{
  "schema_version": 1,
  "measured_at": "2026-09-17T15:56:35.891Z",
  "mode": "live",
  "split": "development",
  "model": "jev-1.13.0",
  "rubric_version": "check-proof-v1",
  "rubric_sha256": "d9550c3c29d1dfb783ad58ee7749c88ccf427d33ba755b59815a15a23e01f565",
  "corpus_sha256": "66919e117ca89fcdb2ace8ccda13641c12919625a5f16b25109d3ab2720d729a",
  "confusion_matrix": {
    "appears_supported": {
      "appears_supported": 5,
      "scope_gap": 0,
      "contradicted": 0,
      "insufficient_context": 0,
      "error": 0
    },
    "scope_gap": {
      "appears_supported": 0,
      "scope_gap": 4,
      "contradicted": 1,
      "insufficient_context": 0,
      "error": 0
    },
    "contradicted": {
      "appears_supported": 0,
      "scope_gap": 0,
      "contradicted": 5,
      "insufficient_context": 0,
      "error": 0
    },
    "insufficient_context": {
      "appears_supported": 0,
      "scope_gap": 0,
      "contradicted": 0,
      "insufficient_context": 5,
      "error": 0
    }
  },
  "false_support": 0,
  "inadequate_flagged": 10,
  "adequate_correct": 5,
  "insufficient_correct": 5,
  "errors": 0,
  "pilot_gate": "NOT_APPLICABLE",
  "latency_ms": {
    "p50": 214,
    "p95": 454
  },
  "usage": {
    "input_tokens": 14301,
    "output_tokens": 1152
  },
  "low_confidence_results": 2,
  "failures": [
    {
      "id": "dev-05",
      "expected": "scope_gap",
      "verdict": "contradicted",
      "result": {
        "advisory": true,
        "verdict": "contradicted",
        "confidence": 0.54,
        "probabilities": {
          "appears_supported": 0,
          "scope_gap": 0.34,
          "contradicted": 0.66,
          "insufficient_context": 0
        },
        "requires_review": true,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 713,
          "output_tokens": 58
        },
        "latency_ms": 212
      }
    }
  ],
  "rows": [
    {
      "id": "dev-01",
      "expected": "scope_gap",
      "verdict": "scope_gap",
      "result": {
        "advisory": true,
        "verdict": "scope_gap",
        "confidence": 0.99,
        "probabilities": {
          "appears_supported": 0,
          "scope_gap": 1,
          "contradicted": 0,
          "insufficient_context": 0
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 714,
          "output_tokens": 56
        },
        "latency_ms": 707
      }
    },
    {
      "id": "dev-02",
      "expected": "scope_gap",
      "verdict": "scope_gap",
      "result": {
        "advisory": true,
        "verdict": "scope_gap",
        "confidence": 0.97,
        "probabilities": {
          "appears_supported": 0,
          "scope_gap": 0.98,
          "contradicted": 0.02,
          "insufficient_context": 0
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 715,
          "output_tokens": 56
        },
        "latency_ms": 431
      }
    },
    {
      "id": "dev-03",
      "expected": "scope_gap",
      "verdict": "scope_gap",
      "result": {
        "advisory": true,
        "verdict": "scope_gap",
        "confidence": 0.97,
        "probabilities": {
          "appears_supported": 0,
          "scope_gap": 0.98,
          "contradicted": 0,
          "insufficient_context": 0.02
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 707,
          "output_tokens": 56
        },
        "latency_ms": 219
      }
    },
    {
      "id": "dev-04",
      "expected": "scope_gap",
      "verdict": "scope_gap",
      "result": {
        "advisory": true,
        "verdict": "scope_gap",
        "confidence": 1,
        "probabilities": {
          "appears_supported": 0,
          "scope_gap": 1,
          "contradicted": 0,
          "insufficient_context": 0
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 738,
          "output_tokens": 56
        },
        "latency_ms": 232
      }
    },
    {
      "id": "dev-05",
      "expected": "scope_gap",
      "verdict": "contradicted",
      "result": {
        "advisory": true,
        "verdict": "contradicted",
        "confidence": 0.54,
        "probabilities": {
          "appears_supported": 0,
          "scope_gap": 0.34,
          "contradicted": 0.66,
          "insufficient_context": 0
        },
        "requires_review": true,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 713,
          "output_tokens": 58
        },
        "latency_ms": 212
      }
    },
    {
      "id": "dev-06",
      "expected": "contradicted",
      "verdict": "contradicted",
      "result": {
        "advisory": true,
        "verdict": "contradicted",
        "confidence": 1,
        "probabilities": {
          "appears_supported": 0,
          "scope_gap": 0,
          "contradicted": 1,
          "insufficient_context": 0
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 706,
          "output_tokens": 58
        },
        "latency_ms": 143
      }
    },
    {
      "id": "dev-07",
      "expected": "contradicted",
      "verdict": "contradicted",
      "result": {
        "advisory": true,
        "verdict": "contradicted",
        "confidence": 1,
        "probabilities": {
          "appears_supported": 0,
          "scope_gap": 0,
          "contradicted": 1,
          "insufficient_context": 0
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 726,
          "output_tokens": 58
        },
        "latency_ms": 168
      }
    },
    {
      "id": "dev-08",
      "expected": "contradicted",
      "verdict": "contradicted",
      "result": {
        "advisory": true,
        "verdict": "contradicted",
        "confidence": 1,
        "probabilities": {
          "appears_supported": 0,
          "scope_gap": 0,
          "contradicted": 1,
          "insufficient_context": 0
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 715,
          "output_tokens": 58
        },
        "latency_ms": 226
      }
    },
    {
      "id": "dev-09",
      "expected": "contradicted",
      "verdict": "contradicted",
      "result": {
        "advisory": true,
        "verdict": "contradicted",
        "confidence": 1,
