TypeSafe native Choice API", "condition": "P0", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 54, "sentiment": 56, "follow_up_needed": 58, "serious_concern_reported": 57, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 140260, "output": 11176, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.00589092, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Reported input tokens at the saved $0.042/M rate; actual provider invoice and server inference time unavailable. Unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/typesafe-repeats.json", "sourceRecordSha256": "664b298af5a4780fa97ccf58bdd89ab9c12fcf4801319db9bfbd3d7136d8ed3e", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/typesafe-repeats.json", "sourceFamily": "typesafe-repeats", "sourceStage": "typesafe-jev113-v2/repeat3/P0" }, { "id": "extended-typesafe-jev113-v2-repeat3-p1", "experimentId": "extended-typesafe-jev113-v2-repeat3-p0", "parentBaselineId": "extended-typesafe-jev113-v2-repeat3-p0", "protocolId": "report-only-typesafe-repeats-v1", "repeatPass": "repeat3", "model": "jev-1.13.0", "effort": null, "provider": "TypeSafe", "surface": "TypeSafe native Choice API", "condition": "P1", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 54, "sentiment": 56, "follow_up_needed": 58, "serious_concern_reported": 57, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 152500, "output": 11176, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.006405, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Reported input tokens at the saved $0.042/M rate; actual provider invoice and server inference time unavailable. Unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/typesafe-repeats.json", "sourceRecordSha256": "664b298af5a4780fa97ccf58bdd89ab9c12fcf4801319db9bfbd3d7136d8ed3e", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/typesafe-repeats.json", "sourceFamily": "typesafe-repeats", "sourceStage": "typesafe-jev113-v2/repeat3/P1" }, { "id": "extended-typesafe-jev113-v2-repeat3-p2", "experimentId": "extended-typesafe-jev113-v2-repeat3-p0", "parentBaselineId": "extended-typesafe-jev113-v2-repeat3-p0", "protocolId": "report-only-typesafe-repeats-v1", "repeatPass": "repeat3", "model": "jev-1.13.0", "effort": null, "provider": "TypeSafe", "surface": "TypeSafe native Choice API", "condition": "P2", "complete": true, "records": 60, "recordsMeaning": "planned denominator", "savedResponses": 60, "valid": 60, "metrics": { "all_four": 54, "sentiment": 57, "follow_up_needed": 58, "serious_concern_reported": 57, "testimonial_potential": 58 }, "pairedEligible": true, "resultStatus": "complete", "timing": { "kind": "unavailable", "requests": 60, "totalRequests": 60, "medianSeconds": null, "p95Seconds": null, "totalSeconds": null, "inferenceSeconds": null, "inferenceReportedRequests": 0, "note": "Client duration is not isolated inference time; unavailable values remain null." }, "tokens": { "input": 163120, "output": 11180, "cachedInput": null, "cacheWrite": null, "reasoning": null, "reportedRequests": 60, "totalRequests": 60, "complete": true, "note": "Only values stated in the linked public report are shown; missing categories are unavailable." }, "cost": { "actualUsd": null, "knownUsd": null, "estimatedUsd": 0.00685104, "unknownUpperBoundUsd": null, "unknownCostCount": 0, "note": "Reported input tokens at the saved $0.042/M rate; actual provider invoice and server inference time unavailable. Unknown charges are not zero." }, "sourceOnlyDetails": true, "sourceRecordsUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/typesafe-repeats.json", "sourceRecordSha256": "664b298af5a4780fa97ccf58bdd89ab9c12fcf4801319db9bfbd3d7136d8ed3e", "evidenceUrl": "https://github.com/adambkovacs/candidate-experience-benchmark/blob/main/public-site/typesafe-repeats.json", "sourceFamily": "typesafe-repeats", "sourceStage": "typesafe-jev113-v2/repeat3/P2" } ], "runCount": 637, "note": "Report-backed saved stages absent from the original explorer. Historical original phases and exact restatements are excluded; remaining report families are enumerated in the coverage audit." }