{
  "campaignId": "fc-3377c49ce724",
  "cells": {
    "@cf/openai/gpt-oss-20b|vvdex.annotation.structured-data-1": {
      "certified": null,
      "certifiedCounts": {
        "certified_pass": 9,
        "invalid": 0,
        "lane_error": 0,
        "model_fail": 1,
        "withheld": 0
      },
      "evalId": "fr-20260907-811ca1e7",
      "grader": null,
      "integrity": "verified_contained",
      "withheldBy": null
    },
    "@cf/openai/gpt-oss-20b|vvdex.annotation.text-labeling-1": {
      "certified": null,
      "certifiedCounts": {
        "certified_pass": 10,
        "invalid": 0,
        "lane_error": 0,
        "model_fail": 0,
        "withheld": 0
      },
      "evalId": "fr-20260907-dad35536",
      "grader": null,
      "integrity": "verified_contained",
      "withheldBy": null
    },
    "codestral-latest|vvdex.annotation.structured-data-1": {
      "certified": null,
      "certifiedCounts": {
        "certified_pass": 9,
        "invalid": 0,
        "lane_error": 0,
        "model_fail": 1,
        "withheld": 0
      },
      "evalId": "fr-20260907-aa28bed9",
      "grader": null,
      "integrity": "verified_contained",
      "withheldBy": null
    },
    "codestral-latest|vvdex.annotation.text-labeling-1": {
      "certified": null,
      "certifiedCounts": {
        "certified_pass": 0,
        "invalid": 0,
        "lane_error": 0,
        "model_fail": 10,
        "withheld": 0
      },
      "evalId": "fr-20260907-d7a267e3",
      "grader": null,
      "integrity": "verified_contained",
      "withheldBy": null
    },
    "ministral-14b-latest|vvdex.annotation.structured-data-1": {
      "certified": null,
      "certifiedCounts": {
        "certified_pass": 8,
        "invalid": 0,
        "lane_error": 0,
        "model_fail": 2,
        "withheld": 0
      },
      "evalId": "fr-20260907-aa28bed9",
      "grader": null,
      "integrity": "verified_contained",
      "withheldBy": null
    },
    "ministral-14b-latest|vvdex.annotation.text-labeling-1": {
      "certified": null,
      "certifiedCounts": {
        "certified_pass": 0,
        "invalid": 0,
        "lane_error": 0,
        "model_fail": 10,
        "withheld": 0
      },
      "evalId": "fr-20260907-d7a267e3",
      "grader": null,
      "integrity": "verified_contained",
      "withheldBy": null
    },
    "ministral-8b-latest|vvdex.annotation.structured-data-1": {
      "certified": null,
      "certifiedCounts": {
        "certified_pass": 1,
        "invalid": 0,
        "lane_error": 0,
        "model_fail": 9,
        "withheld": 0
      },
      "evalId": "fr-20260907-aa28bed9",
      "grader": null,
      "integrity": "verified_contained",
      "withheldBy": null
    },
    "ministral-8b-latest|vvdex.annotation.text-labeling-1": {
      "certified": null,
      "certifiedCounts": {
        "certified_pass": 0,
        "invalid": 0,
        "lane_error": 0,
        "model_fail": 10,
        "withheld": 0
      },
      "evalId": "fr-20260907-d7a267e3",
      "grader": null,
      "integrity": "verified_contained",
      "withheldBy": null
    },
    "mistral-code-latest|vvdex.annotation.structured-data-1": {
      "certified": null,
      "certifiedCounts": {
        "certified_pass": 9,
        "invalid": 0,
        "lane_error": 0,
        "model_fail": 1,
        "withheld": 0
      },
      "evalId": "fr-20260907-aa28bed9",
      "grader": null,
      "integrity": "verified_contained",
      "withheldBy": null
    },
    "mistral-code-latest|vvdex.annotation.text-labeling-1": {
      "certified": null,
      "certifiedCounts": {
        "certified_pass": 0,
        "invalid": 0,
        "lane_error": 0,
        "model_fail": 10,
        "withheld": 0
      },
      "evalId": "fr-20260907-d7a267e3",
