{"age_at_observation_days": 22, "backfilled": true, "commit": "c0def76aaa3b31277f21276e55b6e6a9a57b4af5", "coverage": null, "detail": "block 100%, benign utility 100%", "harness_version": "0.8.6", "measured_at": "2026-08-10T00:00:00Z", "measured_at_precision": "day", "observed_at": "2026-09-01T10:53:50Z", "report": "asb-20260810.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "asb"}
{"age_at_observation_days": 22, "backfilled": true, "commit": "c0def76aaa3b31277f21276e55b6e6a9a57b4af5", "coverage": null, "detail": "governed blocked 100% vs ungoverned 0%", "harness_version": "0.8.6", "measured_at": "2026-08-10T00:00:00Z", "measured_at_precision": "day", "observed_at": "2026-09-01T10:53:50Z", "report": "governed-benchmark-20260810.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "governed-benchmark"}
{"age_at_observation_days": 22, "backfilled": true, "commit": "c0def76aaa3b31277f21276e55b6e6a9a57b4af5", "coverage": null, "detail": "block 100%, benign utility 100%", "harness_version": "0.8.6", "measured_at": "2026-08-10T00:00:00Z", "measured_at_precision": "day", "observed_at": "2026-09-01T10:53:50Z", "report": "injection_defense-20260810.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "injection_defense"}
{"age_at_observation_days": 18, "backfilled": true, "commit": "6674e913f0ab4a740285c31d5586e308d1f64d45", "coverage": 0.5, "detail": "3/3 tasks passed, avg score 1.00, assertion coverage 50%", "harness_version": "0.8.7", "measured_at": "2026-08-14T08:16:34Z", "measured_at_precision": "second", "observed_at": "2026-09-01T10:53:50Z", "report": "eval_smoke_20260814_081634.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "smoke"}
{"age_at_observation_days": 17, "backfilled": true, "commit": "6674e913f0ab4a740285c31d5586e308d1f64d45", "coverage": 0.5, "detail": "3/3 tasks passed, avg score 1.00, assertion coverage 50%", "harness_version": "0.8.7", "measured_at": "2026-08-15T02:54:59Z", "measured_at_precision": "second", "observed_at": "2026-09-01T10:53:50Z", "report": "eval_smoke_20260815_025459.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "smoke"}
{"age_at_observation_days": 16, "backfilled": true, "commit": "e5adcbbe56e84a327e7cbc1bfab34ecf2e427061", "coverage": 0.5, "detail": "20/20 tasks passed, avg score 1.00, assertion coverage 50%", "harness_version": "0.8.7", "measured_at": "2026-08-15T17:17:45Z", "measured_at_precision": "second", "observed_at": "2026-09-01T10:53:50Z", "report": "eval_regression_20260815_171745.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "regression"}
{"age_at_observation_days": 16, "backfilled": true, "commit": "7d04dedacca163b2692f56b352cb452ccecd5141", "coverage": 0.5, "detail": "3/3 tasks passed, avg score 1.00, assertion coverage 50%", "harness_version": "0.8.7", "measured_at": "2026-08-16T03:03:24Z", "measured_at_precision": "second", "observed_at": "2026-09-01T10:53:50Z", "report": "eval_smoke_20260816_030324.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "smoke"}
{"age_at_observation_days": 16, "backfilled": true, "commit": "3d2ccda1fdba5b7dbfbc71eeca8025d621374b4f", "coverage": 0.5, "detail": "20/20 tasks passed, avg score 1.00, assertion coverage 50%", "harness_version": "0.8.7", "measured_at": "2026-08-16T03:45:22Z", "measured_at_precision": "second", "observed_at": "2026-09-01T10:53:50Z", "report": "eval_regression_20260816_034522.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "regression"}
{"age_at_observation_days": 15, "backfilled": true, "commit": "37829d806c1afca88e62f2ca0d1d94484f267f71", "coverage": 0.5, "detail": "3/3 tasks passed, avg score 1.00, assertion coverage 50%", "harness_version": "0.8.7", "measured_at": "2026-08-17T03:02:59Z", "measured_at_precision": "second", "observed_at": "2026-09-01T10:53:50Z", "report": "eval_smoke_20260817_030259.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "smoke"}
{"age_at_observation_days": 14, "backfilled": true, "commit": "94e50c2d07048a7163108ae95a81d4d5a08b09ee", "coverage": 1.0, "detail": "3/3 tasks passed, avg score 1.00, assertion coverage 100%", "harness_version": "0.8.8", "measured_at": "2026-08-18T02:59:16Z", "measured_at_precision": "second", "observed_at": "2026-09-01T10:53:50Z", "report": "eval_smoke_20260818_025916.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "smoke"}
