{
  "schema_version": 1,
  "measured_at": "2026-09-17T15:57:03.184Z",
  "mode": "live",
  "split": "holdout",
  "model": "jev-1.13.0",
  "rubric_version": "check-proof-v1",
  "rubric_sha256": "d9550c3c29d1dfb783ad58ee7749c88ccf427d33ba755b59815a15a23e01f565",
  "corpus_sha256": "66919e117ca89fcdb2ace8ccda13641c12919625a5f16b25109d3ab2720d729a",
  "confusion_matrix": {
    "appears_supported": {
      "appears_supported": 10,
      "scope_gap": 0,
      "contradicted": 0,
      "insufficient_context": 0,
      "error": 0
    },
    "scope_gap": {
      "appears_supported": 0,
      "scope_gap": 10,
      "contradicted": 0,
      "insufficient_context": 0,
      "error": 0
    },
    "contradicted": {
      "appears_supported": 0,
      "scope_gap": 0,
      "contradicted": 10,
      "insufficient_context": 0,
      "error": 0
    },
    "insufficient_context": {
      "appears_supported": 0,
      "scope_gap": 0,
      "contradicted": 0,
      "insufficient_context": 10,
      "error": 0
    }
  },
  "false_support": 0,
  "inadequate_flagged": 20,
  "adequate_correct": 10,
  "insufficient_correct": 10,
  "errors": 0,
  "pilot_gate": "PASS",
  "latency_ms": {
    "p50": 178,
    "p95": 347
  },
  "usage": {
    "input_tokens": 28656,
    "output_tokens": 2300
  },
  "low_confidence_results": 5,
  "failures": [],
  "rows": [
    {
      "id": "holdout-01",
      "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": 710,
          "output_tokens": 56
        },
        "latency_ms": 396
      }
    },
    {
      "id": "holdout-02",
      "expected": "scope_gap",
      "verdict": "scope_gap",
      "result": {
        "advisory": true,
        "verdict": "scope_gap",
        "confidence": 0.97,
        "probabilities": {
          "appears_supported": 0,
          "scope_gap": 0.99,
          "contradicted": 0,
          "insufficient_context": 0.01
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 710,
          "output_tokens": 56
        },
        "latency_ms": 317
      }
    },
    {
      "id": "holdout-03",
      "expected": "scope_gap",
      "verdict": "scope_gap",
      "result": {
        "advisory": true,
        "verdict": "scope_gap",
        "confidence": 0.9,
        "probabilities": {
          "appears_supported": 0,
          "scope_gap": 0.92,
          "contradicted": 0.07,
          "insufficient_context": 0.01
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 704,
          "output_tokens": 56
        },
        "latency_ms": 171
      }
    },
    {
      "id": "holdout-04",
      "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": 707,
          "output_tokens": 56
        },
        "latency_ms": 175
      }
    },
    {
      "id": "holdout-05",
      "expected": "scope_gap",
      "verdict": "scope_gap",
      "result": {
        "advisory": true,
        "verdict": "scope_gap",
        "confidence": 0.99,
        "probabilities": {
          "appears_supported": 0,
          "scope_gap": 0.99,
          "contradicted": 0.01,
          "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": 155
      }
    },
    {
      "id": "holdout-06",
      "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": 718,
          "output_tokens": 56
        },
        "latency_ms": 138
      }
    },
    {
      "id": "holdout-07",
      "expected": "scope_gap",
      "verdict": "scope_gap",
      "result": {
        "advisory": true,
        "verdict": "scope_gap",
        "confidence": 0.94,
        "probabilities": {
          "appears_supported": 0.01,
          "scope_gap": 0.96,
          "contradicted": 0,
          "insufficient_context": 0.03
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 716,
          "output_tokens": 56
        },
        "latency_ms": 149
      }
    },
    {
      "id": "holdout-08",
      "expected": "scope_gap",
      "verdict": "scope_gap",
      "result": {
        "advisory": true,
        "verdict": "scope_gap",
        "confidence": 0.95,
        "probabilities": {
          "appears_supported": 0,
          "scope_gap": 0.96,
          "contradicted": 0.04,
          "insufficient_context": 0
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 717,
          "output_tokens": 56
        },
        "latency_ms": 144
      }
    },
    {
      "id": "holdout-09",
      "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": 713,
          "output_tokens": 56
        },
        "latency_ms": 159
      }
    },
    {
      "id": "holdout-10",
      "expected": "scope_gap",
      "verdict": "scope_gap",
      "result": {
        "advisory": true,
        "verdict": "scope_gap",
        "confidence": 0.95,
        "probabilities": {
          "appears_supported": 0,
          "scope_gap": 0.96,
          "contradicted": 0.04,
          "insufficient_context": 0
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 708,
          "output_tokens": 56
        },
        "latency_ms": 152
      }
    },
    {
      "id": "holdout-11",
      "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": 712,
          "output_tokens": 58
        },
        "latency_ms": 155
      }
    },
    {
      "id": "holdout-12",
      "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": 718,
          "output_tokens": 58
        },
        "latency_ms": 151
      }
    },
    {
      "id": "holdout-13",
      "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": 716,
          "output_tokens": 58
        },
        "latency_ms": 148
      }