      "grader": null,
      "integrity": "verified_contained",
      "withheldBy": null
    },
    "openai/gpt-oss-120b|vvdex.annotation.structured-data-1": {
      "certified": null,
      "certifiedCounts": {
        "certified_pass": 7,
        "invalid": 0,
        "lane_error": 0,
        "model_fail": 3,
        "withheld": 0
      },
      "evalId": "fr-20260907-811ca1e7",
      "grader": null,
      "integrity": "verified_contained",
      "withheldBy": null
    },
    "openai/gpt-oss-120b|vvdex.annotation.text-labeling-1": {
      "certified": null,
      "certifiedCounts": {
        "certified_pass": 3,
        "invalid": 0,
        "lane_error": 3,
        "model_fail": 0,
        "withheld": 0
      },
      "evalId": "fr-20260907-dad35536",
      "grader": null,
      "integrity": "verified_contained",
      "withheldBy": null
    },
    "openai/gpt-oss-20b|vvdex.annotation.structured-data-1": {
      "certified": null,
      "certifiedCounts": {
        "certified_pass": 10,
        "invalid": 0,
        "lane_error": 0,
        "model_fail": 0,
        "withheld": 0
      },
      "evalId": "fr-20260907-811ca1e7",
      "grader": null,
      "integrity": "verified_contained",
      "withheldBy": null
    },
    "openai/gpt-oss-20b|vvdex.annotation.text-labeling-1": {
      "certified": null,
      "certifiedCounts": {
        "certified_pass": 1,
        "invalid": 0,
        "lane_error": 9,
        "model_fail": 0,
        "withheld": 0
      },
      "evalId": "fr-20260907-dad35536",
      "grader": null,
      "integrity": "verified_contained",
      "withheldBy": null
    }
  },
  "certificationReceipts": {},
  "counts": {
    "campaignId": "fc-3377c49ce724",
    "cells": 14,
    "certifiedPasses": 67,
    "lanes": {
      "@cf/openai/gpt-oss-20b": {
        "certified_pass": 19,
        "invalid": 0,
        "lane_error": 0,
        "model_fail": 1,
        "withheld": 0
      },
      "codestral-latest": {
        "certified_pass": 9,
        "invalid": 0,
        "lane_error": 0,
        "model_fail": 11,
        "withheld": 0
      },
      "ministral-14b-latest": {
        "certified_pass": 8,
        "invalid": 0,
        "lane_error": 0,
        "model_fail": 12,
        "withheld": 0
      },
      "ministral-8b-latest": {
        "certified_pass": 1,
        "invalid": 0,
        "lane_error": 0,
        "model_fail": 19,
        "withheld": 0
      },
      "mistral-code-latest": {
        "certified_pass": 9,
        "invalid": 0,
        "lane_error": 0,
        "model_fail": 11,
        "withheld": 0
      },
      "openai/gpt-oss-120b": {
        "certified_pass": 10,
        "invalid": 0,
        "lane_error": 3,
        "model_fail": 3,
        "withheld": 0
      },
      "openai/gpt-oss-20b": {
        "certified_pass": 11,
        "invalid": 0,
        "lane_error": 9,
        "model_fail": 0,
        "withheld": 0
      }
    },
    "recordCount": 4,
    "recordDigests": [
      "50cbe9a820d64927b58510039c580bbed3bd161565d085363f841eb867181fab",
      "7286bf674cfcf3482e06f76daaf1f68a1db1cbf89725833b7c3eb0f9f76e8009",
      "b5bf2458f67d7fef214fedfc66497d235bb436dfd5ca1a13080b1eb7f14e00dd",
      "d98a068bbbb888bb6215a3e1a72a7d079fc043fd8b98f52d14be0a58303da22e"
    ],
    "refused": 0,
    "suspectRecords": [
      "vvdex.annotation.text-labeling-1"
    ],
    "withheldByHarness": 0
  },
  "disclosure": {
    "vvdex.annotation.structured-data-1": {
      "class": "answer_key",
      "rule": "answer-key disclosure (ownership vvdex_proprietary \u2014 no declaration \u2014 proprietary by default; family annotation): the exam is VVDex evaluation IP and the graded output is an answer or a keyed value, so no submission content, diff, model claim or hidden-assertion name is published."
