actor/judge prompt eval 闭合: actor 3.0.5 正文强化+baseline(7轮); judge 3.0.14 正文强化+anyTerms同义词补全+baseline(judge-a 13轮/judge-b 33轮); registry/checker 版本对齐+顺序锚点 fail-closed 双保险 W-GOLD-LIVE live_prompt: play-loop 契约开口(request/3+provenance/3+ReferenceAssetRecord/1+Registry/1+迁移清单15条); cheap_verify 切v3+消费对账六闸(只消费active)+生成prompt注入接线(0 active不注入); Node runner playtest-v3.cdp.cjs 升/3+绊线恢复; 真模型回归验向后兼容 full_gate+三批基线: full_gate.py 集成runner串六子门+降级+22测; baseline_gates.py fresh25阈值+historical11预期表(2 needs_human交创始人定标)+shadow20框架+38测 注: registry cheap-system 登记 1.8.0→1.8.1 同步此前在途 cheap-system.md frontmatter 升版(修 pre-commit 版本漂移); cheap_verify/cheap_studio/validate/test_acceptance_v3/test_cheap_service_driver 为在途M含本会话叠加+此前W-AXIS在途(同一线无法hunk分离); 3红测试根因与raw审计未入本提交
37 lines
398 KiB
JSON
37 lines
398 KiB
JSON
{"ts": "2026-07-25T17:31:48.752154+00:00", "runId": "20260725T173010.532051Z-p8401-n1785000610532308000", "promptId": "playtest.judge-b", "version": "3.0.13", "model": "MiniMax-M3", "promptBodySha256": "13cb5660724674a8a34cd9dfef33d721089ba4c4a1385c302f1e9fdde70f8ff5", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "5fe275ceda1c8359c0dcda603fdf391466c04f980d418d2b0a56f83fce10d604", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "626b138b134ed67d6689c4d5c70aeced0720120ad190d37f56068cbf627336ed"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 6, "nCorrect": 5, "successRate": 0.8333, "gate1_schema": true, "gate2_success": false, "gate3_regression": false, "gate4_cost_latency": false, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "61848e13d8dbc95bbd38697b8ba3de3e07d7f43f089f84ad361353a7da23574b", "stability": {"qualified": false, "consecutiveRuns": 0, "previousRunIds": [], "cohortReady": false, "identity": {"promptBodySha256": "13cb5660724674a8a34cd9dfef33d721089ba4c4a1385c302f1e9fdde70f8ff5", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "5fe275ceda1c8359c0dcda603fdf391466c04f980d418d2b0a56f83fce10d604", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "626b138b134ed67d6689c4d5c70aeced0720120ad190d37f56068cbf627336ed"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "61848e13d8dbc95bbd38697b8ba3de3e07d7f43f089f84ad361353a7da23574b"}, "requestBodySha256": {"judge:accept:business-settlement": "08cb04e653c0b47e731afb9150bbfb562efc02293bf7add22efd2ba145ce054e", "judge:inconclusive:business-visual-conflict": "cfc7ca3d40dc10499ca3b1a13cff71c95fc92f878bed6097f466ad1c5f79ff2e", "judge:accept:puzzle-victory": "4c45f84c46cb09c5ce81b270f7c949b85aea7e44e5591c931f627bbb2fab0e43", "judge:inconclusive:puzzle-conflict": "83a983b3c51e042596e62ab383ceaa939bfda242b4d59343f154ce7a21be8b00", "judge:reject:runner-crashed-injection": "2f3c8e03e8f94d4bfef7b239c3bfce8f74794491754cfb52f5219aac165fd977", "judge:inconclusive:missing-proof-injection": "932dfdf43db3c7a78239505677209d304562b29e9d3f5ca3bd794b3151862e52"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": false}}}, "perKeyCorrect": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": false}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T173010.532051Z-p8401-n1785000610532308000/run-manifest.json", "sha256": "0229a542b0a67696027968a3932a9b0a23de2f8e3a45973bcf234360367fd206", "runAuditHash": "cb71dc2c450b4c2984cd257abaa828d0744e12332dfc1ed99076d416778aad92", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.130169, "promptTokens": 18782, "completionTokens": 10164, "totalLatencyMs": 96754, "nError": 0, "gate3_note": "基线身份与本轮 Prompt/fixture/model/seed 不一致,必须重建基线", "gate4_note": "基线身份不一致,成本/延迟不可比较", "gate5_note": "本轮基础闸未全绿,稳定性计数归零", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T173010.532051Z-p8401-n1785000610532308000/response-0001.txt", "size": 762, "sha256": "4a0306908f475ce39308190c5be4efd6f827c10e9f0add652d2efb1c323c1d70", "requestBodySha256": "08cb04e653c0b47e731afb9150bbfb562efc02293bf7add22efd2ba145ce054e"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T173010.532051Z-p8401-n1785000610532308000/response-0002.txt", "size": 975, "sha256": "ac5e96f6c57ad5a375fdf09d99d8bd30f095b461bb8e66e150ca75a725736a68", "requestBodySha256": "cfc7ca3d40dc10499ca3b1a13cff71c95fc92f878bed6097f466ad1c5f79ff2e"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T173010.532051Z-p8401-n1785000610532308000/response-0003.txt", "size": 627, "sha256": "db60c3f00788f9b6ea84df04313552f13736ca3310c6d497ed371e0a63cdcda7", "requestBodySha256": "4c45f84c46cb09c5ce81b270f7c949b85aea7e44e5591c931f627bbb2fab0e43"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T173010.532051Z-p8401-n1785000610532308000/response-0004.txt", "size": 1041, "sha256": "829f757e58a7893b439dcd602b672f984d6d37cfaec788a8df08d6cf555ab9ed", "requestBodySha256": "83a983b3c51e042596e62ab383ceaa939bfda242b4d59343f154ce7a21be8b00"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T173010.532051Z-p8401-n1785000610532308000/response-0005.txt", "size": 781, "sha256": "5372a159fef83f524708b9b0024e8eca46a998f0008a0b8c0e74cad42a7ab6ae", "requestBodySha256": "2f3c8e03e8f94d4bfef7b239c3bfce8f74794491754cfb52f5219aac165fd977"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": false, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": false}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T173010.532051Z-p8401-n1785000610532308000/response-0006.txt", "size": 706, "sha256": "806a92870f8c5602c77477ae27f254eff8f67b37b2a16b98bce7ce925b052e2c", "requestBodySha256": "932dfdf43db3c7a78239505677209d304562b29e9d3f5ca3bd794b3151862e52"}}}}
|
||
{"ts": "2026-07-25T17:33:51.175496+00:00", "runId": "20260725T173149.850633Z-p40144-n1785000709850841000", "promptId": "playtest.judge-b", "version": "3.0.13", "model": "MiniMax-M3", "promptBodySha256": "13cb5660724674a8a34cd9dfef33d721089ba4c4a1385c302f1e9fdde70f8ff5", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "5fe275ceda1c8359c0dcda603fdf391466c04f980d418d2b0a56f83fce10d604", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "626b138b134ed67d6689c4d5c70aeced0720120ad190d37f56068cbf627336ed"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 6, "nCorrect": 5, "successRate": 0.8333, "gate1_schema": true, "gate2_success": false, "gate3_regression": false, "gate4_cost_latency": false, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "61848e13d8dbc95bbd38697b8ba3de3e07d7f43f089f84ad361353a7da23574b", "stability": {"qualified": false, "consecutiveRuns": 0, "previousRunIds": [], "cohortReady": false, "identity": {"promptBodySha256": "13cb5660724674a8a34cd9dfef33d721089ba4c4a1385c302f1e9fdde70f8ff5", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "5fe275ceda1c8359c0dcda603fdf391466c04f980d418d2b0a56f83fce10d604", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "626b138b134ed67d6689c4d5c70aeced0720120ad190d37f56068cbf627336ed"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "61848e13d8dbc95bbd38697b8ba3de3e07d7f43f089f84ad361353a7da23574b"}, "requestBodySha256": {"judge:accept:business-settlement": "08cb04e653c0b47e731afb9150bbfb562efc02293bf7add22efd2ba145ce054e", "judge:inconclusive:business-visual-conflict": "cfc7ca3d40dc10499ca3b1a13cff71c95fc92f878bed6097f466ad1c5f79ff2e", "judge:accept:puzzle-victory": "4c45f84c46cb09c5ce81b270f7c949b85aea7e44e5591c931f627bbb2fab0e43", "judge:inconclusive:puzzle-conflict": "83a983b3c51e042596e62ab383ceaa939bfda242b4d59343f154ce7a21be8b00", "judge:reject:runner-crashed-injection": "2f3c8e03e8f94d4bfef7b239c3bfce8f74794491754cfb52f5219aac165fd977", "judge:inconclusive:missing-proof-injection": "932dfdf43db3c7a78239505677209d304562b29e9d3f5ca3bd794b3151862e52"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": false, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}}, "perKeyCorrect": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": false, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T173149.850633Z-p40144-n1785000709850841000/run-manifest.json", "sha256": "476b4f059667f17ec1e2adf42b78ed0478eb6c5305539ddb08d0c1a0c80e76a8", "runAuditHash": "6bc611455c6f49c4914f4a7ed9063a93fa4d18ab97862d8d6ec3df17a24192de", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.158963, "promptTokens": 18782, "completionTokens": 13451, "totalLatencyMs": 119851, "nError": 0, "gate3_note": "基线身份与本轮 Prompt/fixture/model/seed 不一致,必须重建基线", "gate4_note": "基线身份不一致,成本/延迟不可比较", "gate5_note": "本轮基础闸未全绿,稳定性计数归零", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T173149.850633Z-p40144-n1785000709850841000/response-0001.txt", "size": 704, "sha256": "7111413043a3ccead3efb2f66b83233f6ea49200a725c573b9a4608a9db95437", "requestBodySha256": "08cb04e653c0b47e731afb9150bbfb562efc02293bf7add22efd2ba145ce054e"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": false, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": false, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T173149.850633Z-p40144-n1785000709850841000/response-0002.txt", "size": 1141, "sha256": "2e00587b7d6c7869dae75732cf10b65410bdbdc40d12a33976a90e8b39dcdee5", "requestBodySha256": "cfc7ca3d40dc10499ca3b1a13cff71c95fc92f878bed6097f466ad1c5f79ff2e"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T173149.850633Z-p40144-n1785000709850841000/response-0003.txt", "size": 601, "sha256": "230f3c3b68b7bc2e185b7d10894a21710c1d6800fa8b2f0812557920558d40f9", "requestBodySha256": "4c45f84c46cb09c5ce81b270f7c949b85aea7e44e5591c931f627bbb2fab0e43"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T173149.850633Z-p40144-n1785000709850841000/response-0004.txt", "size": 1075, "sha256": "1647fba3d17e2086eec637f75963f576fad403ff563762554f0b7596e401dd34", "requestBodySha256": "83a983b3c51e042596e62ab383ceaa939bfda242b4d59343f154ce7a21be8b00"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T173149.850633Z-p40144-n1785000709850841000/response-0005.txt", "size": 879, "sha256": "90a63bcbf81fd2c00a983b55113d5c2f9405137ab60ee9fde0f88d5a24df498d", "requestBodySha256": "2f3c8e03e8f94d4bfef7b239c3bfce8f74794491754cfb52f5219aac165fd977"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T173149.850633Z-p40144-n1785000709850841000/response-0006.txt", "size": 827, "sha256": "397290614369d3f45557a3788049d5c3a0a3e8576471ac40c07bb6bb37b84f08", "requestBodySha256": "932dfdf43db3c7a78239505677209d304562b29e9d3f5ca3bd794b3151862e52"}}}}
|
||
{"ts": "2026-07-25T17:36:18.870825+00:00", "runId": "20260725T173352.225441Z-p68191-n1785000832225669000", "promptId": "playtest.judge-b", "version": "3.0.13", "model": "MiniMax-M3", "promptBodySha256": "13cb5660724674a8a34cd9dfef33d721089ba4c4a1385c302f1e9fdde70f8ff5", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "5fe275ceda1c8359c0dcda603fdf391466c04f980d418d2b0a56f83fce10d604", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "626b138b134ed67d6689c4d5c70aeced0720120ad190d37f56068cbf627336ed"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 4, "nCorrect": 3, "successRate": 0.5, "gate1_schema": false, "gate2_success": false, "gate3_regression": false, "gate4_cost_latency": false, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "61848e13d8dbc95bbd38697b8ba3de3e07d7f43f089f84ad361353a7da23574b", "stability": {"qualified": false, "consecutiveRuns": 0, "previousRunIds": [], "cohortReady": false, "identity": {"promptBodySha256": "13cb5660724674a8a34cd9dfef33d721089ba4c4a1385c302f1e9fdde70f8ff5", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "5fe275ceda1c8359c0dcda603fdf391466c04f980d418d2b0a56f83fce10d604", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "626b138b134ed67d6689c4d5c70aeced0720120ad190d37f56068cbf627336ed"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "61848e13d8dbc95bbd38697b8ba3de3e07d7f43f089f84ad361353a7da23574b"}, "requestBodySha256": {"judge:accept:business-settlement": "08cb04e653c0b47e731afb9150bbfb562efc02293bf7add22efd2ba145ce054e", "judge:inconclusive:business-visual-conflict": "cfc7ca3d40dc10499ca3b1a13cff71c95fc92f878bed6097f466ad1c5f79ff2e", "judge:accept:puzzle-victory": "4c45f84c46cb09c5ce81b270f7c949b85aea7e44e5591c931f627bbb2fab0e43", "judge:inconclusive:puzzle-conflict": "83a983b3c51e042596e62ab383ceaa939bfda242b4d59343f154ce7a21be8b00", "judge:reject:runner-crashed-injection": "2f3c8e03e8f94d4bfef7b239c3bfce8f74794491754cfb52f5219aac165fd977", "judge:inconclusive:missing-proof-injection": "932dfdf43db3c7a78239505677209d304562b29e9d3f5ca3bd794b3151862e52"}, "signatures": {"judge:accept:business-settlement": {"decision": null, "failureClass": null, "obligations": null, "textTraceability": {"problems": false, "contradictions": false, "summary": false}}, "judge:inconclusive:business-visual-conflict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": false, "summary": false}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": null, "failureClass": null, "obligations": null, "textTraceability": {"problems": false, "contradictions": false, "summary": false}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}}, "perKeyCorrect": {"judge:accept:business-settlement": false, "judge:inconclusive:business-visual-conflict": false, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": false, "judge:inconclusive:missing-proof-injection": true}, "perKeySchemaOk": {"judge:accept:business-settlement": false, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": false, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T173352.225441Z-p68191-n1785000832225669000/run-manifest.json", "sha256": "4380ad2e2448bce9b9015fc4d21f79ef8ec71c467cb731eb22bc166bd3130e69", "runAuditHash": "2de865846d154bab5da6f2c6c9075cae420c8baba3af728bf1342be044ddda71", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.160426, "promptTokens": 18778, "completionTokens": 13619, "totalLatencyMs": 145188, "nError": 0, "gate3_note": "基线身份与本轮 Prompt/fixture/model/seed 