    },
    {
      "id": "holdout-14",
      "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": 144
      }
    },
    {
      "id": "holdout-15",
      "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": 236
      }
    },
    {
      "id": "holdout-16",
      "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": 717,
          "output_tokens": 58
        },
        "latency_ms": 145
      }
    },
    {
      "id": "holdout-17",
      "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": 716,
          "output_tokens": 58
        },
        "latency_ms": 310
      }
    },
    {
      "id": "holdout-18",
      "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": 720,
          "output_tokens": 58
        },
        "latency_ms": 347
      }
    },
    {
      "id": "holdout-19",
      "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": 707,
          "output_tokens": 58
        },
        "latency_ms": 155
      }
    },
    {
      "id": "holdout-20",
      "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": 721,
          "output_tokens": 58
        },
        "latency_ms": 143
      }
    },
    {
      "id": "holdout-21",
      "expected": "appears_supported",
      "verdict": "appears_supported",
      "result": {
        "advisory": true,
        "verdict": "appears_supported",
        "confidence": 0.84,
        "probabilities": {
          "appears_supported": 0.88,
          "scope_gap": 0.06,
          "contradicted": 0,
          "insufficient_context": 0.06
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 734,
          "output_tokens": 57
        },
        "latency_ms": 178
      }
    },
    {
      "id": "holdout-22",
      "expected": "appears_supported",
      "verdict": "appears_supported",
      "result": {
        "advisory": true,
        "verdict": "appears_supported",
        "confidence": 0.97,
        "probabilities": {
          "appears_supported": 0.98,
          "scope_gap": 0.02,
          "contradicted": 0,
          "insufficient_context": 0
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 748,
          "output_tokens": 57
        },
        "latency_ms": 180
      }
    },
    {
      "id": "holdout-23",
      "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": 729,
          "output_tokens": 57
        },
        "latency_ms": 170
      }
    },
    {
      "id": "holdout-24",
      "expected": "appears_supported",
      "verdict": "appears_supported",
      "result": {
        "advisory": true,
        "verdict": "appears_supported",
        "confidence": 0.94,
        "probabilities": {
          "appears_supported": 0.95,
          "scope_gap": 0.04,
          "contradicted": 0,
          "insufficient_context": 0.01
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 740,
          "output_tokens": 57
        },
        "latency_ms": 158
      }
    },
    {
      "id": "holdout-25",
      "expected": "appears_supported",
      "verdict": "appears_supported",
      "result": {
        "advisory": true,
        "verdict": "appears_supported",
        "confidence": 0.96,
        "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": 764,
          "output_tokens": 57
        },
        "latency_ms": 189
      }
    },
    {
      "id": "holdout-26",
      "expected": "appears_supported",
      "verdict": "appears_supported",
      "result": {
        "advisory": true,
        "verdict": "appears_supported",
        "confidence": 0.94,
        "probabilities": {
          "appears_supported": 0.96,
          "scope_gap": 0.04,
          "contradicted": 0,
          "insufficient_context": 0
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 735,
          "output_tokens": 57
        },
        "latency_ms": 502
      }
    },
    {
      "id": "holdout-27",
      "expected": "appears_supported",
      "verdict": "appears_supported",
      "result": {
        "advisory": true,
        "verdict": "appears_supported",
        "confidence": 0.98,
        "probabilities": {
          "appears_supported": 0.99,
          "scope_gap": 0.01,
          "contradicted": 0,
          "insufficient_context": 0
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 736,
          "output_tokens": 57
        },
        "latency_ms": 188
      }
    },
    {
      "id": "holdout-28",
      "expected": "appears_supported",
      "verdict": "appears_supported",
      "result": {
        "advisory": true,
        "verdict": "appears_supported",
        "confidence": 0.62,
        "probabilities": {
          "appears_supported": 0.72,
          "scope_gap": 0.08,
          "contradicted": 0.15,
          "insufficient_context": 0.05
        },
        "requires_review": true,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 732,
          "output_tokens": 57
        },
        "latency_ms": 219
      }
    },
    {
      "id": "holdout-29",
      "expected": "appears_supported",
      "verdict": "appears_supported",
      "result": {
        "advisory": true,
        "verdict": "appears_supported",
        "confidence": 0.94,
        "probabilities": {
          "appears_supported": 0.95,
          "scope_gap": 0.04,
          "contradicted": 0,
          "insufficient_context": 0.01
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 733,
          "output_tokens": 57
        },
        "latency_ms": 145
      }
    },
    {
      "id": "holdout-30",
      "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": 724,
