{ "version": 1, "entries": [ { "provider": "openai-codex", "model": "gpt-5.6-sol", "api": "openai-codex-responses", "status": "recommended", "promptVersion": "bash-shadow-v4", "corpusVersion": "2026-08-21.2", "testedAt": "2026-08-21T15:00:47.219Z", "corpusCases": 21, "matched": 21, "infrastructureFailures": 0, "latencyMs": { "p50": 5823, "p95": 10396, "max": 10396 }, "reportPath": "reports/corpus-replay-gpt-5.6-sol-20260821-03.json", "notes": "30000ms timeout cohort. Advisory compatibility data, not a safety certification (ADR 0008). Corpus 2026-08-21.2 revised unclear-forward defer→deny after two conservative deny runs (owner-endorsed); pre-revision runs -01 (20/21) and -02 (19/21) retained in reports/." }, { "provider": "deepseek", "model": "deepseek-v4-flash", "api": "openai-completions", "status": "recommended", "promptVersion": "bash-shadow-v4", "corpusVersion": "2026-08-21.2", "testedAt": "2026-08-21T15:28:39.815Z", "corpusCases": 21, "matched": 21, "infrastructureFailures": 0, "latencyMs": { "p50": 1448, "p95": 1682, "max": 2146 }, "reportPath": "reports/corpus-replay-deepseek-v4-flash-20260821-02.json", "notes": "30000ms timeout cohort. Advisory compatibility data, not a safety certification (ADR 0008). Run -01 (20/21, covered-compound judged defer) retained in reports/: single non-repeating sampling miss, matched in run -02, not treated as systematic. Flash-tier latency (p50 ~1.4s vs gpt-5.6-sol ~5.8s)." } ] }