不一致,必须重建基线", "gate4_note": "基线身份不一致,成本/延迟不可比较", "gate5_note": "本轮基础闸未全绿,稳定性计数归零", "perKey": {"judge:accept:business-settlement": {"schema_ok": false, "correct": false, "verdict": {"decision": null, "failureClass": null, "obligations": null, "textTraceability": {"problems": false, "contradictions": false, "summary": false}}, "schema_bad": ["<非 JSON 对象>", "生产 parser:unknown_obligation_result:Judge 返回未知义务:sem-business.revenue-positive"], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T173352.225441Z-p68191-n1785000832225669000/response-0001.txt", "size": 730, "sha256": "da35a0ba8aebd035334b2c1e7afbb6acf35fded6c8f66df13b226b22d41698fe", "requestBodySha256": "08cb04e653c0b47e731afb9150bbfb562efc02293bf7add22efd2ba145ce054e"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": false, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": false, "summary": false}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T173352.225441Z-p68191-n1785000832225669000/response-0002.txt", "size": 685, "sha256": "fb025bdcd820fe38679e54a1ef04653c9da8f48ac30f90ddea23fbeb07b0147a", "requestBodySha256": "cfc7ca3d40dc10499ca3b1a13cff71c95fc92f878bed6097f466ad1c5f79ff2e"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T173352.225441Z-p68191-n1785000832225669000/response-0003.txt", "size": 680, "sha256": "ebd1935bb64933c92a95af96dca538f8ad7dbf18d90c4a04f3dafbaa18a62e42", "requestBodySha256": "4c45f84c46cb09c5ce81b270f7c949b85aea7e44e5591c931f627bbb2fab0e43"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T173352.225441Z-p68191-n1785000832225669000/response-0004.txt", "size": 1154, "sha256": "ff0f73c1e4f43c05715759da8ca73f6a0316d368f66cb6ab0a802a0e52094ea6", "requestBodySha256": "83a983b3c51e042596e62ab383ceaa939bfda242b4d59343f154ce7a21be8b00"}}, "judge:reject:runner-crashed-injection": {"schema_ok": false, "correct": false, "verdict": {"decision": null, "failureClass": null, "obligations": null, "textTraceability": {"problems": false, "contradictions": false, "summary": false}}, "schema_bad": ["<非 JSON 对象>", "生产 parser:invalid_judge_json:Judge 必须只输出一个合法 JSON 对象"], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T173352.225441Z-p68191-n1785000832225669000/response-0005.txt", "size": 766, "sha256": "3c1aca2a220c12fcb6a2f83797f13ab4089575e4d9f13d97a32b9522129f8b7c", "requestBodySha256": "2f3c8e03e8f94d4bfef7b239c3bfce8f74794491754cfb52f5219aac165fd977"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T173352.225441Z-p68191-n1785000832225669000/response-0006.txt", "size": 674, "sha256": "3e58ba7be98979452dbe7329cfc68f491c42f44ac4b648d3daf9052ae212f8c4", "requestBodySha256": "932dfdf43db3c7a78239505677209d304562b29e9d3f5ca3bd794b3151862e52"}}}}
|
||
{"ts": "2026-07-25T19:41:42.060067+00:00", "runId": "20260725T193952.149614Z-p39754-n1785008392149852000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 6, "nCorrect": 6, "successRate": 1.0, "gate1_schema": true, "gate2_success": true, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": true, "consecutiveRuns": 1, "previousRunIds": [], "cohortReady": false, "cohortRuns": 1, "cohortCorrect": 6, "cohortSchemaOk": 6, "perKeyCorrectCounts": {"judge:accept:business-settlement": 1, "judge:inconclusive:business-visual-conflict": 1, "judge:accept:puzzle-victory": 1, "judge:inconclusive:puzzle-conflict": 1, "judge:reject:runner-crashed-injection": 1, "judge:inconclusive:missing-proof-injection": 1}, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}}, "perKeyCorrect": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T193952.149614Z-p39754-n1785008392149852000/run-manifest.json", "sha256": "d567496a1fe5a4733b9ed388e210d45e28879b02316533cea05498d25d906bb1", "runAuditHash": "a399d0fb6ff6624354bcba4d65fe284bb01c5cffe16b3617bbf709c2a44bc500", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.167456, "promptTokens": 20328, "completionTokens": 14034, "totalLatencyMs": 108455, "nError": 0, "gate3_note": "无基线,首次跑(advisory,未拦)", "gate4_note": "无基线,首次跑(advisory,未拦)", "gate5_note": "同请求合格 1 轮;三轮 cohort 正确 6/18", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T193952.149614Z-p39754-n1785008392149852000/response-0001.txt", "size": 854, "sha256": "2207da36877497ad81c576b71e74db16b15dadb6aee4fc7d82e2033df6a06ac7", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T193952.149614Z-p39754-n1785008392149852000/response-0002.txt", "size": 1056, "sha256": "de5c9f06961985ed6b9548decd3a8d43d8b7a847c7cf4199d609d51598510ffe", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T193952.149614Z-p39754-n1785008392149852000/response-0003.txt", "size": 721, "sha256": "acda3a59ee145a3e72f880fda1efd58e60964b226968d1772784bf1f7ebd1f60", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T193952.149614Z-p39754-n1785008392149852000/response-0004.txt", "size": 1143, "sha256": "7523d42b0a73fe82022727bc5199dd5f09335600fa56eea7732c0824667d80f2", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T193952.149614Z-p39754-n1785008392149852000/response-0005.txt", "size": 1162, "sha256": "a35d53e77f2d4e92f9279a0275fb128b2936d138e89c12b8c457a72ebd401653", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T193952.149614Z-p39754-n1785008392149852000/response-0006.txt", "size": 1017, "sha256": "b96f85ea2743b8fb1b38f53bb07e864cdf62a8c2276406006d041b4b7b0fdb54", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T19:44:37.805614+00:00", "runId": "20260725T194158.927296Z-p75634-n1785008518927571000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 6, "nCorrect": 6, "successRate": 1.0, "gate1_schema": true, "gate2_success": true, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": true, "consecutiveRuns": 2, "previousRunIds": ["20260725T193952.149614Z-p39754-n1785008392149852000"], "cohortReady": false, "cohortRuns": 2, "cohortCorrect": 12, "cohortSchemaOk": 12, "perKeyCorrectCounts": {"judge:accept:business-settlement": 2, "judge:inconclusive:business-visual-conflict": 2, "judge:accept:puzzle-victory": 2, "judge:inconclusive:puzzle-conflict": 2, "judge:reject:runner-crashed-injection": 2, "judge:inconclusive:missing-proof-injection": 2}, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}}, "perKeyCorrect": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T194158.927296Z-p75634-n1785008518927571000/run-manifest.json", "sha256": "81abf0e8f9c9bf6be7682ba251677df3671962e31291f91035f89795fc530217", "runAuditHash": "e72ecbd694bce32e12533561403841daa1ae4b1c10ed8d19834c0db57103c410", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.139621, "promptTokens": 20330, "completionTokens": 10856, "totalLatencyMs": 157446, "nError": 0, "gate3_note": "无基线,首次跑(advisory,未拦)", "gate4_note": "无基线,首次跑(advisory,未拦)", "gate5_note": "同请求合格 2 轮;三轮 cohort 正确 12/18", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T194158.927296Z-p75634-n1785008518927571000/response-0001.txt", "size": 741, "sha256": "c9ca18ef94003bee0dec41b808f4fde19e9e8d5392874cf3dbdd036c75610455", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T194158.927296Z-p75634-n1785008518927571000/response-0002.txt", "size": 1612, "sha256": "11f92f549482f323b2fccec99ea982b42db6f7f8866080254498215e11665332", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T194158.927296Z-p75634-n1785008518927571000/response-0003.txt", "size": 636, "sha256": "9af6de6372b28a5af07b93f35af9ff9fddbcd53580cc927b2241619bef963386", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T194158.927296Z-p75634-n1785008518927571000/response-0004.txt", "size": 1120, "sha256": "48c970d961071345964abf17f5d23d3359dc949b736e8b2ee841775207a0f10d", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T194158.927296Z-p75634-n1785008518927571000/response-0005.txt", "size": 1241, "sha256": "9b3c4489eb8884aa3db62d3cd35b6211358ed7d8df643c49aa57fa441dde8521", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T194158.927296Z-p75634-n1785008518927571000/response-0006.txt", "size": 649, "sha256": "3365380c4d0d9f023cabf2c4da7c4664e94c93da0e98241d1ee4c6bf74e65357", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T19:46:30.901021+00:00", "runId": "20260725T194451.683595Z-p12282-n1785008691683851000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 6, "nCorrect": 5, "successRate": 0.8333, "gate1_schema": true, "gate2_success": false, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": false, "consecutiveRuns": 0, "previousRunIds": [], "cohortReady": false, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": false, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}}, "perKeyCorrect": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": false, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": true, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T194451.683595Z-p12282-n1785008691683851000/run-manifest.json", "sha256": "b162310ebfbe73061e648f35008899d5cd415f1306ccaa8242dfc8265040466e", "runAuditHash": "da007db7cd010a6a63067c22df5b878cc7cb7ef77b522cbf678e60ae910d4671", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.15733, "promptTokens": 20328, "completionTokens": 12878, "totalLatencyMs": 97786, "nError": 0, "gate3_note": "无基线,首次跑(advisory,未拦)", "gate4_note": "无基线,首次跑(advisory,未拦)", "gate5_note": "本轮基础闸未全绿,稳定性计数归零", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T194451.683595Z-p12282-n1785008691683851000/response-0001.txt", "size": 719, "sha256": "a328463c31bf73ddba844c239c85ef0a6c429a85881e529592855fee1de8d4cd", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T194451.683595Z-p12282-n1785008691683851000/response-0002.txt", "size": 1254, "sha256": "58a2b5bd48b08552299c916d2fe15742c03248b1f54d5d62d7e2b896a0790a50", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T194451.683595Z-p12282-n1785008691683851000/response-0003.txt", "size": 781, "sha256": "f0e24284b00d19a74c38d662b98487673e13844330c2ba2ab2014c76923c1157", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": false, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": false, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T194451.683595Z-p12282-n1785008691683851000/response-0004.txt", "size": 1237, "sha256": "e01e33a76777641c6c551adbe69a5109f848b9fd0b28f9602f333dc96aa8ba75", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T194451.683595Z-p12282-n1785008691683851000/response-0005.txt", "size": 898, "sha256": "2b22baeca8e14a80f5c2f60f81a6c75434c662cfcddfe6bef637df67b28d57d2", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T194451.683595Z-p12282-n1785008691683851000/response-0006.txt", "size": 724, "sha256": "dd1de84f49fd7c16e48a4fb321f9562a1768347707ffea1c4f8f6feb17ac6f0e", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T19:48:11.331933+00:00", "runId": "20260725T194654.553921Z-p52246-n1785008814554154000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 6, "nCorrect": 6, "successRate": 1.0, "gate1_schema": true, "gate2_success": true, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": true, "consecutiveRuns": 1, "previousRunIds": [], "cohortReady": false, "cohortRuns": 1, "cohortCorrect": 6, "cohortSchemaOk": 6, "perKeyCorrectCounts": {"judge:accept:business-settlement": 1, "judge:inconclusive:business-visual-conflict": 1, "judge:accept:puzzle-victory": 1, "judge:inconclusive:puzzle-conflict": 1, "judge:reject:runner-crashed-injection": 1, "judge:inconclusive:missing-proof-injection": 1}, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}}, "perKeyCorrect": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T194654.553921Z-p52246-n1785008814554154000/run-manifest.json", "sha256": "ff3e3211b675847f3a874439673c87fadcca1ee37eca0523d974c03a8f192bf9", "runAuditHash": "1516198cc8a0451f5003a31ed7916487c703500d70682373e5b7ca9e8434b5b9", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.126122, "promptTokens": 20330, "completionTokens": 9315, "totalLatencyMs": 75257, "nError": 0, "gate3_note": "无基线,首次跑(advisory,未拦)", "gate4_note": "无基线,首次跑(advisory,未拦)", "gate5_note": "同请求合格 1 轮;三轮 cohort 正确 6/18", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T194654.553921Z-p52246-n1785008814554154000/response-0001.txt", "size": 619, "sha256": "889aeee17a388a256cdff2f18f604ac70210e53e1c8e2d1f6d2b78f042a86469", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T194654.553921Z-p52246-n1785008814554154000/response-0002.txt", "size": 1362, "sha256": "b5a86e8746ff6780194598418aa4ef218b5bc12e20016473ea05e837fa69692d", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T194654.553921Z-p52246-n1785008814554154000/response-0003.txt", "size": 659, "sha256": "c9041e82f1163884de6e7d2c5ef65939878ffb47905a24808dba45690dfba657", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T194654.553921Z-p52246-n1785008814554154000/response-0004.txt", "size": 1134, "sha256": "8b773108bf84a21ace556a069684734672fe49b93cc79c7d8097b25c0b048b10", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T194654.553921Z-p52246-n1785008814554154000/response-0005.txt", "size": 1250, "sha256": "1b1df338074e526979967e257473d9c178811fc48283d96b71a1f32802779520", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T194654.553921Z-p52246-n1785008814554154000/response-0006.txt", "size": 949, "sha256": "4e7ce665952c631be991815cac80e70d324bf17e41d759940b0459be8c05a216", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T19:50:23.990436+00:00", "runId": "20260725T194821.464844Z-p80597-n1785008901465145000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 6, "nCorrect": 6, "successRate": 1.0, "gate1_schema": true, "gate2_success": true, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": true, "consecutiveRuns": 2, "previousRunIds": ["20260725T194654.553921Z-p52246-n1785008814554154000"], "cohortReady": false, "cohortRuns": 2, "cohortCorrect": 12, "cohortSchemaOk": 12, "perKeyCorrectCounts": {"judge:accept:business-settlement": 2, "judge:inconclusive:business-visual-conflict": 2, "judge:accept:puzzle-victory": 2, "judge:inconclusive:puzzle-conflict": 2, "judge:reject:runner-crashed-injection": 2, "judge:inconclusive:missing-proof-injection": 