          "output_tokens": 57
        },
        "latency_ms": 260
      }
    },
    {
      "id": "holdout-31",
      "expected": "insufficient_context",
      "verdict": "insufficient_context",
      "result": {
        "advisory": true,
        "verdict": "insufficient_context",
        "confidence": 0.98,
        "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": 689,
          "output_tokens": 59
        },
        "latency_ms": 198
      }
    },
    {
      "id": "holdout-32",
      "expected": "insufficient_context",
      "verdict": "insufficient_context",
      "result": {
        "advisory": true,
        "verdict": "insufficient_context",
        "confidence": 1,
        "probabilities": {
          "appears_supported": 0,
          "scope_gap": 0,
          "contradicted": 0,
          "insufficient_context": 1
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 681,
          "output_tokens": 59
        },
        "latency_ms": 256
      }
    },
    {
      "id": "holdout-33",
      "expected": "insufficient_context",
      "verdict": "insufficient_context",
      "result": {
        "advisory": true,
        "verdict": "insufficient_context",
        "confidence": 1,
        "probabilities": {
          "appears_supported": 0,
          "scope_gap": 0,
          "contradicted": 0,
          "insufficient_context": 1
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 708,
          "output_tokens": 59
        },
        "latency_ms": 178
      }
    },
    {
      "id": "holdout-34",
      "expected": "insufficient_context",
      "verdict": "insufficient_context",
      "result": {
        "advisory": true,
        "verdict": "insufficient_context",
        "confidence": 0.7,
        "probabilities": {
          "appears_supported": 0.01,
          "scope_gap": 0.22,
          "contradicted": 0,
          "insufficient_context": 0.77
        },
        "requires_review": true,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 695,
          "output_tokens": 59
        },
        "latency_ms": 220
      }
    },
    {
      "id": "holdout-35",
      "expected": "insufficient_context",
      "verdict": "insufficient_context",
      "result": {
        "advisory": true,
        "verdict": "insufficient_context",
        "confidence": 0.38,
        "probabilities": {
          "appears_supported": 0,
          "scope_gap": 0.46,
          "contradicted": 0.01,
          "insufficient_context": 0.53
        },
        "requires_review": true,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 695,
          "output_tokens": 59
        },
        "latency_ms": 232
      }
    },
    {
      "id": "holdout-36",
      "expected": "insufficient_context",
      "verdict": "insufficient_context",
      "result": {
        "advisory": true,
        "verdict": "insufficient_context",
        "confidence": 0.68,
        "probabilities": {
          "appears_supported": 0.12,
          "scope_gap": 0.12,
          "contradicted": 0,
          "insufficient_context": 0.76
        },
        "requires_review": true,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 697,
          "output_tokens": 59
        },
        "latency_ms": 201
      }
    },
    {
      "id": "holdout-37",
      "expected": "insufficient_context",
      "verdict": "insufficient_context",
      "result": {
        "advisory": true,
        "verdict": "insufficient_context",
        "confidence": 0.73,
        "probabilities": {
          "appears_supported": 0,
          "scope_gap": 0.12,
          "contradicted": 0.07,
          "insufficient_context": 0.81
        },
        "requires_review": true,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 697,
          "output_tokens": 59
        },
        "latency_ms": 129
      }
    },
    {
      "id": "holdout-38",
      "expected": "insufficient_context",
      "verdict": "insufficient_context",
      "result": {
        "advisory": true,
        "verdict": "insufficient_context",
        "confidence": 0.85,
        "probabilities": {
          "appears_supported": 0,
          "scope_gap": 0.11,
          "contradicted": 0,
          "insufficient_context": 0.89
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 706,
          "output_tokens": 59
        },
        "latency_ms": 179
      }
    },
    {
      "id": "holdout-39",
      "expected": "insufficient_context",
      "verdict": "insufficient_context",
      "result": {
        "advisory": true,
        "verdict": "insufficient_context",
        "confidence": 0.92,
        "probabilities": {
          "appears_supported": 0.01,
          "scope_gap": 0.06,
          "contradicted": 0,
          "insufficient_context": 0.9299999999999999
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 705,
          "output_tokens": 59
        },
        "latency_ms": 194
      }
    },
    {
      "id": "holdout-40",
      "expected": "insufficient_context",
      "verdict": "insufficient_context",
      "result": {
        "advisory": true,
        "verdict": "insufficient_context",
        "confidence": 1,
        "probabilities": {
          "appears_supported": 0,
          "scope_gap": 0,
          "contradicted": 0,
          "insufficient_context": 1
        },
        "requires_review": false,
        "model": "jev-1.13.0",
        "rubric_version": "check-proof-v1",
        "usage": {
          "input_tokens": 706,
          "output_tokens": 59
        },
        "latency_ms": 195
      }
    }
  ]
}
