{
  "ok": true,
  "database": "actual dev PostgreSQL via runtime app role",
  "fixture_cohort": "g6-repo-benchmark-v1",
  "benchmark_schema_version": "vignette.supervision-research-benchmark.v1",
  "benchmark_version": "1.0.0",
  "benchmark_content_sha256": "9b63e9e0647714116e07545fed67f9dec278822878ac742aaa129a0fc7898f64",
  "first_append": {
    "idempotent_replay": false,
    "drift_report_id": "c05c75f6-0fd7-5a60-9140-416d83824516",
    "status": "drift_flagged",
    "counts": {
      "batches": 2,
      "reports": 1,
      "subgroup_metrics": 2
    }
  },
  "replay": {
    "idempotent_replay": true,
    "counts": {
      "batches": 2,
      "reports": 1,
      "subgroup_metrics": 2
    },
    "duplicate_rows": 0
  },
  "periodic_cycle_replay": {
    "cohort_count": 6,
    "completed": 6,
    "failed": 0,
    "version_comparison_failed": 0,
    "status": "drift_flagged",
    "idempotent_replay": true
  },
  "hydrated": {
    "status": "drift_flagged",
    "baseline_model": "evaluator-v1",
    "candidate_model": "evaluator-v2",
    "baseline_prompt_version": "1.0.0",
    "candidate_prompt_version": "2.0.0",
    "instrument_id": "rupture-eval",
    "baseline_instrument_version": "1.0.0",
    "candidate_instrument_version": "1.1.0",
    "subgroup_metrics": [
      {
        "subgroup": "synthetic-a",
        "matched_count": 3,
        "baseline_accuracy": 1.0,
        "candidate_accuracy": 1.0,
        "accuracy_delta": 0.0
      },
      {
        "subgroup": "synthetic-b",
        "matched_count": 3,
        "baseline_accuracy": 1.0,
        "candidate_accuracy": 0.3333333333333333,
        "accuracy_delta": -0.6666666666666667
      }
    ]
  },
  "data_classification": "synthetic_educational",
  "raw_transcript_included": false,
  "clinical_claim_allowed": false
}