        "probabilities": {
          "appears_supported": 0,
          "scope_gap": 0,
          "contradicted": 1,
          "insufficient_context": 0
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 719,
          "output_tokens": 58
        },
        "latency_ms": 160
      }
    },
    {
      "id": "dev-10",
      "expected": "contradicted",
      "verdict": "contradicted",
      "result": {
        "advisory": true,
        "verdict": "contradicted",
        "confidence": 1,
        "probabilities": {
          "appears_supported": 0,
          "scope_gap": 0,
          "contradicted": 1,
          "insufficient_context": 0
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 714,
          "output_tokens": 58
        },
        "latency_ms": 214
      }
    },
    {
      "id": "dev-11",
      "expected": "appears_supported",
      "verdict": "appears_supported",
      "result": {
        "advisory": true,
        "verdict": "appears_supported",
        "confidence": 0.99,
        "probabilities": {
          "appears_supported": 1,
          "scope_gap": 0,
          "contradicted": 0,
          "insufficient_context": 0
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 710,
          "output_tokens": 57
        },
        "latency_ms": 167
      }
    },
    {
      "id": "dev-12",
      "expected": "appears_supported",
      "verdict": "appears_supported",
      "result": {
        "advisory": true,
        "verdict": "appears_supported",
        "confidence": 0.9,
        "probabilities": {
          "appears_supported": 0.93,
          "scope_gap": 0.06,
          "contradicted": 0,
          "insufficient_context": 0.01
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 756,
          "output_tokens": 57
        },
        "latency_ms": 254
      }
    },
    {
      "id": "dev-13",
      "expected": "appears_supported",
      "verdict": "appears_supported",
      "result": {
        "advisory": true,
        "verdict": "appears_supported",
        "confidence": 0.95,
        "probabilities": {
          "appears_supported": 0.96,
          "scope_gap": 0.03,
          "contradicted": 0,
          "insufficient_context": 0.01
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 739,
          "output_tokens": 57
        },
        "latency_ms": 244
      }
    },
    {
      "id": "dev-14",
      "expected": "appears_supported",
      "verdict": "appears_supported",
      "result": {
        "advisory": true,
        "verdict": "appears_supported",
        "confidence": 0.98,
        "probabilities": {
          "appears_supported": 0.98,
          "scope_gap": 0.01,
          "contradicted": 0,
          "insufficient_context": 0.01
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 726,
          "output_tokens": 57
        },
        "latency_ms": 454
      }
    },
    {
      "id": "dev-15",
      "expected": "appears_supported",
      "verdict": "appears_supported",
      "result": {
        "advisory": true,
        "verdict": "appears_supported",
        "confidence": 0.95,
        "probabilities": {
          "appears_supported": 0.96,
          "scope_gap": 0.03,
          "contradicted": 0,
          "insufficient_context": 0.01
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 754,
          "output_tokens": 57
        },
        "latency_ms": 393
      }
    },
    {
      "id": "dev-16",
      "expected": "insufficient_context",
      "verdict": "insufficient_context",
      "result": {
        "advisory": true,
        "verdict": "insufficient_context",
        "confidence": 0.96,
        "probabilities": {
          "appears_supported": 0,
          "scope_gap": 0.03,
          "contradicted": 0,
          "insufficient_context": 0.97
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 684,
          "output_tokens": 59
        },
        "latency_ms": 196
      }
    },
    {
      "id": "dev-17",
      "expected": "insufficient_context",
      "verdict": "insufficient_context",
      "result": {
        "advisory": true,
        "verdict": "insufficient_context",
        "confidence": 0.94,
        "probabilities": {
          "appears_supported": 0.03,
          "scope_gap": 0.01,
          "contradicted": 0.01,
          "insufficient_context": 0.95
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 686,
          "output_tokens": 59
        },
        "latency_ms": 163
      }
    },
    {
      "id": "dev-18",
      "expected": "insufficient_context",
      "verdict": "insufficient_context",
      "result": {
        "advisory": true,
        "verdict": "insufficient_context",
        "confidence": 0.99,
        "probabilities": {
          "appears_supported": 0,
          "scope_gap": 0.01,
          "contradicted": 0,
          "insufficient_context": 0.99
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 690,
          "output_tokens": 59
        },
        "latency_ms": 154
      }
    },
    {
      "id": "dev-19",
      "expected": "insufficient_context",
      "verdict": "insufficient_context",
      "result": {
        "advisory": true,
        "verdict": "insufficient_context",
        "confidence": 0.89,
        "probabilities": {
          "appears_supported": 0,
          "scope_gap": 0.08,
          "contradicted": 0,
          "insufficient_context": 0.92
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 693,
          "output_tokens": 59
        },
        "latency_ms": 261
      }
    },
    {
      "id": "dev-20",
      "expected": "insufficient_context",
      "verdict": "insufficient_context",
      "result": {
        "advisory": true,
        "verdict": "insufficient_context",
        "confidence": 0.76,
        "probabilities": {
          "appears_supported": 0,
          "scope_gap": 0.17,
          "contradicted": 0,
          "insufficient_context": 0.83
        },
        "requires_review": true,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 696,
          "output_tokens": 59
        },
        "latency_ms": 156
      }
    }
  ]
}
