{
  "run_id": "2026-10-08-core-greedy-nothink-3f4f20",
  "suite": "decision-conformance",
  "tier": "core",
  "suite_hash": "554e796a858218e48bcb83da003554769782a4a32d3e061da87510d7f9cea490",
  "subject": "clef-flash/hf-fde727a/mlx-q8-mlx-community/clef-mlx-mlx0.32.3-mlxvlm0.7.4",
  "mode": "native",
  "profile": "greedy-nothink",
  "status": "complete",
  "label": null,
  "items": {
    "planned": 17,
    "attempted": 17,
    "succeeded": 17,
    "failed": 0,
    "failed_by_status": {}
  },
  "metrics": {
    "checks": {
      "invariants": {
        "passed": 33,
        "total": 33,
        "failures": []
      },
      "batched_vs_separate": {
        "passed": 4,
        "total": 6,
        "failures": [
          "support/team: differs by 0.0769",
          "support/needs_human: differs by 0.0644"
        ],
        "max_abs_diff": 0.0769
      },
      "repeat_stability": {
        "passed": 6,
        "total": 6,
        "failures": [],
        "max_std": 0
      },
      "option_order": {
        "passed": 2,
        "total": 2,
        "failures": [],
        "max_confidence_delta": 0
      },
      "monotonic": {
        "passed": 2,
        "total": 2,
        "failures": [],
        "expected_scores": [
          0.9175,
          1.2438,
          2.8957
        ]
      }
    },
    "passed": 47,
    "total": 49
  },
  "latency_ms": {
    "p50": 1619.000041,
    "p95": 6759.752708,
    "p99": 6759.752708,
    "note": "successful requests, nearest rank, measured from America/Chicago"
  },
  "usage": {
    "input_tokens": 5562,
    "output_tokens": 0,
    "cost_usd": 0
  }
}