2}, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}}, "perKeyCorrect": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T194821.464844Z-p80597-n1785008901465145000/run-manifest.json", "sha256": "af35914a9047073d995224a6d6cb751115f1e41117c5e447b67b1fb5ccd86d7f", "runAuditHash": "e9d0ecf7f7097b0c305b1617538ae8f3470d14e328542229cd2cfdb964fa82bf", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.147133, "promptTokens": 20332, "completionTokens": 11713, "totalLatencyMs": 121009, "nError": 0, "gate3_note": "无基线,首次跑(advisory,未拦)", "gate4_note": "无基线,首次跑(advisory,未拦)", "gate5_note": "同请求合格 2 轮;三轮 cohort 正确 12/18", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T194821.464844Z-p80597-n1785008901465145000/response-0001.txt", "size": 687, "sha256": "bbaa9c50cdac7c05dbf1298b2bb4dfe3697e4621664225b60836cf11baa4fa52", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T194821.464844Z-p80597-n1785008901465145000/response-0002.txt", "size": 1112, "sha256": "edf7d6aedfef5f69ead351116ca06c40cc3f7059172ceccb949dfdb85cfec97b", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T194821.464844Z-p80597-n1785008901465145000/response-0003.txt", "size": 752, "sha256": "9dfb46aed57e45d5b27ba3b7053582890ca8a8e3c8fa7519a927703f09cf5d6e", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T194821.464844Z-p80597-n1785008901465145000/response-0004.txt", "size": 851, "sha256": "5b9b3661ec9c91d24c98fb6ac828c16ae5f7fe0f0a144fda1d44bfda8320a6cb", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T194821.464844Z-p80597-n1785008901465145000/response-0005.txt", "size": 934, "sha256": "53eeb947d23ff905fcd0d971cbf1f2c30e1d846f548029575fb3ec0c4d358cf0", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T194821.464844Z-p80597-n1785008901465145000/response-0006.txt", "size": 542, "sha256": "6e51f2f0fe6d1a52a54815a404c9c73e6f9777815e890ba1aa8d0da4dca6ec50", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T19:53:26.698267+00:00", "runId": "20260725T195037.024292Z-p16445-n1785009037024654000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 6, "nCorrect": 5, "successRate": 0.8333, "gate1_schema": true, "gate2_success": false, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": false, "consecutiveRuns": 0, "previousRunIds": [], "cohortReady": false, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": false}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}}, "perKeyCorrect": {"judge:accept:business-settlement": false, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": true, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T195037.024292Z-p16445-n1785009037024654000/run-manifest.json", "sha256": "254e804f9b265cfce57f2a57b52bd10615cfb4d3ec262028703bdf3c9a33465a", "runAuditHash": "033e2983e58d5d216e7c7631613369c42f6b11ce5ade94e6b975d8f07f8aa05b", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.197218, "promptTokens": 20330, "completionTokens": 17431, "totalLatencyMs": 168178, "nError": 0, "gate3_note": "无基线,首次跑(advisory,未拦)", "gate4_note": "无基线,首次跑(advisory,未拦)", "gate5_note": "本轮基础闸未全绿,稳定性计数归零", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": false, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": false}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T195037.024292Z-p16445-n1785009037024654000/response-0001.txt", "size": 736, "sha256": "907f48addb83aea545f3f871b1ec99a7fb36cfab5882aa475ac582a5981731c9", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T195037.024292Z-p16445-n1785009037024654000/response-0002.txt", "size": 1553, "sha256": "b1f0afa7bff25c69462e62d353583350116d3f41521fa0d34a57f00859fd05a5", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T195037.024292Z-p16445-n1785009037024654000/response-0003.txt", "size": 637, "sha256": "04ce740f1a2780f1b464c2ba8741bf1da27b93d55aadda0eae6a323d2bfe05b3", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T195037.024292Z-p16445-n1785009037024654000/response-0004.txt", "size": 1317, "sha256": "29b5107349f0b74c277d87084f9afe67eb2d1e35bda6cb0da4fbc5f91582134b", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T195037.024292Z-p16445-n1785009037024654000/response-0005.txt", "size": 767, "sha256": "93f2d498786f8107ce987485589aff89d4dfd39ea82b2d6ec40964f0bdf26fd5", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T195037.024292Z-p16445-n1785009037024654000/response-0006.txt", "size": 691, "sha256": "960a5b34226a15317bd6aafa837bed98f3a090d7fc02c0a790f2b1353821767a", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T19:55:18.657394+00:00", "runId": "20260725T195346.878921Z-p53236-n1785009226879224000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 6, "nCorrect": 6, "successRate": 1.0, "gate1_schema": true, "gate2_success": true, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": true, "consecutiveRuns": 1, "previousRunIds": [], "cohortReady": false, "cohortRuns": 1, "cohortCorrect": 6, "cohortSchemaOk": 6, "perKeyCorrectCounts": {"judge:accept:business-settlement": 1, "judge:inconclusive:business-visual-conflict": 1, "judge:accept:puzzle-victory": 1, "judge:inconclusive:puzzle-conflict": 1, "judge:reject:runner-crashed-injection": 1, "judge:inconclusive:missing-proof-injection": 1}, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}}, "perKeyCorrect": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T195346.878921Z-p53236-n1785009226879224000/run-manifest.json", "sha256": "741d12aec287fff9b8ddd08cce9c71cf738938a6e7aae4210fac9ca6e5f01aed", "runAuditHash": "645a6ebb8a075eb0c4d7feaf16d8f4ad4dfb9f0fcf7a8c72351510f6b964eff6", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.13225, "promptTokens": 20328, "completionTokens": 10015, "totalLatencyMs": 90327, "nError": 0, "gate3_note": "无基线,首次跑(advisory,未拦)", "gate4_note": "无基线,首次跑(advisory,未拦)", "gate5_note": "同请求合格 1 轮;三轮 cohort 正确 6/18", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T195346.878921Z-p53236-n1785009226879224000/response-0001.txt", "size": 737, "sha256": "996f274b7d03a0ebb7348debb183e9aa8a23a565c73fa6a1f228bc5e47a0201f", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T195346.878921Z-p53236-n1785009226879224000/response-0002.txt", "size": 1596, "sha256": "1bb4a9d2bb4287bd6d3bd6d42172e3dc44c4644b4e674177ceb994e46aa3c683", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T195346.878921Z-p53236-n1785009226879224000/response-0003.txt", "size": 600, "sha256": "a99028f7a6ad0515c6e052f0d44f9ab7767cce25eb6ba92911fca1bc87bfd06e", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T195346.878921Z-p53236-n1785009226879224000/response-0004.txt", "size": 1181, "sha256": "4cae7ec947675332b6fb5fbaa368f6e885313506ed79df68b9903e40554219bd", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T195346.878921Z-p53236-n1785009226879224000/response-0005.txt", "size": 1336, "sha256": "665adbdc515a0bdb41510f34ac8cba900837b2663eb338aed22c903d11b5f5ba", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T195346.878921Z-p53236-n1785009226879224000/response-0006.txt", "size": 789, "sha256": "0bdedc0459ed92d68709118f6dcb48f09457f0bcacdbf41d79c09d55e17ecf6f", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T19:57:27.650180+00:00", "runId": "20260725T195530.120208Z-p93122-n1785009330120493000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 6, "nCorrect": 5, "successRate": 0.8333, "gate1_schema": true, "gate2_success": false, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": false, "consecutiveRuns": 0, "previousRunIds": [], "cohortReady": false, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": false, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}}, "perKeyCorrect": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": false, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T195530.120208Z-p93122-n1785009330120493000/run-manifest.json", "sha256": "e760676a7924b929f8769b047e45b3c9f8404dee9417fc330f506ccf9a9d5609", "runAuditHash": "734fac1fb32cb265129163b97631d3d0cc9b108f9ad906a85c00cdfde8647381", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.167224, "promptTokens": 20330, "completionTokens": 14007, "totalLatencyMs": 116042, "nError": 0, "gate3_note": "无基线,首次跑(advisory,未拦)", "gate4_note": "无基线,首次跑(advisory,未拦)", "gate5_note": "本轮基础闸未全绿,稳定性计数归零", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T195530.120208Z-p93122-n1785009330120493000/response-0001.txt", "size": 687, "sha256": "8804d993f74f49eed202dfdc1b4e0717076d862f9122507586f38f4cb5a83518", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": false, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": false, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T195530.120208Z-p93122-n1785009330120493000/response-0002.txt", "size": 1162, "sha256": "50658f74f89a6f8a71fc33fed62c3c3592bfb74ea85ad924ef7f9894fc979c99", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T195530.120208Z-p93122-n1785009330120493000/response-0003.txt", "size": 959, "sha256": "02153acd7503355e0050fd9bd4c7bafb7e59b7bf3abdff82a43cd05f9fc8e9c6", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T195530.120208Z-p93122-n1785009330120493000/response-0004.txt", "size": 1063, "sha256": "df8a354ae693c2f91d2bb2f12c94846d31ba14c3e4d209eadbeb2fde20cd4eef", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T195530.120208Z-p93122-n1785009330120493000/response-0005.txt", "size": 914, "sha256": "f6eba3c84f4f10748d467a00e972f81cd55af7e81f2f4decf339f3770bc3beb4", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T195530.120208Z-p93122-n1785009330120493000/response-0006.txt", "size": 703, "sha256": "7ad749c3acd903e6c8e5451c4d753f7b4e6fcd29c32fa4add442a4d11f2a4574", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T19:59:44.452151+00:00", "runId": "20260725T195752.433128Z-p21567-n1785009472433402000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 6, "nCorrect": 5, "successRate": 0.8333, "gate1_schema": true, "gate2_success": false, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": false, "consecutiveRuns": 0, "previousRunIds": [], "cohortReady": false, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": false}}}, "perKeyCorrect": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": false}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T195752.433128Z-p21567-n1785009472433402000/run-manifest.json", "sha256": "22c427dc6190471f0598a0c27ea09a1b972c60a8042133858e9f61d077d377cc", "runAuditHash": "195a583909e96f1b1515016d11c5ff412a243674d01a071154327190a2322c3e", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.15853, "promptTokens": 20328, "completionTokens": 13015, "totalLatencyMs": 110593, "nError": 0, "gate3_note": "无基线,首次跑(advisory,未拦)", "gate4_note": "无基线,首次跑(advisory,未拦)", "gate5_note": "本轮基础闸未全绿,稳定性计数归零", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T195752.433128Z-p21567-n1785009472433402000/response-0001.txt", "size": 835, "sha256": "08bfe398d6b00460c6b7cf29f84fc289b29f74ea2fdf259dd8fad8f0afb7315d", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T195752.433128Z-p21567-n1785009472433402000/response-0002.txt", "size": 1762, "sha256": "7799932ef57c2205337a4949157d6ba9a4e8d84d813a7550ed82043bc12e10df", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T195752.433128Z-p21567-n1785009472433402000/response-0003.txt", "size": 790, "sha256": "e965c83a7af4bd4da12420529a60ebebda6d286a7b008091dbae8b6a28150f38", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T195752.433128Z-p21567-n1785009472433402000/response-0004.txt", "size": 986, "sha256": "01b4efc26bb1c2c472b09be8541b4ee39d6f8998d1fddc5569c008cf5bfc912e", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T195752.433128Z-p21567-n1785009472433402000/response-0005.txt", "size": 996, "sha256": "17006d93953ed142442f13f1f5edc39de6f99e5fbdece3c9f03b435f292e756d", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": false, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": false}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T195752.433128Z-p21567-n1785009472433402000/response-0006.txt", "size": 1099, "sha256": "93d72e76f9fcdffb5a25cbd04a858abd43cf67b984e7bcea133fbe0ceb96c016", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T20:03:22.754225+00:00", "runId": "20260725T200008.295712Z-p57661-n1785009608295972000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 5, "nCorrect": 5, "successRate": 0.8333, "gate1_schema": false, "gate2_success": false, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": false, "consecutiveRuns": 0, "previousRunIds": [], "cohortReady": false, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:business-visual-conflict": {"decision": null, "failureClass": null, "obligations": null, "textTraceability": {"problems": false, "contradictions": false, "summary": false}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}}, "perKeyCorrect": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": false, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": false, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T200008.295712Z-p57661-n1785009608295972000/run-manifest.json", "sha256": "bb81be47a290efacb512457be00e87139c1eeedaf668feed01edc57590762a18", "runAuditHash": "59fabd40e6c9dee7d2d73757cb4586e71cb42695e496a06fe8e8bbefa8a4d2f9", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.160886, "promptTokens": 20332, "completionTokens": 13283, "totalLatencyMs": 193023, "nError": 0, "gate3_note": "无基线,首次跑(advisory,未拦)", "gate4_note": "无基线,首次跑(advisory,未拦)", "gate5_note": "本轮基础闸未全绿,稳定性计数归零", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T200008.295712Z-p57661-n1785009608295972000/response-0001.txt", "size": 644, "sha256": "f08f6b5fb868c295d247ee838af365c158af5ed64ed532e5e666d7c79aeeaaea", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": false, "correct": false, "verdict": {"decision": null, "failureClass": null, "obligations": null, "textTraceability": {"problems": false, "contradictions": false, "summary": false}}, "schema_bad": ["<非 