{"age_at_observation_days": 13, "backfilled": true, "commit": "b07480f8ffa1976109214e2880335ba76706d1d2", "coverage": 1.0, "detail": "3/3 tasks passed, avg score 1.00, assertion coverage 100%", "harness_version": "0.8.8", "measured_at": "2026-08-19T03:00:39Z", "measured_at_precision": "second", "observed_at": "2026-09-01T10:53:50Z", "report": "eval_smoke_20260819_030039.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "smoke"}
{"age_at_observation_days": 12, "backfilled": true, "commit": "b7154c6d3d224134bf749390f17b16856ce688d7", "coverage": 1.0, "detail": "3/3 tasks passed, avg score 1.00, assertion coverage 100%", "harness_version": "0.8.9", "measured_at": "2026-08-20T03:00:17Z", "measured_at_precision": "second", "observed_at": "2026-09-01T10:53:50Z", "report": "eval_smoke_20260820_030017.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "smoke"}
{"age_at_observation_days": 11, "backfilled": true, "commit": "0facd5d86cb655e41fe6c0ebf5d4ffd932207295", "coverage": 1.0, "detail": "3/3 tasks passed, avg score 1.00, assertion coverage 100%", "harness_version": "0.8.9", "measured_at": "2026-08-21T03:06:12Z", "measured_at_precision": "second", "observed_at": "2026-09-01T10:53:50Z", "report": "eval_smoke_20260821_030612.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "smoke"}
{"age_at_observation_days": 10, "backfilled": true, "commit": "146bdadf76d4afd729a88663b30cb71cf00bc5ff", "coverage": null, "detail": "block 100%, benign utility 100%", "harness_version": "0.8.11", "measured_at": "2026-08-22T00:00:00Z", "measured_at_precision": "day", "observed_at": "2026-09-01T10:53:50Z", "report": "asb-20260822.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "asb"}
{"age_at_observation_days": 10, "backfilled": true, "commit": "146bdadf76d4afd729a88663b30cb71cf00bc5ff", "coverage": null, "detail": "governed blocked 100% vs ungoverned 0%", "harness_version": "0.8.11", "measured_at": "2026-08-22T00:00:00Z", "measured_at_precision": "day", "observed_at": "2026-09-01T10:53:50Z", "report": "governed-benchmark-20260822.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "governed-benchmark"}
{"age_at_observation_days": 10, "backfilled": true, "commit": "146bdadf76d4afd729a88663b30cb71cf00bc5ff", "coverage": null, "detail": "block 100%, benign utility 100%", "harness_version": "0.8.11", "measured_at": "2026-08-22T00:00:00Z", "measured_at_precision": "day", "observed_at": "2026-09-01T10:53:50Z", "report": "injection_defense-20260822.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "injection_defense"}
{"age_at_observation_days": 10, "backfilled": true, "commit": "9dafe7d59a355f8c9f8ed90a737fc50d08c2e4b2", "coverage": 1.0, "detail": "3/3 tasks passed, avg score 1.00, assertion coverage 100%", "harness_version": "0.8.10", "measured_at": "2026-08-22T02:57:41Z", "measured_at_precision": "second", "observed_at": "2026-09-01T10:53:50Z", "report": "eval_smoke_20260822_025741.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "smoke"}
{"age_at_observation_days": 9, "backfilled": true, "commit": "b049d4254f8bf720a6a8276f6903375e6525955c", "coverage": 1.0, "detail": "3/3 tasks passed, avg score 1.00, assertion coverage 100%", "harness_version": "0.8.12", "measured_at": "2026-08-23T03:05:42Z", "measured_at_precision": "second", "observed_at": "2026-09-01T10:53:50Z", "report": "eval_smoke_20260823_030542.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "smoke"}
{"age_at_observation_days": 9, "backfilled": true, "commit": "67cfa72f9875d549a613f7cc7f4f69196d870085", "coverage": 1.0, "detail": "20/20 tasks passed, avg score 1.00, assertion coverage 100%", "harness_version": "0.8.12", "measured_at": "2026-08-23T03:47:08Z", "measured_at_precision": "second", "observed_at": "2026-09-01T10:53:50Z", "report": "eval_regression_20260823_034708.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "regression"}
{"age_at_observation_days": 8, "backfilled": true, "commit": "8e16519db15fd4d9ec2205da54d94446cbbcfa3a", "coverage": 1.0, "detail": "3/3 tasks passed, avg score 1.00, assertion coverage 100%", "harness_version": "0.8.12", "measured_at": "2026-08-24T03:07:10Z", "measured_at_precision": "second", "observed_at": "2026-09-01T10:53:50Z", "report": "eval_smoke_20260824_030710.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "smoke"}