    },
    "vvdex.annotation.text-labeling-1": {
      "class": "answer_key",
      "rule": "answer-key disclosure (ownership vvdex_proprietary \u2014 no declaration \u2014 proprietary by default; family annotation): the exam is VVDex evaluation IP and the graded output is an answer or a keyed value, so no submission content, diff, model claim or hidden-assertion name is published."
    }
  },
  "lanes": [
    {
      "certifiedPasses": 19,
      "countable": 20,
      "counts": {
        "certified_pass": 19,
        "invalid": 0,
        "lane_error": 0,
        "model_fail": 1,
        "withheld": 0
      },
      "lane": "@cf/openai/gpt-oss-20b",
      "rate": 0.95,
      "rateInterval95": [
        0.7639,
        0.9911
      ]
    },
    {
      "certifiedPasses": 11,
      "countable": 11,
      "counts": {
        "certified_pass": 11,
        "invalid": 0,
        "lane_error": 9,
        "model_fail": 0,
        "withheld": 0
      },
      "lane": "openai/gpt-oss-20b",
      "rate": 1.0,
      "rateInterval95": [
        0.7412,
        1.0
      ]
    },
    {
      "certifiedPasses": 10,
      "countable": 13,
      "counts": {
        "certified_pass": 10,
        "invalid": 0,
        "lane_error": 3,
        "model_fail": 3,
        "withheld": 0
      },
      "lane": "openai/gpt-oss-120b",
      "rate": 0.7692307692307693,
      "rateInterval95": [
        0.4974,
        0.9182
      ]
    },
    {
      "certifiedPasses": 9,
      "countable": 20,
      "counts": {
        "certified_pass": 9,
        "invalid": 0,
        "lane_error": 0,
        "model_fail": 11,
        "withheld": 0
      },
      "lane": "codestral-latest",
      "rate": 0.45,
      "rateInterval95": [
        0.2582,
        0.6579
      ]
    },
    {
      "certifiedPasses": 9,
      "countable": 20,
      "counts": {
        "certified_pass": 9,
        "invalid": 0,
        "lane_error": 0,
        "model_fail": 11,
        "withheld": 0
      },
      "lane": "mistral-code-latest",
      "rate": 0.45,
      "rateInterval95": [
        0.2582,
        0.6579
      ]
    },
    {
      "certifiedPasses": 8,
      "countable": 20,
      "counts": {
        "certified_pass": 8,
        "invalid": 0,
        "lane_error": 0,
        "model_fail": 12,
        "withheld": 0
      },
      "lane": "ministral-14b-latest",
      "rate": 0.4,
      "rateInterval95": [
        0.2188,
        0.6134
      ]
    },
    {
      "certifiedPasses": 1,
      "countable": 20,
      "counts": {
        "certified_pass": 1,
        "invalid": 0,
        "lane_error": 0,
        "model_fail": 19,
        "withheld": 0
      },
      "lane": "ministral-8b-latest",
      "rate": 0.05,
      "rateInterval95": [
        0.0089,
        0.2361
      ]
    }
  ],
  "refused": [],
  "retired_for_future_evaluation": {},
  "reviews": {
    "vvdex.annotation.structured-data-1": {
      "classification": [],
      "law": "a suspect examiner may not blame the model: verdict-bearing suspicion not cleared by in-record evidence withholds every model_fail in the run",
      "suspect": false,
      "withheld": [],
      "withheldCount": 0
    },
    "vvdex.annotation.text-labeling-1": {
      "classification": [
        {
          "class": "diagnostic",
          "rationale": "an API failure is a per-rollout lane event, already recorded on that rollout as lane_error; it cannot alter another rollout's grading. It lowers coverage, not verdicts.",
          "reason": "R1 api-failure share 12/26 \u2014 most rollouts never got a working completion",
          "rule": "R1"
        }
      ],
      "law": "a suspect examiner may not blame the model: verdict-bearing suspicion not cleared by in-record evidence withholds every model_fail in the run",
      "suspect": true,
      "withheld": [],
      "withheldCount": 0
    }
  },
  "schema": "vvdex.forge.campaign-counts/v1"
}