JSON 对象>", "生产 parser:invalid_judge_json:Judge 必须只输出一个合法 JSON 对象"], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T200008.295712Z-p57661-n1785009608295972000/response-0002.txt", "size": 1010, "sha256": "6e0f163457559f23c148c90328cf53be0beaba36ccd51a95188645b020fd0486", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T200008.295712Z-p57661-n1785009608295972000/response-0003.txt", "size": 533, "sha256": "906880bdf552b35e6171fdfc003f1fbbf5d4629fcd345133c792cdfac96008a9", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T200008.295712Z-p57661-n1785009608295972000/response-0004.txt", "size": 991, "sha256": "97012337cce5315df52fbd3d3bbde71ab083cd1ebd201402024087b66cd40891", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T200008.295712Z-p57661-n1785009608295972000/response-0005.txt", "size": 786, "sha256": "155dcf6de903177250a5697b452e9269dcc9b763215a18aee4c7b8912d376e77", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T200008.295712Z-p57661-n1785009608295972000/response-0006.txt", "size": 549, "sha256": "ee158e6022d993e2758753a1e67fca32a7c3cd3a76c1e27f80f32a1fdacb7d11", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T20:05:55.925844+00:00", "runId": "20260725T200339.251701Z-p95328-n1785009819251960000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 6, "nCorrect": 6, "successRate": 1.0, "gate1_schema": true, "gate2_success": true, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": true, "consecutiveRuns": 1, "previousRunIds": [], "cohortReady": false, "cohortRuns": 1, "cohortCorrect": 6, "cohortSchemaOk": 6, "perKeyCorrectCounts": {"judge:accept:business-settlement": 1, "judge:inconclusive:business-visual-conflict": 1, "judge:accept:puzzle-victory": 1, "judge:inconclusive:puzzle-conflict": 1, "judge:reject:runner-crashed-injection": 1, "judge:inconclusive:missing-proof-injection": 1}, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}}, "perKeyCorrect": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T200339.251701Z-p95328-n1785009819251960000/run-manifest.json", "sha256": "65ca02512231bf6d92e7f7e812bdcdaed51bae4cc39acbdb742802cced9b800d", "runAuditHash": "166e47c6d691b10c1d2f55c6d552800596edc7d6294ade9dc157714f178a00b5", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.185984, "promptTokens": 20328, "completionTokens": 16149, "totalLatencyMs": 135201, "nError": 0, "gate3_note": "无基线,首次跑(advisory,未拦)", "gate4_note": "无基线,首次跑(advisory,未拦)", "gate5_note": "同请求合格 1 轮;三轮 cohort 正确 6/18", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T200339.251701Z-p95328-n1785009819251960000/response-0001.txt", "size": 704, "sha256": "2e438e4b2a18e61d15bc187ad492df9e11ade0cb8f7764926bd46f9b5eb1b1a0", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T200339.251701Z-p95328-n1785009819251960000/response-0002.txt", "size": 1075, "sha256": "2be13fcd65ad4d4a82d6ea14eeb0ea31797ecf237f4d691a815c530f06d80cd2", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T200339.251701Z-p95328-n1785009819251960000/response-0003.txt", "size": 624, "sha256": "25dd81a8946a71918774114a511e9e6819b238f1045a1d0a26fc5c9259eefb6f", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T200339.251701Z-p95328-n1785009819251960000/response-0004.txt", "size": 816, "sha256": "93436514742d35ef71513778e1a9465a9d923c3c793f92b662fabfd7a7bad801", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T200339.251701Z-p95328-n1785009819251960000/response-0005.txt", "size": 817, "sha256": "6e8accb95459afb01927fd005b756d7a3d8c21d3985cd29e34ebb51bebbf7fed", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T200339.251701Z-p95328-n1785009819251960000/response-0006.txt", "size": 569, "sha256": "b09e647947493782b111b23c994eca464d6f52cba2fb046bedbea3a78ba39c09", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T20:09:34.481090+00:00", "runId": "20260725T200607.669280Z-p35670-n1785009967669544000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 6, "nCorrect": 6, "successRate": 1.0, "gate1_schema": true, "gate2_success": true, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": true, "consecutiveRuns": 2, "previousRunIds": ["20260725T200339.251701Z-p95328-n1785009819251960000"], "cohortReady": false, "cohortRuns": 2, "cohortCorrect": 12, "cohortSchemaOk": 12, "perKeyCorrectCounts": {"judge:accept:business-settlement": 2, "judge:inconclusive:business-visual-conflict": 2, "judge:accept:puzzle-victory": 2, "judge:inconclusive:puzzle-conflict": 2, "judge:reject:runner-crashed-injection": 2, "judge:inconclusive:missing-proof-injection": 2}, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}}, "perKeyCorrect": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T200607.669280Z-p35670-n1785009967669544000/run-manifest.json", "sha256": "5a65b8da716239e9b254b875620bd983063cd18805296d0b9740de5d638e02bf", "runAuditHash": "6d863ffeb5f7260fcb9ce7994b72d48075fef108fcb9d78feae737a37869b899", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.202303, "promptTokens": 20328, "completionTokens": 18012, "totalLatencyMs": 205388, "nError": 0, "gate3_note": "无基线,首次跑(advisory,未拦)", "gate4_note": "无基线,首次跑(advisory,未拦)", "gate5_note": "同请求合格 2 轮;三轮 cohort 正确 12/18", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T200607.669280Z-p35670-n1785009967669544000/response-0001.txt", "size": 695, "sha256": "70b3a3d1b9ab1c547807899a398d77f0979e5fdd9b143013dc32715885a55f8e", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T200607.669280Z-p35670-n1785009967669544000/response-0002.txt", "size": 1468, "sha256": "5a9d74ea778da35d36fc36783dc24d50ac1813533031497f5221a89e641e2107", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T200607.669280Z-p35670-n1785009967669544000/response-0003.txt", "size": 686, "sha256": "74067379a5a2da09ddbbe219b39f8d6b059164409630d5ebf95dab3c79487842", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T200607.669280Z-p35670-n1785009967669544000/response-0004.txt", "size": 1489, "sha256": "82b3128784298ce72ddc63211869828ef34d187b039924f8c17cf77d81cb1751", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T200607.669280Z-p35670-n1785009967669544000/response-0005.txt", "size": 1383, "sha256": "5d9d62e68eb4b5d5d4ad2156f9a130c1feec3f0290247631d24ce138761735f6", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T200607.669280Z-p35670-n1785009967669544000/response-0006.txt", "size": 617, "sha256": "0011e9013be010ee7fd51ffc71ca388bc50ac2914aba6b23cda3861ecfa00355", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T20:11:23.338454+00:00", "runId": "20260725T200950.400777Z-p72842-n1785010190401080000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 6, "nCorrect": 5, "successRate": 0.8333, "gate1_schema": true, "gate2_success": false, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": false, "consecutiveRuns": 0, "previousRunIds": [], "cohortReady": false, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": false, "summary": false}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}}, "perKeyCorrect": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": false, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": true, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T200950.400777Z-p72842-n1785010190401080000/run-manifest.json", "sha256": "7155364ba5383f839bcd20c7728c2b22e7e1f60a268f895a204a757bd1bb286c", "runAuditHash": "5f99f0d807c75f937b3205cdd7baddb7672513a83a3e516e5a5ad17ff8d160b4", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.133507, "promptTokens": 20330, "completionTokens": 10158, "totalLatencyMs": 91487, "nError": 0, "gate3_note": "无基线,首次跑(advisory,未拦)", "gate4_note": "无基线,首次跑(advisory,未拦)", "gate5_note": "本轮基础闸未全绿,稳定性计数归零", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T200950.400777Z-p72842-n1785010190401080000/response-0001.txt", "size": 741, "sha256": "1f3520c53f5a2c35ea6954ee434a7ff46b2a1685dd0b3fc620162ae874ddd256", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T200950.400777Z-p72842-n1785010190401080000/response-0002.txt", "size": 882, "sha256": "294e4d47c003b268a41dc664070035b29b3ea9fbd06b9ef7129977ffc0806ac9", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T200950.400777Z-p72842-n1785010190401080000/response-0003.txt", "size": 732, "sha256": "1b60d728e42890d624a3fc0d5b428fd44947820201262b5a135300925d6d1f80", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": false, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": false, "summary": false}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T200950.400777Z-p72842-n1785010190401080000/response-0004.txt", "size": 550, "sha256": "da5bb434ab0595fbb582ff453121978f02b8f7665557f5f42449f16b24e8cba7", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T200950.400777Z-p72842-n1785010190401080000/response-0005.txt", "size": 830, "sha256": "823b13d169ef6ba34b1391122be37f6b3feced372fb4154f177106b60fd26db8", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T200950.400777Z-p72842-n1785010190401080000/response-0006.txt", "size": 877, "sha256": "627c3b9b46520b0c0abf83e23154fc5890a7e1214b4c68b055e3746aa94a80df", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T20:14:55.950050+00:00", "runId": "20260725T201156.204804Z-p9487-n1785010316205092000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 5, "nCorrect": 5, "successRate": 0.8333, "gate1_schema": false, "gate2_success": false, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": false, "consecutiveRuns": 0, "previousRunIds": [], "cohortReady": false, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": null, "failureClass": null, "obligations": null, "textTraceability": {"problems": false, "contradictions": false, "summary": false}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}}, "perKeyCorrect": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": false, "judge:inconclusive:missing-proof-injection": true}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": false, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T201156.204804Z-p9487-n1785010316205092000/run-manifest.json", "sha256": "51877e81e2d44a0b9ef2f793bcfaa31b24531bc9ff2454fb3fd636a5420b6314", "runAuditHash": "52d93648ae0e537f400405a4a7bc40f39d5033a9d8a7186caf17c9df9888cb6f", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.152091, "promptTokens": 20332, "completionTokens": 12279, "totalLatencyMs": 178268, "nError": 0, "gate3_note": "无基线,首次跑(advisory,未拦)", "gate4_note": "无基线,首次跑(advisory,未拦)", "gate5_note": "本轮基础闸未全绿,稳定性计数归零", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T201156.204804Z-p9487-n1785010316205092000/response-0001.txt", "size": 745, "sha256": "3904788be839ff50e4c35a7ac033c325d8c72ad58d67d6e19977bbc7a3218a13", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T201156.204804Z-p9487-n1785010316205092000/response-0002.txt", "size": 1109, "sha256": "37bd31fb603d762d4dcd2b9a3ff75b094e828a9334fc977dce6203c732253def", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T201156.204804Z-p9487-n1785010316205092000/response-0003.txt", "size": 631, "sha256": "979df83d0ea39c792f366136065521b804b130694e636778da25c07d07e756c9", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T201156.204804Z-p9487-n1785010316205092000/response-0004.txt", "size": 1207, "sha256": "d5f77cdf0678eb0788e4c425a5b20c12471f15bd6d149eb8cdca22ce3c752b7b", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": false, "correct": false, "verdict": {"decision": null, "failureClass": null, "obligations": null, "textTraceability": {"problems": false, "contradictions": false, "summary": false}}, "schema_bad": ["<非 JSON 对象>", "生产 parser:invalid_judge_json:Judge 必须只输出一个合法 JSON 对象"], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T201156.204804Z-p9487-n1785010316205092000/response-0005.txt", "size": 1272, "sha256": "d7ebee3a58fc3303aa358cc0c970becbf0ff91aa193db5fcbed273d270ae5772", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T201156.204804Z-p9487-n1785010316205092000/response-0006.txt", "size": 531, "sha256": "4a656b1cb22ec8ba56c31c7737a0dd8d443dadd50f6b3f93e9293fc4e13e4e9d", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T20:17:10.061794+00:00", "runId": "20260725T201519.188841Z-p50573-n1785010519189116000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 6, "nCorrect": 5, "successRate": 0.8333, "gate1_schema": true, "gate2_success": false, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": false, "consecutiveRuns": 0, "previousRunIds": [], "cohortReady": false, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": false, "summary": false}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}}, "perKeyCorrect": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": false, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T201519.188841Z-p50573-n1785010519189116000/run-manifest.json", "sha256": "c92cf8e5ee83a23fc4939496a6aba69d84cb48603ee7b8b33ed700c7341ff9fc", "runAuditHash": "854f75d20df680ad52abf01a4488f1dd26622d27b3a24cce6aaf6544bf934a03", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.157947, "promptTokens": 20330, "completionTokens": 12948, "totalLatencyMs": 109399, "nError": 0, "gate3_note": "无基线,首次跑(advisory,未拦)", "gate4_note": "无基线,首次跑(advisory,未拦)", "gate5_note": "本轮基础闸未全绿,稳定性计数归零", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T201519.188841Z-p50573-n1785010519189116000/response-0001.txt", "size": 720, "sha256": "f85c7db0b015f6556e9137ea44e98490cf598f382511d4f898f4f41aaac4880c", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T201519.188841Z-p50573-n1785010519189116000/response-0002.txt", "size": 1182, "sha256": "c5234d425f6edd4ccccd7b1310ab7ddbff30d6d141b3f95d67f4df9a04af2ea5", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T201519.188841Z-p50573-n1785010519189116000/response-0003.txt", "size": 