{
  "evidence": {
    "runId": "92a2ee16-45ff-4476-8008-8355f0368c7d",
    "evaluatedAt": "2026-09-27T07:56:22.956Z",
    "packageVersion": "0.7.0",
    "recipeFingerprint": "accce497113821fcd870e3ebd3806c7cbe214d13e3a6ca96544043ab52b168b6",
    "datasetFingerprint": "4e363d02a89e1564d62e921ca3c449299d09880ec06a748f8db24a10fa3e3a16",
    "split": "held-out",
    "mode": "live",
    "policy": {
      "minConfidence": 0.8,
      "selectedOn": {
        "runId": "d6327a42-3715-4495-962c-c8e6055217fb",
        "datasetFingerprint": "82349d5da9900695fefdfcc826e15db6ec5246fdd6fcf792a65719d86b870aeb",
        "recipeFingerprint": "accce497113821fcd870e3ebd3806c7cbe214d13e3a6ca96544043ab52b168b6",
        "model": "jev-1.13.0",
        "split": "development"
      }
    },
    "provenance": [
      {
        "method": "author-synthetic",
        "source": "AI-authored synthetic boundary cases for jev-recipes; labels have not had independent human review.",
        "cases": 40
      }
    ]
  },
  "recipe": "response-needed",
  "model": "jev-1.13.0",
  "models": [
    "jev-1.13.0"
  ],
  "cases": 40,
  "completed": 40,
  "failed": 0,
  "correct": 40,
  "wrong": 0,
  "ready": 40,
  "review": 0,
  "accuracy": 1,
  "completedAccuracy": 1,
  "accuracyInterval95": [
    0.9124,
    1
  ],
  "readyAccuracy": 1,
  "readyAccuracyInterval95": [
    0.9124,
    1
  ],
  "reviewRate": 0,
  "contestedAccuracy": null,
  "adversarialAccuracy": 1,
  "calibration": [
    {
      "confidence": "0-0.5",
      "cases": 0,
      "accuracy": null
    },
    {
      "confidence": "0.5-0.6",
      "cases": 0,
      "accuracy": null
    },
    {
      "confidence": "0.6-0.7",
      "cases": 0,
      "accuracy": null
    },
    {
      "confidence": "0.7-0.8",
      "cases": 0,
      "accuracy": null
    },
    {
      "confidence": "0.8-0.9",
      "cases": 0,
      "accuracy": null
    },
    {
      "confidence": "0.9-1",
      "cases": 40,
      "accuracy": 1
    }
  ],
  "thresholdEvaluation": "frozen-policy",
  "thresholds": [],
  "suggestedMinConfidence": null,
  "latencyMs": {
    "p50": 104.27,
    "p95": 163.15,
    "totalCaseTime": 4577.13
  },
  "usage": {
    "requests": 40,
    "input_tokens": 17784,
    "output_tokens": 1740,
    "unknownResponses": 0,
    "failedRequests": 0,
    "models": [
      "jev-1.13.0"
    ]
  },
  "cost": {
    "model": "jev-1.13.0",
    "inputPerMillion": 0.042,
    "outputPerMillion": 0,
    "currency": "USD",
    "date": "2026-09-27",
    "source": "https://docs.typesafe.ai/models",
    "estimated": 0.00074693
  },
  "confusion": {
    "{\"verdict\":\"no_reply_needed\"}": {
      "total": 20,
      "correct": 20,
      "misses": {}
    },
    "{\"verdict\":\"reply_needed\"}": {
      "total": 20,
      "correct": 20,
      "misses": {}
    }
  },
  "failures": [],
  "acceptance": {
    "minConfidence": 0.8,
    "minimumHeldOutReadyCases": 20,
    "minimumReadyAccuracy": 0.95,
    "maximumProviderFailures": 0,
    "met": true,
    "label": "Measured on these synthetic cases"
  }
}