{"age_at_observation_days": 7, "backfilled": true, "commit": "1c0fdc02c29f3dd878447e4464853a21f2817b3f", "coverage": 1.0, "detail": "3/3 tasks passed, avg score 1.00, assertion coverage 100%", "harness_version": "0.8.13", "measured_at": "2026-08-25T03:01:48Z", "measured_at_precision": "second", "observed_at": "2026-09-01T10:53:50Z", "report": "eval_smoke_20260825_030148.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "smoke"}
{"age_at_observation_days": 6, "backfilled": true, "commit": "ad4bd8528f921b17a7c3761f356d16b66e499966", "coverage": null, "detail": "block 100%, benign utility 100%", "harness_version": "0.8.15", "measured_at": "2026-08-26T00:00:00Z", "measured_at_precision": "day", "observed_at": "2026-09-01T10:53:50Z", "report": "asb-20260826.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "asb"}
{"age_at_observation_days": 6, "backfilled": true, "commit": "ad4bd8528f921b17a7c3761f356d16b66e499966", "coverage": null, "detail": "governed blocked 100% vs ungoverned 0%", "harness_version": "0.8.15", "measured_at": "2026-08-26T00:00:00Z", "measured_at_precision": "day", "observed_at": "2026-09-01T10:53:50Z", "report": "governed-benchmark-20260826.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "governed-benchmark"}
{"age_at_observation_days": 6, "backfilled": true, "commit": "ad4bd8528f921b17a7c3761f356d16b66e499966", "coverage": null, "detail": "block 100%, benign utility 100%", "harness_version": "0.8.15", "measured_at": "2026-08-26T00:00:00Z", "measured_at_precision": "day", "observed_at": "2026-09-01T10:53:50Z", "report": "injection_defense-20260826.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "injection_defense"}
{"age_at_observation_days": 6, "backfilled": true, "commit": "839c7472d8aa0d46daa380825bbe62098e1dc41c", "coverage": 1.0, "detail": "3/3 tasks passed, avg score 1.00, assertion coverage 100%", "harness_version": "0.8.14", "measured_at": "2026-08-26T03:08:02Z", "measured_at_precision": "second", "observed_at": "2026-09-01T10:53:50Z", "report": "eval_smoke_20260826_030802.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "smoke"}
{"age_at_observation_days": 4, "backfilled": true, "commit": "3802c429fb3eda67a5312785bfd11570535fd9f1", "coverage": 1.0, "detail": "3/3 tasks passed, avg score 1.00, assertion coverage 100%", "harness_version": "0.8.15", "measured_at": "2026-08-27T12:27:23Z", "measured_at_precision": "second", "observed_at": "2026-09-01T10:53:50Z", "report": "eval_smoke_20260827_122723.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "smoke"}
{"age_at_observation_days": 3, "backfilled": true, "commit": "795da1775f74adcdf3e45483d87c84552f209a8d", "coverage": 1.0, "detail": "3/3 tasks passed, avg score 1.00, assertion coverage 100%", "harness_version": "0.8.15", "measured_at": "2026-08-28T13:53:20Z", "measured_at_precision": "second", "observed_at": "2026-09-01T10:53:50Z", "report": "eval_smoke_20260828_135320.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "smoke"}
{"age_at_observation_days": 3, "backfilled": true, "commit": "0970a24a4ccf01901d1693f09743742bb975a2e4", "coverage": 1.0, "detail": "3/3 tasks passed, avg score 1.00, assertion coverage 100%", "harness_version": "0.8.15", "measured_at": "2026-08-29T08:44:03Z", "measured_at_precision": "second", "observed_at": "2026-09-01T10:53:50Z", "report": "eval_smoke_20260829_084403.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "smoke"}
{"age_at_observation_days": 2, "backfilled": true, "commit": "8f5882c400f7d53106b18c351d296bb54f4a421a", "coverage": null, "detail": "block 100%, benign utility 100%", "harness_version": "0.8.15", "measured_at": "2026-08-30T00:00:00Z", "measured_at_precision": "day", "observed_at": "2026-09-01T10:53:50Z", "report": "asb-20260830.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "asb"}
{"age_at_observation_days": 2, "backfilled": true, "commit": "8f5882c400f7d53106b18c351d296bb54f4a421a", "coverage": null, "detail": "governed blocked 100% vs ungoverned 0%", "harness_version": "0.8.15", "measured_at": "2026-08-30T00:00:00Z", "measured_at_precision": "day", "observed_at": "2026-09-01T10:53:50Z", "report": "governed-benchmark-20260830.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "governed-benchmark"}