673, "sha256": "ad1d6956cbf1cb862df90eba612888c25325c2d7548e942628bfa4284e117d16", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": false, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": false, "summary": false}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T201519.188841Z-p50573-n1785010519189116000/response-0004.txt", "size": 743, "sha256": "e4493caf997046a70d04d85cdbf30bab7b984c54270f07ae811af770f56188f8", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T201519.188841Z-p50573-n1785010519189116000/response-0005.txt", "size": 1262, "sha256": "6c025dc557648335865cac2554ff016aefee185c454281e438e34e9779a26f37", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T201519.188841Z-p50573-n1785010519189116000/response-0006.txt", "size": 673, "sha256": "82a0b7c925a9d4e10062bbbb1bd5e462b2670247d250494baa59c8944556d05c", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T20:18:47.301604+00:00", "runId": "20260725T201729.580804Z-p86454-n1785010649581076000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 6, "nCorrect": 6, "successRate": 1.0, "gate1_schema": true, "gate2_success": true, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": true, "consecutiveRuns": 1, "previousRunIds": [], "cohortReady": false, "cohortRuns": 1, "cohortCorrect": 6, "cohortSchemaOk": 6, "perKeyCorrectCounts": {"judge:accept:business-settlement": 1, "judge:inconclusive:business-visual-conflict": 1, "judge:accept:puzzle-victory": 1, "judge:inconclusive:puzzle-conflict": 1, "judge:reject:runner-crashed-injection": 1, "judge:inconclusive:missing-proof-injection": 1}, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}}, "perKeyCorrect": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T201729.580804Z-p86454-n1785010649581076000/run-manifest.json", "sha256": "b8f9382e8cca4d76a470e6379f4f627551f3918b7e2cf3a1761cd6816e80285f", "runAuditHash": "8d069bd4d155f5ecee6c2d448679ed6260aacae768a8934cdad1371d9d8ba35a", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.136818, "promptTokens": 20330, "completionTokens": 10536, "totalLatencyMs": 76268, "nError": 0, "gate3_note": "无基线,首次跑(advisory,未拦)", "gate4_note": "无基线,首次跑(advisory,未拦)", "gate5_note": "同请求合格 1 轮;三轮 cohort 正确 6/18", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T201729.580804Z-p86454-n1785010649581076000/response-0001.txt", "size": 649, "sha256": "1dee0744968133d7d4c45da30f6dfb2353ab49cea2bc2557d1aad51e4a8a5a7d", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T201729.580804Z-p86454-n1785010649581076000/response-0002.txt", "size": 1176, "sha256": "8d266cbb52ef40ada12a4596da8890976ba5c2ac9ddd3eae40ede1dfe88b9c77", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T201729.580804Z-p86454-n1785010649581076000/response-0003.txt", "size": 625, "sha256": "74f88926dc2069d00ff92900199a66c96be57d5f5655d26b51571546c9117008", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T201729.580804Z-p86454-n1785010649581076000/response-0004.txt", "size": 823, "sha256": "afe619bb2f2d40d0196d64220dee98b0d03a0c30ec17100dd789f7f1f592cc07", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T201729.580804Z-p86454-n1785010649581076000/response-0005.txt", "size": 918, "sha256": "a787106e8ea574542d8c98ebd80bb02dae925cd165829e257a1900811ee4aef0", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T201729.580804Z-p86454-n1785010649581076000/response-0006.txt", "size": 873, "sha256": "2c01d7f93ec094ead3dedde234aad261321acecf47f35d7c75fe84164997d7c2", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T20:20:22.388368+00:00", "runId": "20260725T201858.564229Z-p18241-n1785010738564451000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 5, "nCorrect": 4, "successRate": 0.6667, "gate1_schema": false, "gate2_success": false, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": false, "consecutiveRuns": 0, "previousRunIds": [], "cohortReady": false, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:business-visual-conflict": {"decision": null, "failureClass": null, "obligations": null, "textTraceability": {"problems": false, "contradictions": false, "summary": false}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": false}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}}, "perKeyCorrect": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": false, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": false, "judge:inconclusive:missing-proof-injection": true}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": false, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T201858.564229Z-p18241-n1785010738564451000/run-manifest.json", "sha256": "e69a8aed4fecb822a862a2c4aff4be8fd1acd85b47840fd31d32020f466e3a0b", "runAuditHash": "c021e1d80f05a75957ee73f8fcb7f6d94bc9897192f20aaafa1ff997d90068ce", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.149595, "promptTokens": 20332, "completionTokens": 11994, "totalLatencyMs": 82268, "nError": 0, "gate3_note": "无基线,首次跑(advisory,未拦)", "gate4_note": "无基线,首次跑(advisory,未拦)", "gate5_note": "本轮基础闸未全绿,稳定性计数归零", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T201858.564229Z-p18241-n1785010738564451000/response-0001.txt", "size": 699, "sha256": "3d13f8f47dfae615dd3d7da737011c5f1218bcdb947cacca0694c4fdcfe55a61", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": false, "correct": false, "verdict": {"decision": null, "failureClass": null, "obligations": null, "textTraceability": {"problems": false, "contradictions": false, "summary": false}}, "schema_bad": ["<非 JSON 对象>", "生产 parser:invalid_judge_shape:Judge 输出字段不符合白名单"], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T201858.564229Z-p18241-n1785010738564451000/response-0002.txt", "size": 626, "sha256": "7df710268dd6bf041f03ea8d0d8c7842564a6ebe38b4319f9e1608d6cb7f8ff4", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T201858.564229Z-p18241-n1785010738564451000/response-0003.txt", "size": 665, "sha256": "59fb49059557876fd31e6bb2263b88e844f19c81be46cf5afd3275bdbaf25b3f", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T201858.564229Z-p18241-n1785010738564451000/response-0004.txt", "size": 917, "sha256": "c48cd686b7cf22fdb95dbfcf2e6414a5987808860899ff580673c23d63242e96", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": false, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": false}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T201858.564229Z-p18241-n1785010738564451000/response-0005.txt", "size": 1154, "sha256": "65865d638ed4b0da87085711d05120527e6215f5683496d1657badb1a32a388d", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T201858.564229Z-p18241-n1785010738564451000/response-0006.txt", "size": 920, "sha256": "ec7cc909c3af48cd8947983eda43230513120786396e790a8eee79d71844a3ad", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T20:23:02.217966+00:00", "runId": "20260725T202047.512179Z-p47267-n1785010847512462000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 6, "nCorrect": 6, "successRate": 1.0, "gate1_schema": true, "gate2_success": true, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": true, "consecutiveRuns": 1, "previousRunIds": [], "cohortReady": false, "cohortRuns": 1, "cohortCorrect": 6, "cohortSchemaOk": 6, "perKeyCorrectCounts": {"judge:accept:business-settlement": 1, "judge:inconclusive:business-visual-conflict": 1, "judge:accept:puzzle-victory": 1, "judge:inconclusive:puzzle-conflict": 1, "judge:reject:runner-crashed-injection": 1, "judge:inconclusive:missing-proof-injection": 1}, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}}, "perKeyCorrect": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T202047.512179Z-p47267-n1785010847512462000/run-manifest.json", "sha256": "6f0b7c2707b17e34178d2ad51b9845a97657f64cf0feb78e338077d2007f0722", "runAuditHash": "494a64a7624da532ca22cdad259d5cd6fbdd0fe59793bb56d47b8a3035308cdd", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.148193, "promptTokens": 20332, "completionTokens": 11834, "totalLatencyMs": 133265, "nError": 0, "gate3_note": "无基线,首次跑(advisory,未拦)", "gate4_note": "无基线,首次跑(advisory,未拦)", "gate5_note": "同请求合格 1 轮;三轮 cohort 正确 6/18", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T202047.512179Z-p47267-n1785010847512462000/response-0001.txt", "size": 647, "sha256": "39c4b420a12be7a7bf45c2e79d56756ba192d753a76fa5fe228e47fc60873635", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T202047.512179Z-p47267-n1785010847512462000/response-0002.txt", "size": 980, "sha256": "2d15a9a47bbf0815ebcc6c1c77ab27c0a5f1d70787803ebd22478e2073d0a6fb", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T202047.512179Z-p47267-n1785010847512462000/response-0003.txt", "size": 882, "sha256": "59b3d270f29afdc5b48e4379bb9c0fab462a16cacb0bc0a771ff427a4f929851", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T202047.512179Z-p47267-n1785010847512462000/response-0004.txt", "size": 1072, "sha256": "71579ea9ba2cdd93cc7d163e981de5327bc5cecfd02b1544cc750b8414921e66", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T202047.512179Z-p47267-n1785010847512462000/response-0005.txt", "size": 889, "sha256": "72de0ed059aede1067e4a0cb4d778588c23b54534d98a879f13f0b9128829f1b", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T202047.512179Z-p47267-n1785010847512462000/response-0006.txt", "size": 660, "sha256": "c017ae981954d26d0d72dab23f2191b38109a50cd76b34a34b1130fe927aff8b", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T20:24:57.450721+00:00", "runId": "20260725T202312.634099Z-p83469-n1785010992634412000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 6, "nCorrect": 5, "successRate": 0.8333, "gate1_schema": true, "gate2_success": false, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": false, "consecutiveRuns": 0, "previousRunIds": [], "cohortReady": false, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": false}}}, "perKeyCorrect": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": false}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T202312.634099Z-p83469-n1785010992634412000/run-manifest.json", "sha256": "b75221941fecad973be919d310a294aa903acce5690cbb7648c487ef00e2f067", "runAuditHash": "f449d8ab640bfccec47187758a434dc6953bc3510ba4a9f144e1d8d067cfc3dc", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.148543, "promptTokens": 20328, "completionTokens": 11875, "totalLatencyMs": 103356, "nError": 0, "gate3_note": "无基线,首次跑(advisory,未拦)", "gate4_note": "无基线,首次跑(advisory,未拦)", "gate5_note": "本轮基础闸未全绿,稳定性计数归零", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T202312.634099Z-p83469-n1785010992634412000/response-0001.txt", "size": 756, "sha256": "e8d6e5a7b20fc49e1eb086dc2f979187e6a7a31e2f7017c8857c9894c3995f89", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T202312.634099Z-p83469-n1785010992634412000/response-0002.txt", "size": 1158, "sha256": "f13f5782c621b8949dd8871993345ae568a6147f90db811180d79c79cf0415fb", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T202312.634099Z-p83469-n1785010992634412000/response-0003.txt", "size": 691, "sha256": "3d805da492fab325d6b064bb36af8f44790396fdd9d61d7ffd8d354aa23f4047", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T202312.634099Z-p83469-n1785010992634412000/response-0004.txt", "size": 1047, "sha256": "cd00e359ec644837da6433be4e45ec1921bf50d954c2b71a28d8fa1d4e8c4d9f", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T202312.634099Z-p83469-n1785010992634412000/response-0005.txt", "size": 1604, "sha256": "f390be9bd92c39695e53d466724cd468de2ff3bf9256a8090405f57176e63e57", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": false, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": false}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T202312.634099Z-p83469-n1785010992634412000/response-0006.txt", "size": 612, "sha256": "0705a122121f782d51bb7013466af84fa635f1c56aacbc2dfe11043df8bbc51f", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T20:26:38.974925+00:00", "runId": "20260725T202514.213487Z-p19640-n1785011114213808000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 6, "nCorrect": 5, "successRate": 0.8333, "gate1_schema": true, "gate2_success": false, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": false, "consecutiveRuns": 0, "previousRunIds": [], "cohortReady": false, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": false}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}}, "perKeyCorrect": {"judge:accept:business-settlement": false, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T202514.213487Z-p19640-n1785011114213808000/run-manifest.json", "sha256": "d2a05cdc2f0b57ddd99fd0a80b0c82cd7a90980eacec7aa54b674e8e2a9c2cf0", "runAuditHash": "c3abf32e4684c1cf73152d01b3e11b787acedcd85c91d60e5d0e633642df5637", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.145626, "promptTokens": 20328, "completionTokens": 11542, "totalLatencyMs": 83287, "nError": 0, "gate3_note": "无基线,首次跑(advisory,未拦)", "gate4_note": "无基线,首次跑(advisory,未拦)", "gate5_note": "本轮基础闸未全绿,稳定性计数归零", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": false, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": false}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T202514.213487Z-p19640-n1785011114213808000/response-0001.txt", "size": 656, "sha256": "364f7bf44f1245b1866331a62182538edc24725ee992acf2a5548ec20c55837e", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T202514.213487Z-p19640-n1785011114213808000/response-0002.txt", "size": 1215, "sha256": "219b76012c8508d643a9c6644d561582cf9ce60ad3f43adb929f7594f650d970", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T202514.213487Z-p19640-n1785011114213808000/response-0003.txt", "size": 592, "sha256": "f0d5186902509d53f0d5e7c6f56aee56ae138040270ce781c2b1c67f4409098b", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T202514.213487Z-p19640-n1785011114213808000/response-0004.txt", "size": 863, "sha256": "dbf209127f381ac4f98c2f2c79537513dfaf45bbf5d55a45be1f11301b122c79", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T202514.213487Z-p19640-n1785011114213808000/response-0005.txt", "size": 916, "sha256": "eba4c3bc6fcf2b4c2d10851fb465149d356d1c1d1aa71e13c0e648ea5a43455f", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T202514.213487Z-p19640-n1785011114213808000/response-0006.txt", "size": 545, "sha256": "d4a0425712437064b3b1203ca21c65179d3ea935479efa9979802d2b73600a1c", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T20:29:15.139433+00:00", "runId": "20260725T202713.274467Z-p47731-n1785011233274752000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 6, "nCorrect": 4, "successRate": 0.6667, "gate1_schema": true, "gate2_success": false, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": false, "consecutiveRuns": 0, "previousRunIds": [], "cohortReady": false, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": false, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": false}}}, "perKeyCorrect": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": false, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": false}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T202713.274467Z-p47731-n1785011233274752000/run-manifest.json", "sha256": "5e33b38b50fb946fb38007e2aa5220ddf6a39ead7def7b8d91901b7eaeb0de8a", "runAuditHash": "7d0bb3e00dfd5d36c04966d35cd50ea3b069c27cdde56833fe214d3ae86ea68f", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.17319, "promptTokens": 20330, "completionTokens": 14688, "totalLatencyMs": 120407, "nError": 0, "gate3_note": "无基线,首次跑(advisory,未拦)", "gate4_note": "无基线,首次跑(advisory,未拦)", "gate5_note": "本轮基础闸未全绿,稳定性计数归零", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T202713.274467Z-p47731-n1785011233274752000/response-0001.txt", "size": 682, "sha256": "e56ae0508bd96816f14cddc3dea6135709072457031b1e6a99f9688b3328e12e", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": false, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": false, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T202713.274467Z-p47731-n1785011233274752000/response-0002.txt", "size": 1156, "sha256": "59001b8b3be05c9eb52ca9c3c1e15e9a985099a8f6f0d7fb1edb402e49a98f7e", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T202713.274467Z-p47731-n1785011233274752000/response-0003.txt", "size": 681, "sha256": "f6a8dd14415ebed9aa567dbfae14c71dfea66ce66aff7e4ee837e40b3105e998", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T202713.274467Z-p47731-n1785011233274752000/response-0004.txt", "size": 1167, "sha256": "60d797be4edb7a93ad2ce2d1ba23469a77453f7f47a277b2a9fb9c11f6c20884", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T202713.274467Z-p47731-n1785011233274752000/response-0005.txt", "size": 1103, "sha256": "fe69caf8190a2328b8b5fbbebc63b6fc7b3d7eb1c68ee61e7ae972b79c3c3846", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": false, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": false}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T202713.274467Z-p47731-n1785011233274752000/response-0006.txt", "size": 843, "sha256": "fe350e6707e6dc47b9f5c5b154a7e6fed28e97d9e8144be6b9b0aa9da6b729d6", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T20:31:21.741674+00:00", "runId": "20260725T203002.250103Z-p87817-n1785011402250337000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 5, "nCorrect": 4, "successRate": 0.6667, "gate1_schema": false, "gate2_success": false, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": false, "consecutiveRuns": 0, "previousRunIds": [], "cohortReady": false, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": false, "summary": false}}, "judge:reject:runner-crashed-injection": {"decision": null, "failureClass": null, "obligations": null, "textTraceability": {"problems": false, "contradictions": false, "summary": false}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}}, "perKeyCorrect": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": false, "judge:reject:runner-crashed-injection": false, "judge:inconclusive:missing-proof-injection": true}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": false, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T203002.250103Z-p87817-n1785011402250337000/run-manifest.json", "sha256": "886c5c09b414ac56492081306e119d3d04e2ec91afd0fedd99f305acc0cf306b", "runAuditHash": "9b4fff89653b83ec97bcb8a59ff4e50b0991f86dd0eeb3ea1e0285d480a9ddf8", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.132061, "promptTokens": 20330, "completionTokens": 9993, "totalLatencyMs": 78040, "nError": 0, "gate3_note": "无基线,首次跑(advisory,未拦)", "gate4_note": "无基线,首次跑(advisory,未拦)", "gate5_note": "本轮基础闸未全绿,稳定性计数归零", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T203002.250103Z-p87817-n1785011402250337000/response-0001.txt", "size": 617, "sha256": "e1c9561cf448e66bb2868675fe46733622163e51374ddfac4ffdbb422e96f03f", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T203002.250103Z-p87817-n1785011402250337000/response-0002.txt", "size": 1106, "sha256": "2f95a240000ee6b96f99df00efd47381db7ab84d4f6bbb95d0d4a14675f5c397", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T203002.250103Z-p87817-n1785011402250337000/response-0003.txt", "size": 675, "sha256": "c3c5d4cabdba69170f3a3692d254a861c6082fabc79f52194a41a1ddc2ef8ec3", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": false, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": false, "summary": false}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T203002.250103Z-p87817-n1785011402250337000/response-0004.txt", "size": 628, "sha256": "94e94eef61bebdc6f2462abcdd031303098541ae26fe799911338f43c5704827", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": false, "correct": false, "verdict": {"decision": null, "failureClass": null, "obligations": null, "textTraceability": {"problems": false, "contradictions": false, "summary": false}}, "schema_bad": ["<非 JSON 对象>", "生产 parser:invalid_judge_json:Judge 必须只输出一个合法 JSON 对象"], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T203002.250103Z-p87817-n1785011402250337000/response-0005.txt", "size": 1022, "sha256": "a0fa5cfaf89de12b504d921d0918adbdb754506406eaccdfe43a59302082d478", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T203002.250103Z-p87817-n1785011402250337000/response-0006.txt", "size": 710, "sha256": "f3882207438c6cbd12cf83132647dd04b7d3bb3b0944de546c1d131b9edac2c8", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T20:33:45.470434+00:00", "runId": "20260725T203149.109794Z-p28295-n1785011509110081000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 6, "nCorrect": 4, "successRate": 0.6667, "gate1_schema": true, "gate2_success": false, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": false, "consecutiveRuns": 0, "previousRunIds": [], "cohortReady": false, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": false, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": false, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}}, "perKeyCorrect": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": false, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": false, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T203149.109794Z-p28295-n1785011509110081000/run-manifest.json", "sha256": "33172f6a50a3abc6cf2e6563515edd66c21dc9f59122fd60f5faec0ce7d59364", "runAuditHash": "5b12761547c0013340a8cbeb520ccc8cbd360d4dabdebb5027c94618b666c366", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.156278, "promptTokens": 20332, "completionTokens": 12757, "totalLatencyMs": 114898, "nError": 0, "gate3_note": "无基线,首次跑(advisory,未拦)", "gate4_note": "无基线,首次跑(advisory,未拦)", "gate5_note": "本轮基础闸未全绿,稳定性计数归零", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T203149.109794Z-p28295-n1785011509110081000/response-0001.txt", "size": 656, "sha256": "400fbc6d9ceedf48c27cf873cdbded8dbff16ce5d0f05c518f9a1e44ef024120", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": false, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": false, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T203149.109794Z-p28295-n1785011509110081000/response-0002.txt", "size": 1054, "sha256": "7ee00a69e8b7d326da524e298a3fd5ecd10f96087ed167b93f3461a068cf55d7", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T203149.109794Z-p28295-n1785011509110081000/response-0003.txt", "size": 604, "sha256": "24559a81065ad2fd61267e6770a8dc947bd9f4bb996980a177db3deea5daaacb", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": false, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": false, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T203149.109794Z-p28295-n1785011509110081000/response-0004.txt", "size": 1216, "sha256": "4fcc22ec0c9441fa8e607c6f181d2ba2b7dce6dbbfc22474bdaffe039d16f065", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T203149.109794Z-p28295-n1785011509110081000/response-0005.txt", "size": 1215, "sha256": "f1d188712ac7b2879ef7a70f81cc489f8c8aeca8360e424e0566eb5f0a4b2f3d", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T203149.109794Z-p28295-n1785011509110081000/response-0006.txt", "size": 795, "sha256": "d0b08c065d8c753f6f3efa519e85be335cfe5ae6872b0db92d9023e37da19337", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T20:36:04.158258+00:00", "runId": "20260725T203416.374309Z-p68431-n1785011656374597000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 6, "nCorrect": 5, "successRate": 0.8333, "gate1_schema": true, "gate2_success": false, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": false, "consecutiveRuns": 0, "previousRunIds": [], "cohortReady": false, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": false}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}}, "perKeyCorrect": {"judge:accept:business-settlement": false, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T203416.374309Z-p68431-n1785011656374597000/run-manifest.json", "sha256": "33eaf70796951feac049c91a1e3dae1ba6cbe839c13e1b15cd3d9b2b120860b6", "runAuditHash": "2ffbb83ada714ef1b7783068f4f24d9a2cf8c008f0b14ab004cc41b0272d1aef", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.150576, "promptTokens": 20332, "completionTokens": 12106, "totalLatencyMs": 106335, "nError": 0, "gate3_note": "无基线,首次跑(advisory,未拦)", "gate4_note": "无基线,首次跑(advisory,未拦)", "gate5_note": "本轮基础闸未全绿,稳定性计数归零", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": false, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": false}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T203416.374309Z-p68431-n1785011656374597000/response-0001.txt", "size": 599, "sha256": "59764eb189c2632c513badadc0e37e2a148435bace356657742d19a3791d6f31", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T203416.374309Z-p68431-n1785011656374597000/response-0002.txt", "size": 1144, "sha256": "b5eea81c28a3891abd6f31de8fca37cf9236e6f052234a9000c3c9ff7c983dd4", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T203416.374309Z-p68431-n1785011656374597000/response-0003.txt", "size": 616, "sha256": "e59eacd2317d8a00a8ce424619b74c09e957df023dfe2fea39f8da5c27ca3b27", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T203416.374309Z-p68431-n1785011656374597000/response-0004.txt", "size": 1044, "sha256": "7fdda11e8830566b5d0f605a720549a84fd60e8b356d3aaea917d26cb7889553", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T203416.374309Z-p68431-n1785011656374597000/response-0005.txt", "size": 977, "sha256": "ed952b2e3a19939cd42684194006e1d2b30bea9b210722be6f85e058b418efdb", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T203416.374309Z-p68431-n1785011656374597000/response-0006.txt", "size": 486, "sha256": "4b10e09b21c3629beb60d0371a499f6ad2998e2c4d920d7d2c7a5777d1fcf0dd", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T20:38:31.067624+00:00", "runId": "20260725T203625.821780Z-p97652-n1785011785822040000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 5, "nCorrect": 5, "successRate": 0.8333, "gate1_schema": false, "gate2_success": false, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": false, "consecutiveRuns": 0, "previousRunIds": [], "cohortReady": false, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": null, "failureClass": null, "obligations": null, "textTraceability": {"problems": false, "contradictions": false, "summary": false}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}}, "perKeyCorrect": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": false, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": false, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T203625.821780Z-p97652-n1785011785822040000/run-manifest.json", "sha256": "1279bf364523ef2bbe8fb19c45c34e0850d8a5c6aaadf3f9d65dc361b79030c4", "runAuditHash": "e69ef1d8379ead9d6117abc62cf01a6b2bf9dc29c2a5a3a2c1df0b99f3337aa5", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.201305, "promptTokens": 20332, "completionTokens": 17897, "totalLatencyMs": 123797, "nError": 0, "gate3_note": "无基线,首次跑(advisory,未拦)", "gate4_note": "无基线,首次跑(advisory,未拦)", "gate5_note": "本轮基础闸未全绿,稳定性计数归零", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T203625.821780Z-p97652-n1785011785822040000/response-0001.txt", "size": 689, "sha256": "f7fa2a28f9cb7a111adc77cd6bdc89212a976b83b8c1c2939943bf61d523e92e", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T203625.821780Z-p97652-n1785011785822040000/response-0002.txt", "size": 1245, "sha256": "325bf8ce6470a6340b0bfbe09871b0cb4410edee445a843551ad3a90e387ede0", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T203625.821780Z-p97652-n1785011785822040000/response-0003.txt", "size": 623, "sha256": "d8a2e38cd99c22d545ded6b4c4d37bea2816713105e2b0207e5d7bf16786c13b", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": false, "correct": false, "verdict": {"decision": null, "failureClass": null, "obligations": null, "textTraceability": {"problems": false, "contradictions": false, "summary": false}}, "schema_bad": ["<非 JSON 对象>", "生产 parser:invalid_judge_shape:Judge 