{"age_at_observation_days": 2, "backfilled": true, "commit": "8f5882c400f7d53106b18c351d296bb54f4a421a", "coverage": null, "detail": "block 100%, benign utility 100%", "harness_version": "0.8.15", "measured_at": "2026-08-30T00:00:00Z", "measured_at_precision": "day", "observed_at": "2026-09-01T10:53:50Z", "report": "injection_defense-20260830.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "injection_defense"}
{"age_at_observation_days": 2, "backfilled": true, "commit": "a5578ef378714203b7c115388eeb1ceb2550896f", "coverage": 1.0, "detail": "3/3 tasks passed, avg score 1.00, assertion coverage 100%", "harness_version": "0.8.15", "measured_at": "2026-08-30T07:59:30Z", "measured_at_precision": "second", "observed_at": "2026-09-01T10:53:50Z", "report": "eval_smoke_20260830_075930.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "smoke"}
{"age_at_observation_days": 2, "backfilled": true, "commit": "8f5882c400f7d53106b18c351d296bb54f4a421a", "coverage": 1.0, "detail": "20/20 tasks passed, avg score 1.00, assertion coverage 100%", "harness_version": "0.8.15", "measured_at": "2026-08-30T08:46:00Z", "measured_at_precision": "second", "observed_at": "2026-09-01T10:53:50Z", "report": "eval_regression_20260830_084600.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "regression"}
{"age_at_observation_days": 1, "backfilled": true, "commit": "526cfb6a8e91411e10771e8eddaae471eb1e11d2", "coverage": 1.0, "detail": "3/3 tasks passed, avg score 1.00, assertion coverage 100%", "harness_version": "0.8.15", "measured_at": "2026-08-31T08:13:40Z", "measured_at_precision": "second", "observed_at": "2026-09-01T10:53:50Z", "report": "eval_smoke_20260831_081340.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "smoke"}
{"age_at_observation_days": 0, "backfilled": true, "commit": "f93744a2a195b9ca90b6187532ccdd37d729be10", "coverage": 1.0, "detail": "3/3 tasks passed, avg score 1.00, assertion coverage 100%", "harness_version": "0.8.16", "measured_at": "2026-09-01T07:23:12Z", "measured_at_precision": "second", "observed_at": "2026-09-01T10:53:50Z", "report": "eval_smoke_20260901_072312.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "smoke"}
{"age_at_observation_days": 0, "backfilled": false, "commit": null, "coverage": 1.0, "detail": "3/3 tasks passed, avg score 1.00, assertion coverage 100%", "harness_version": "0.8.16", "measured_at": "2026-09-02T06:54:55Z", "measured_at_precision": "second", "observed_at": "2026-09-02T06:55:11Z", "report": "eval_smoke_20260902_065455.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "smoke"}
{"age_at_observation_days": 0, "backfilled": false, "commit": null, "corpus_real_traces": 0, "coverage": null, "detail": "false-positive rate 10.42% (25/240), Wilson 95% CI [7.16%, 14.92%]; 0 trace(s) from a real agent run", "fp_ci95_high": 0.14924912020839565, "fp_ci95_low": 0.07155651754988678, "fp_ci_method": "wilson_95", "fp_flagged": 25, "fp_rate": 0.10416666666666667, "fp_total": 240, "harness_version": "0.8.17", "measured_at": "2026-09-02T00:00:00Z", "measured_at_precision": "day", "observed_at": "2026-09-02T10:10:02Z", "report": "coherence_fp-20260902.json", "result": "pass", "schema": 1, "score": 0.8958333333333334, "stale_at_observation": false, "suite": "coherence_fp"}
{"age_at_observation_days": 0, "backfilled": false, "commit": null, "coverage": 1.0, "detail": "3/3 tasks passed, avg score 1.00, assertion coverage 100%", "harness_version": "0.8.17", "measured_at": "2026-09-03T06:57:14Z", "measured_at_precision": "second", "observed_at": "2026-09-03T06:57:31Z", "report": "eval_smoke_20260903_065714.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "smoke"}
{"age_at_observation_days": 0, "backfilled": false, "commit": null, "coverage": 1.0, "detail": "3/3 tasks passed, avg score 1.00, assertion coverage 100%", "harness_version": "0.8.17", "measured_at": "2026-09-04T07:02:30Z", "measured_at_precision": "second", "observed_at": "2026-09-04T07:02:45Z", "report": "eval_smoke_20260904_070230.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "smoke"}