输出字段不符合白名单"], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T203625.821780Z-p97652-n1785011785822040000/response-0004.txt", "size": 662, "sha256": "57e8b021c898cd8ca7db28e0bdc8e2d8d12674af80d9f35c3785a3cd212cb227", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T203625.821780Z-p97652-n1785011785822040000/response-0005.txt", "size": 1260, "sha256": "47855f4803d30d29e3468f665cffb2603dcd0ed764825df6afd49f635502ed88", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T203625.821780Z-p97652-n1785011785822040000/response-0006.txt", "size": 799, "sha256": "182e35af81523b3fa1cbdc2561cffae4f35ea1ca5048f0997f621f4890b22179", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T20:41:05.446252+00:00", "runId": "20260725T203907.614332Z-p34150-n1785011947614575000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 6, "nCorrect": 4, "successRate": 0.6667, "gate1_schema": true, "gate2_success": false, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": false, "consecutiveRuns": 0, "previousRunIds": [], "cohortReady": false, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": false, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": false, "contradictions": true, "summary": true}}}, "perKeyCorrect": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": false, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": false}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T203907.614332Z-p34150-n1785011947614575000/run-manifest.json", "sha256": "f662dd4507c85db211bd6d663da5e27bd94571791690a3fc03593cb196f7fd29", "runAuditHash": "b64903485ab1f43d3e89f7117c296936b1dd7ca7729f21ed3a874bc3f8ac212b", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.177097, "promptTokens": 20330, "completionTokens": 15134, "totalLatencyMs": 116367, "nError": 0, "gate3_note": "无基线,首次跑(advisory,未拦)", "gate4_note": "无基线,首次跑(advisory,未拦)", "gate5_note": "本轮基础闸未全绿,稳定性计数归零", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T203907.614332Z-p34150-n1785011947614575000/response-0001.txt", "size": 672, "sha256": "403468322fc405d546d923508de22a2faa5239abdefcb815f270ff2289a5b8f2", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T203907.614332Z-p34150-n1785011947614575000/response-0002.txt", "size": 1422, "sha256": "d06a3be23628aa8ff3848155914917b66a30e4c63d39fb5697e683c0e891e412", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T203907.614332Z-p34150-n1785011947614575000/response-0003.txt", "size": 632, "sha256": "78854dff0834a50dabb742991c85b0d937a217219fb04e3d46b5a9c11cc07d20", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": false, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": false, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T203907.614332Z-p34150-n1785011947614575000/response-0004.txt", "size": 1212, "sha256": "9403c25b98e9b9f8bcd551ad83007579b9cf09b229e6edfee584158fd898b957", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T203907.614332Z-p34150-n1785011947614575000/response-0005.txt", "size": 1117, "sha256": "0cc574634d9288a52a89c8683a4df4dc4a1be913a549566ddda3234b5022a5e0", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": false, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": false, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T203907.614332Z-p34150-n1785011947614575000/response-0006.txt", "size": 1346, "sha256": "8d321336c477a0875185c94fb016b381b887d39344b144e5cc7d523a3b7b96e1", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T20:42:53.806041+00:00", "runId": "20260725T204126.479309Z-p70675-n1785012086479595000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 6, "nCorrect": 4, "successRate": 0.6667, "gate1_schema": true, "gate2_success": false, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": false, "consecutiveRuns": 0, "previousRunIds": [], "cohortReady": false, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": false}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": false}}}, "perKeyCorrect": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": false, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": false}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T204126.479309Z-p70675-n1785012086479595000/run-manifest.json", "sha256": "aec60f99ec89689890f1dadf5c26106b25d7ac3c35b66bd6a81276d48a6cfa46", "runAuditHash": "9a29f4bfd04ffd1e233657352df0ef626e564bd3654b08fc93fa8b77ab7b49a2", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.146147, "promptTokens": 20330, "completionTokens": 11601, "totalLatencyMs": 85895, "nError": 0, "gate3_note": "无基线,首次跑(advisory,未拦)", "gate4_note": "无基线,首次跑(advisory,未拦)", "gate5_note": "本轮基础闸未全绿,稳定性计数归零", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T204126.479309Z-p70675-n1785012086479595000/response-0001.txt", "size": 680, "sha256": "e5c02b527a13eb9ec28ce3a6f36010d601a375a3b815518aac2414aea0bdb99b", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T204126.479309Z-p70675-n1785012086479595000/response-0002.txt", "size": 1317, "sha256": "3f63eebcfb9bbd9170c2a941d5ff73d6ebb44f1e208e5367642ba03140d408ee", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": false, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": false}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T204126.479309Z-p70675-n1785012086479595000/response-0003.txt", "size": 611, "sha256": "fdda9901f0efe58fdfa8ee83f9f4bf5f5d04702324d0beae562b68c849720b89", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T204126.479309Z-p70675-n1785012086479595000/response-0004.txt", "size": 1022, "sha256": "0d622f82b0e351e3ac035306485296c9001c2c6a7fb3f4a9f3b0c939c6ec3dd6", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T204126.479309Z-p70675-n1785012086479595000/response-0005.txt", "size": 869, "sha256": "f1a4979dbaef3efa74835ecffb0410914c75e6c4f7f44c2984c57b53efb2b6f9", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": false, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": false}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T204126.479309Z-p70675-n1785012086479595000/response-0006.txt", "size": 524, "sha256": "d305c4e40b566c8b78e3a8273f8867e62b3f866f11bb59a9e5f67733983959df", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T20:45:02.039453+00:00", "runId": "20260725T204336.479965Z-p7057-n1785012216480218000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 6, "nCorrect": 6, "successRate": 1.0, "gate1_schema": true, "gate2_success": true, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": true, "consecutiveRuns": 1, "previousRunIds": [], "cohortReady": false, "cohortRuns": 1, "cohortCorrect": 6, "cohortSchemaOk": 6, "perKeyCorrectCounts": {"judge:accept:business-settlement": 1, "judge:inconclusive:business-visual-conflict": 1, "judge:accept:puzzle-victory": 1, "judge:inconclusive:puzzle-conflict": 1, "judge:reject:runner-crashed-injection": 1, "judge:inconclusive:missing-proof-injection": 1}, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}}, "perKeyCorrect": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T204336.479965Z-p7057-n1785012216480218000/run-manifest.json", "sha256": "f95fddd6241205e51904ae71c023181c911a98f437de0cf39d96328d00dbafcb", "runAuditHash": "6e7797e5b07635fa94804e9559e1c30da02f558c2916effbe468d82936a7a625", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.128903, "promptTokens": 20328, "completionTokens": 9633, "totalLatencyMs": 84006, "nError": 0, "gate3_note": "无基线,首次跑(advisory,未拦)", "gate4_note": "无基线,首次跑(advisory,未拦)", "gate5_note": "同请求合格 1 轮;三轮 cohort 正确 6/18", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T204336.479965Z-p7057-n1785012216480218000/response-0001.txt", "size": 779, "sha256": "cb63d7f1e5be3455a0a5b35b5954359209f55910cd4865706f2530eadb9b9bfc", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T204336.479965Z-p7057-n1785012216480218000/response-0002.txt", "size": 1417, "sha256": "1386d9a2c0097ccac68cc3baa2ae0e745a2f87e31c0b31868aa002cfd061c7a9", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T204336.479965Z-p7057-n1785012216480218000/response-0003.txt", "size": 712, "sha256": "65601aa78dcd93abcc93ec2fafcfcff63b67041ca802c6e08e533e160b6beb54", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T204336.479965Z-p7057-n1785012216480218000/response-0004.txt", "size": 1075, "sha256": "33a89e7fd087bf10cd419ff5d6290d7a6022eb7c455277965b43fec45562e32f", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T204336.479965Z-p7057-n1785012216480218000/response-0005.txt", "size": 1238, "sha256": "fd01f4694aa0eae4d59c305c6ce572046ccb7bb97581184b1ed6b23d529c38e7", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T204336.479965Z-p7057-n1785012216480218000/response-0006.txt", "size": 554, "sha256": "e1ba3c0c6f8a488dfadf95853b9b1ba0869cc0e2da47f097a60e30aabfdd7c9d", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T20:46:44.646963+00:00", "runId": "20260725T204511.506288Z-p34530-n1785012311506545000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 6, "nCorrect": 6, "successRate": 1.0, "gate1_schema": true, "gate2_success": true, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": true, "consecutiveRuns": 2, "previousRunIds": ["20260725T204336.479965Z-p7057-n1785012216480218000"], "cohortReady": false, "cohortRuns": 2, "cohortCorrect": 12, "cohortSchemaOk": 12, "perKeyCorrectCounts": {"judge:accept:business-settlement": 2, "judge:inconclusive:business-visual-conflict": 2, "judge:accept:puzzle-victory": 2, "judge:inconclusive:puzzle-conflict": 2, "judge:reject:runner-crashed-injection": 2, "judge:inconclusive:missing-proof-injection": 2}, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}}, "perKeyCorrect": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T204511.506288Z-p34530-n1785012311506545000/run-manifest.json", "sha256": "618ae92df6aa9fa4bf60e461f133e1812dfc7367c0de1e6839159e1fe68c9146", "runAuditHash": "7a605b7f33144aa6fd0b29ffdad3ed36cdebffdcd282a1b7d5bf242955231b92", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.153756, "promptTokens": 20332, "completionTokens": 12469, "totalLatencyMs": 91707, "nError": 0, "gate3_note": "无基线,首次跑(advisory,未拦)", "gate4_note": "无基线,首次跑(advisory,未拦)", "gate5_note": "同请求合格 2 轮;三轮 cohort 正确 12/18", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T204511.506288Z-p34530-n1785012311506545000/response-0001.txt", "size": 617, "sha256": "ed9123e78cae8261cf5c1c8e71a63b1a88b9be88b7635d10c1d5d9655458f3ec", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T204511.506288Z-p34530-n1785012311506545000/response-0002.txt", "size": 1209, "sha256": "96b30decf165749987a4744059409a438c1e7c7606859e6b9fc5a93f84ff39e4", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T204511.506288Z-p34530-n1785012311506545000/response-0003.txt", "size": 578, "sha256": "2c52025b64ab5acb063203b212019d18643f45fb9c00b5172e2cb45c93f4c7d0", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T204511.506288Z-p34530-n1785012311506545000/response-0004.txt", "size": 987, "sha256": "f13fc5b2a0907af981b0255ae136981e5a7d345347865cddf3773867db497762", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T204511.506288Z-p34530-n1785012311506545000/response-0005.txt", "size": 969, "sha256": "a545da42c26458fd4b2d5d4b82221f65cb0622d074cdf911758480bb46850b5a", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T204511.506288Z-p34530-n1785012311506545000/response-0006.txt", "size": 745, "sha256": "2cfc39ca1db346268508da529477542f423aa864b44e5d62eccdd96203ddd3eb", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T20:48:23.935387+00:00", "runId": "20260725T204658.236654Z-p74535-n1785012418236907000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 6, "nCorrect": 6, "successRate": 1.0, "gate1_schema": true, "gate2_success": true, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": true, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": true, "consecutiveRuns": 3, "previousRunIds": ["20260725T204511.506288Z-p34530-n1785012311506545000", "20260725T204336.479965Z-p7057-n1785012216480218000"], "cohortReady": true, "cohortRuns": 3, "cohortCorrect": 18, "cohortSchemaOk": 18, "perKeyCorrectCounts": {"judge:accept:business-settlement": 3, "judge:inconclusive:business-visual-conflict": 3, "judge:accept:puzzle-victory": 3, "judge:inconclusive:puzzle-conflict": 3, "judge:reject:runner-crashed-injection": 3, "judge:inconclusive:missing-proof-injection": 3}, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}}, "perKeyCorrect": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "baseline_updated_rerun_required", "allGreen": false, "baselineUpdateRequested": true, "baselineUpdateEligible": true, "baselineUpdated": true, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T204658.236654Z-p74535-n1785012418236907000/run-manifest.json", "sha256": "e1a089e2a8d178c478d68c5d59fbb5411fe57a37f5fecdb1ae24b5dec79859f3", "runAuditHash": "8729f37d370d009ad01528dc31fdf8f2b1d22fc743d89aaf6e921d4100735eef", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.143414, "promptTokens": 20330, "completionTokens": 11289, "totalLatencyMs": 84252, "nError": 0, "gate3_note": "无基线,首次跑(advisory,未拦)", "gate4_note": "无基线,首次跑(advisory,未拦)", "gate5_note": "同请求合格 3 轮;三轮 cohort 正确 18/18", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T204658.236654Z-p74535-n1785012418236907000/response-0001.txt", "size": 885, "sha256": "01b28f0e4d18827eb3c10392238b05e435e4399c2985f193db621fd8ce0a0a13", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T204658.236654Z-p74535-n1785012418236907000/response-0002.txt", "size": 1292, "sha256": "ad0f70b55a0926b6ff190ab94d8d1ff8ace25b219e0b28b9c78987f5d4298c6a", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T204658.236654Z-p74535-n1785012418236907000/response-0003.txt", "size": 573, "sha256": "7fb2e932b6324d3d37de0f9fb480e4c1bbfdf07ba4c3205996b4feba2d21c62f", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T204658.236654Z-p74535-n1785012418236907000/response-0004.txt", "size": 