{"age_at_observation_days": 0, "backfilled": false, "commit": null, "coverage": 1.0, "detail": "3/3 tasks passed, avg score 1.00, assertion coverage 100%", "harness_version": "0.8.17", "measured_at": "2026-09-05T06:47:02Z", "measured_at_precision": "second", "observed_at": "2026-09-05T06:47:18Z", "report": "eval_smoke_20260905_064702.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "smoke"}
{"age_at_observation_days": 0, "backfilled": false, "commit": null, "coverage": 1.0, "detail": "3/3 tasks passed, avg score 1.00, assertion coverage 100%", "harness_version": "0.8.18", "measured_at": "2026-09-06T06:58:34Z", "measured_at_precision": "second", "observed_at": "2026-09-06T06:58:49Z", "report": "eval_smoke_20260906_065834.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "smoke"}
{"age_at_observation_days": 0, "backfilled": false, "commit": null, "coverage": null, "detail": "block 100%, benign utility 100%", "harness_version": "0.8.18", "measured_at": "2026-09-06T00:00:00Z", "measured_at_precision": "day", "observed_at": "2026-09-06T07:33:16Z", "report": "asb-20260906.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "asb"}
{"age_at_observation_days": 0, "backfilled": false, "commit": null, "corpus_real_traces": 0, "coverage": null, "detail": "false-positive rate 10.42% (25/240), Wilson 95% CI [7.16%, 14.92%]; 0 trace(s) from a real agent run", "fp_ci95_high": 0.14924912020839565, "fp_ci95_low": 0.07155651754988678, "fp_ci_method": "wilson_95", "fp_flagged": 25, "fp_rate": 0.10416666666666667, "fp_total": 240, "harness_version": "0.8.18", "measured_at": "2026-09-06T00:00:00Z", "measured_at_precision": "day", "observed_at": "2026-09-06T07:33:16Z", "report": "coherence_fp-20260906.json", "result": "pass", "schema": 1, "score": 0.8958333333333334, "stale_at_observation": false, "suite": "coherence_fp"}
{"age_at_observation_days": 0, "backfilled": false, "commit": null, "coverage": null, "detail": "governed blocked 100% vs ungoverned 0%", "harness_version": "0.8.18", "measured_at": "2026-09-06T00:00:00Z", "measured_at_precision": "day", "observed_at": "2026-09-06T07:33:16Z", "report": "governed-benchmark-20260906.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "governed-benchmark"}
{"age_at_observation_days": 0, "backfilled": false, "commit": null, "coverage": null, "detail": "block 100%, benign utility 100%", "harness_version": "0.8.18", "measured_at": "2026-09-06T00:00:00Z", "measured_at_precision": "day", "observed_at": "2026-09-06T07:33:16Z", "report": "injection_defense-20260906.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "injection_defense"}
{"age_at_observation_days": 0, "backfilled": false, "commit": null, "coverage": 1.0, "detail": "20/20 tasks passed, avg score 1.00, assertion coverage 100%", "harness_version": "0.8.18", "measured_at": "2026-09-06T07:30:37Z", "measured_at_precision": "second", "observed_at": "2026-09-06T07:33:16Z", "report": "eval_regression_20260906_073037.json", "result": "pass", "schema": 1, "score": 1.0, "stale_at_observation": false, "suite": "regression"}
{"age_at_observation_days": 0, "backfilled": false, "commit": null, "corpus_real_traces": 5, "correction_of": "2026-09-06T07:33:16Z", "coverage": null, "detail": "false-positive rate 10.20% (25/245), Wilson 95% CI [7.01%, 14.63%]; 5 trace(s) from a real agent run", "fp_ci95_high": 0.14629352621809297, "fp_ci95_low": 0.07007544102854106, "fp_ci_method": "wilson_95", "fp_flagged": 25, "fp_rate": 0.10204081632653061, "fp_total": 245, "harness_version": "0.8.19", "measured_at": "2026-09-06T00:00:00Z", "measured_at_precision": "day", "observed_at": "2026-09-06T07:33:16Z", "reason": "Re-measured on the same day at harness 0.8.19. The nightly row above was a correct measurement of the corpus as it stood (240 synthetic traces, no real arm) and stays. This release added opt-in agent-trajectory persistence and five real trajectories, so the corpus is 245 and the same report filename now holds the later measurement. The earlier row is not wrong about what it measured; it no longer describes the file it names.", "report": "coherence_fp-20260906.json", "result": "pass", "schema": 1, "score": 0.8979591836734694, "stale_at_observation": false, "suite": "coherence_fp"}