1142, "sha256": "c7ce1c575979ef00c75c30176247f7bc5a29ac58f4a5593a65aee4511dbd4567", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T204658.236654Z-p74535-n1785012418236907000/response-0005.txt", "size": 682, "sha256": "fa99cc0679596f3e23dac56931918a3b60e21ff5716b79746d2541cad400eed7", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T204658.236654Z-p74535-n1785012418236907000/response-0006.txt", "size": 769, "sha256": "e775114d6f783779f5664ae26e28526a25da2ea913c17c59097f1f093efd60fc", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T20:50:19.469862+00:00", "runId": "20260725T204836.648943Z-p3404-n1785012516649216000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 6, "nCorrect": 5, "successRate": 0.8333, "gate1_schema": true, "gate2_success": false, "gate3_regression": false, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": false, "consecutiveRuns": 0, "previousRunIds": [], "cohortReady": false, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": false}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}}, "perKeyCorrect": {"judge:accept:business-settlement": false, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T204836.648943Z-p3404-n1785012516649216000/run-manifest.json", "sha256": "e7c3dd33313f18a96f18dade0f534be4911a6cedacdc092dc1f3b11445f12527", "runAuditHash": "0f3c9fb38d6c776158ea330ce35140dd1661887d2346d61f1a0c37019bfaa526", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.161136, "promptTokens": 20330, "completionTokens": 13312, "totalLatencyMs": 101376, "nError": 0, "gate3_note": "Judge 金标全对标准回退", "gate4_note": "成本Δ=+12.4%(限+50%) 延迟Δ=+20.3%(限+100%)", "gate5_note": "本轮基础闸未全绿,稳定性计数归零", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": false, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": false}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T204836.648943Z-p3404-n1785012516649216000/response-0001.txt", "size": 639, "sha256": "e8025998b468b8a0a4a116342f13dfcb9277b8e55b7904e52c262af4fbbbce21", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T204836.648943Z-p3404-n1785012516649216000/response-0002.txt", "size": 1622, "sha256": "bcedfdb5c67eeccaa9317ce8e8640bb978933bbec7a38635bfaea11daf5144f7", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T204836.648943Z-p3404-n1785012516649216000/response-0003.txt", "size": 599, "sha256": "7c950088808838e079206bf40e387f98cb2c0745dffbe297d292f23c90566150", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T204836.648943Z-p3404-n1785012516649216000/response-0004.txt", "size": 860, "sha256": "9811e7c1bbbe10ef8dd605ef4deaf94eeb349b4ce70a517f6b9674e14804b79a", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T204836.648943Z-p3404-n1785012516649216000/response-0005.txt", "size": 958, "sha256": "d09dff0858af3096e00beed16be3686e6c1629214333ffb2e74270accbed462b", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T204836.648943Z-p3404-n1785012516649216000/response-0006.txt", "size": 690, "sha256": "2097ce6f82f112a934a6dbc9a75434c2187bd158ef3f0dae8ad7cbb98ebf4a2d", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T20:52:18.152451+00:00", "runId": "20260725T205030.509829Z-p43108-n1785012630510092000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 5, "nCorrect": 5, "successRate": 0.8333, "gate1_schema": false, "gate2_success": false, "gate3_regression": false, "gate4_cost_latency": true, "gate5_stability": false, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": false, "consecutiveRuns": 0, "previousRunIds": [], "cohortReady": false, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": null, "failureClass": null, "obligations": null, "textTraceability": {"problems": false, "contradictions": false, "summary": false}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}}, "perKeyCorrect": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": false, "judge:inconclusive:missing-proof-injection": true}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": false, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "failed", "allGreen": false, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T205030.509829Z-p43108-n1785012630510092000/run-manifest.json", "sha256": "4308f3f23d872eeae339abcaef51ee13c5c7d2ecc8e150c0624ea95ab80ce0e7", "runAuditHash": "79d3416979205202d8c3e15c44e364644478c1862479801b8c5fa5601642bd02", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.167706, "promptTokens": 20330, "completionTokens": 14062, "totalLatencyMs": 106216, "nError": 0, "gate3_note": "Judge 金标全对标准回退", "gate4_note": "成本Δ=+16.9%(限+50%) 延迟Δ=+26.1%(限+100%)", "gate5_note": "本轮基础闸未全绿,稳定性计数归零", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T205030.509829Z-p43108-n1785012630510092000/response-0001.txt", "size": 718, "sha256": "b5c23d86a99dcb6b3700577aec23bd84358e4d3445e3d9cb081b63856fdefe05", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T205030.509829Z-p43108-n1785012630510092000/response-0002.txt", "size": 1376, "sha256": "512b16f74b8cf6ccf831b85c8fdbc9df3e008b671be38ef46c211ca2053ef4ba", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T205030.509829Z-p43108-n1785012630510092000/response-0003.txt", "size": 568, "sha256": "fd4dc5740c2cc069d5f72004b656274ed320f8b8ee76438dcdd7be99478fd77a", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T205030.509829Z-p43108-n1785012630510092000/response-0004.txt", "size": 1366, "sha256": "80d4bf946229bdd00338a68c3586e9361cd39f9a20c102dfbe212994f05bb791", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": false, "correct": false, "verdict": {"decision": null, "failureClass": null, "obligations": null, "textTraceability": {"problems": false, "contradictions": false, "summary": false}}, "schema_bad": ["<非 JSON 对象>", "生产 parser:invalid_judge_json:Judge 必须只输出一个合法 JSON 对象"], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T205030.509829Z-p43108-n1785012630510092000/response-0005.txt", "size": 1377, "sha256": "4f7e98f84f9152ccb69c77eb36b8e9a2009c30a867ef5619b8c5863651ebef0c", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T205030.509829Z-p43108-n1785012630510092000/response-0006.txt", "size": 707, "sha256": "4058a33309699c4ed859307c051dd5f962271fd453d5bd6dab00b1a3c8232b2a", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|
||
{"ts": "2026-07-25T20:54:05.303120+00:00", "runId": "20260725T205229.606136Z-p83185-n1785012749606406000", "promptId": "playtest.judge-b", "version": "3.0.14", "model": "MiniMax-M3", "promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "nSamples": 6, "nJudged": 6, "nSchemaOk": 6, "nCorrect": 6, "successRate": 1.0, "gate1_schema": true, "gate2_success": true, "gate3_regression": true, "gate4_cost_latency": true, "gate5_stability": true, "infrastructureComplete": true, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437", "stability": {"qualified": true, "consecutiveRuns": 1, "previousRunIds": [], "cohortReady": false, "cohortRuns": 1, "cohortCorrect": 6, "cohortSchemaOk": 6, "perKeyCorrectCounts": {"judge:accept:business-settlement": 1, "judge:inconclusive:business-visual-conflict": 1, "judge:accept:puzzle-victory": 1, "judge:inconclusive:puzzle-conflict": 1, "judge:reject:runner-crashed-injection": 1, "judge:inconclusive:missing-proof-injection": 1}, "identity": {"promptBodySha256": "adc6faec0ce5fd35068c7f800ae04b237ff5524099c283f43cb03c9e3742d2aa", "fixtureSnapshot": {"inputsSha256": "8cfdb7253d350020674320430db55dfe9c6eac289b9a3562a18e8108173966fd", "labelsSha256": "60928f29d8d1c3f888981314469e7a4e8b9b38d08892bfc0356c021f75b97f09", "imageFixturesSha256": "dc63b2deed36a0d86996ea17a6333b9954ef8e364e22cf0b693a04602b7d1cf2", "overallSha256": "17f3a49142892aa355f7b55da57855c7a408590a7916391703285320b860b459"}, "model": "MiniMax-M3", "providerProtocol": "anthropic-messages", "providerOutputSchemaSha256": "45eac8ff06933337a50bf7823f762a6f470bb297d41f178a2966ff63d1bffc80", "thinkingBudgetTokens": 2000, "maxTokens": 10000, "seedStrategy": "audit-only-sha256(promptId\\0evalKey)-uint32be;anthropic-provider-no-seed", "auditSchemaVersion": "PromptEvalAudit/2", "codeIdentityHash": "a224ba9c0d0064a9aa3b95d0475d413f33be88bb30a00008926b5214ee658437"}, "requestBodySha256": {"judge:accept:business-settlement": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a", "judge:inconclusive:business-visual-conflict": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce", "judge:accept:puzzle-victory": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133", "judge:inconclusive:puzzle-conflict": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8", "judge:reject:runner-crashed-injection": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8", "judge:inconclusive:missing-proof-injection": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}, "signatures": {"judge:accept:business-settlement": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:business-visual-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:accept:puzzle-victory": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:puzzle-conflict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:reject:runner-crashed-injection": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "judge:inconclusive:missing-proof-injection": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}}, "perKeyCorrect": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "perKeySchemaOk": {"judge:accept:business-settlement": true, "judge:inconclusive:business-visual-conflict": true, "judge:accept:puzzle-victory": true, "judge:inconclusive:puzzle-conflict": true, "judge:reject:runner-crashed-injection": true, "judge:inconclusive:missing-proof-injection": true}, "requiredRuns": 3}, "status": "passed", "allGreen": true, "baselineUpdateRequested": false, "baselineUpdateEligible": false, "baselineUpdated": false, "auditManifest": {"schemaVersion": "PromptEvalAudit/2", "path": "raw/20260725T205229.606136Z-p83185-n1785012749606406000/run-manifest.json", "sha256": "54432a9da3a8aaf7d6c7aa406c8b1361b2da095f4227d2669c87496403969859", "runAuditHash": "0bb4ea07b3ece284461f008a3df8e4f9bd00dad9f3ab66b0119e3a16e420759c", "auditComplete": true, "requestReplayable": true, "providerDeterministic": "unknown"}, "estCostRmb": 0.159577, "promptTokens": 20330, "completionTokens": 13134, "totalLatencyMs": 94237, "nError": 0, "gate3_note": "Judge 金标全对标准保持达标", "gate4_note": "成本Δ=+11.3%(限+50%) 延迟Δ=+11.9%(限+100%)", "gate5_note": "同请求合格 1 轮;三轮 cohort 正确 6/18", "perKey": {"judge:accept:business-settlement": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3229931891, "rawAudit": {"path": "raw/20260725T205229.606136Z-p83185-n1785012749606406000/response-0001.txt", "size": 658, "sha256": "790fc5c4c67e1be3a9ce9210f132955d8f5c21d21adcd7adcfa1950f145abfe6", "requestBodySha256": "307374f1db095cf51b89f2d1dd0cf864c1171051fe22c8b3347c85d0a3b64e0a"}}, "judge:inconclusive:business-visual-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-9", "eventRef": 21, "postFrameRef": "frames/action-9-post.png", "stepId": "revenue"}], "evidenceRefs": ["action-9", "frames/action-9-post.png", "event:21"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 4205681681, "rawAudit": {"path": "raw/20260725T205229.606136Z-p83185-n1785012749606406000/response-0002.txt", "size": 1101, "sha256": "3657c8e8c96c4d473fe418748f1b447b5d468e9c76903dfad8de6535c3a2a5cd", "requestBodySha256": "996d913b1882d7e19744320c7b7dbb99ea038a52e3be607d8c79fb6a7e0889ce"}}, "judge:accept:puzzle-victory": {"schema_ok": true, "correct": true, "verdict": {"decision": "accept", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "satisfied", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 2704448392, "rawAudit": {"path": "raw/20260725T205229.606136Z-p83185-n1785012749606406000/response-0003.txt", "size": 632, "sha256": "406e6117bec0e9410adefacfb604ddfb2932aab2824e76fee9966159e2503795", "requestBodySha256": "b42822d5ea2bf6181b7c523b6534797101deef724d197ac1e6c762b45e7cc133"}}, "judge:inconclusive:puzzle-conflict": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "puzzle.level-completed", "status": "contradicted", "sequenceRefs": [{"actionRef": "action-10", "eventRef": 31, "postFrameRef": "frames/action-10-post.png", "stepId": "complete"}], "evidenceRefs": ["action-10", "frames/action-10-post.png", "event:31"]}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 1698103914, "rawAudit": {"path": "raw/20260725T205229.606136Z-p83185-n1785012749606406000/response-0004.txt", "size": 1180, "sha256": "6a94e409e33804e09ca92c7d676cb52d0daa299bf0fc7f242861a88092d8e371", "requestBodySha256": "1c74a1492b37edf97ecee227e11ad45e26730794d03f451690f1c0b29e677aa8"}}, "judge:reject:runner-crashed-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "reject", "failureClass": "off_brief", "obligations": [{"id": "narrative.ending-reached", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 714485925, "rawAudit": {"path": "raw/20260725T205229.606136Z-p83185-n1785012749606406000/response-0005.txt", "size": 1464, "sha256": "bb066df1ae15cfa762b2b0fd96e582bdc4c8300ca94d41e919034cb652850af1", "requestBodySha256": "ecee0d67bd3c38c1b83afae4ba93ecd4b9b8f8114b5465d991976280805ad6e8"}}, "judge:inconclusive:missing-proof-injection": {"schema_ok": true, "correct": true, "verdict": {"decision": "inconclusive", "failureClass": "none", "obligations": [{"id": "sim-business.revenue-positive", "status": "missing", "sequenceRefs": [], "evidenceRefs": []}], "textTraceability": {"problems": true, "contradictions": true, "summary": true}}, "schema_bad": [], "error": null, "seed": 3138786458, "rawAudit": {"path": "raw/20260725T205229.606136Z-p83185-n1785012749606406000/response-0006.txt", "size": 652, "sha256": "b831fcc4425e3eed94d8c226f5bc883dcf985d07a5530acbbf3c57472da671c1", "requestBodySha256": "e06799f15bea1efd79108b728c932923b32e52e4e1479b8f1b822a80cf03bf0a"}}}}
|