{
 "schemaVersion": 1,
 "generatedAt": "2026-11-11T21:02:16Z",
 "repo": {
  "display": "Humanizer",
  "site": "https://github.com/Humanizr/Humanizer",
  "language": "csharp",
  "url": "https://github.com/Humanizr/Humanizer",
  "visibility": "public"
 },
 "method": {
  "oneTry": false,
  "reproduceFirst": false,
  "hiddenTests": true,
  "weightRule": null,
  "totalPoints": null,
  "trialsPerBug": 3
 },
 "models": [
  {
   "id": "claude-haiku-5-5",
   "display": "Claude Haiku 5.5",
   "effort": null,
   "vendor": "anthropic",
   "colour": "#ff8f66"
  },
  {
   "id": "gpt-6-luna",
   "display": "GPT-6 Luna",
   "effort": null,
   "vendor": "openai",
   "colour": "#5cc8ff"
  }
 ],
 "videos": [
  {
   "id": "humanizer",
   "title": "Humanizer: 5 real bugs",
   "youtubeId": null,
   "publishedDate": "2026-11-11",
   "benchmarkId": "85ac6ffa3955",
   "contenders": [
    "claude-haiku-5-5",
    "gpt-6-luna"
   ],
   "bonus": [],
   "pricingBasis": null,
   "totals": {
    "claude-haiku-5-5": {
     "fixed": 3,
     "attempted": 5,
     "points": null,
     "maxPoints": null,
     "costUSD": null,
     "timeSeconds": 1768.6,
     "tokens": null,
     "statistics": {
      "bugCount": 5,
      "trialsPerBug": 3,
      "trialCount": 15,
      "resolveRate": {
       "mean": 0.6,
       "low": 0.2,
       "high": 1
      },
      "passAtK": [
       {
        "k": 1,
        "value": 0.6
       },
       {
        "k": 2,
        "value": 0.6
       },
       {
        "k": 3,
        "value": 0.6
       }
      ],
      "firstTryRate": 0.5333,
      "feedbackGain": 0.0667,
      "confidence": 0.95,
      "bootstrapSamples": 2000,
      "seed": 166
     }
    },
    "gpt-6-luna": {
     "fixed": 3,
     "attempted": 5,
     "points": null,
     "maxPoints": null,
     "costUSD": null,
     "timeSeconds": 922.2,
     "tokens": null,
     "statistics": {
      "bugCount": 5,
      "trialsPerBug": 3,
      "trialCount": 15,
      "resolveRate": {
       "mean": 0.5333,
       "low": 0.1333,
       "high": 0.9333
      },
      "passAtK": [
       {
        "k": 1,
        "value": 0.5333
       },
       {
        "k": 2,
        "value": 0.6
       },
       {
        "k": 3,
        "value": 0.6
       }
      ],
      "firstTryRate": 0.5333,
      "feedbackGain": 0,
      "confidence": 0.95,
      "bootstrapSamples": 2000,
      "seed": 166
     }
    }
   }
  }
 ],
 "bugs": [
  {
   "scenarioId": "142664ee5a9a",
   "videoIds": [
    "humanizer"
   ],
   "title": "fix(truncation): treat any whitespace as a word boundary (#1969)",
   "plainTitle": null,
   "explanation": null,
   "points": null,
   "linesChanged": null,
   "inCommonBoard": true,
   "buggyCommit": "66e5c56dfbc6936e1e331074f8fea75a1516e3fb",
   "fixCommit": "755626ef365947f55d720e819d3cca905553c03b",
   "benchmarkId": "85ac6ffa3955",
   "links": {
    "dataset": {
     "task": "Humanizr__Humanizer__142664ee5a9a",
     "path": "harbor/Humanizr__Humanizer__142664ee5a9a"
    },
    "video": null,
    "replays": {
     "claude-haiku-5-5": [
      "replays/humanizer/claude-haiku-5-5/142664ee5a9a.json",
      "replays/humanizer/claude-haiku-5-5/142664ee5a9a.t2.json",
      "replays/humanizer/claude-haiku-5-5/142664ee5a9a.t3.json"
     ],
     "gpt-6-luna": [
      "replays/humanizer/gpt-6-luna/142664ee5a9a.json",
      "replays/humanizer/gpt-6-luna/142664ee5a9a.t2.json",
      "replays/humanizer/gpt-6-luna/142664ee5a9a.t3.json"
     ]
    }
   }
  },
  {
   "scenarioId": "63f500c69cf8",
   "videoIds": [
    "humanizer"
   ],
   "title": "Add Bits(double) extension for fractional bit values (#1953)",
   "plainTitle": null,
   "explanation": null,
   "points": null,
   "linesChanged": null,
   "inCommonBoard": true,
   "buggyCommit": "3e06e140a6adec85f650a90abafe11f960d9a5b2",
   "fixCommit": "66e5c56dfbc6936e1e331074f8fea75a1516e3fb",
   "benchmarkId": "85ac6ffa3955",
   "links": {
    "dataset": {
     "task": "Humanizr__Humanizer__63f500c69cf8",
     "path": "harbor/Humanizr__Humanizer__63f500c69cf8"
    },
    "video": null,
    "replays": {
     "claude-haiku-5-5": [
      "replays/humanizer/claude-haiku-5-5/63f500c69cf8.json",
      "replays/humanizer/claude-haiku-5-5/63f500c69cf8.t2.json",
      "replays/humanizer/claude-haiku-5-5/63f500c69cf8.t3.json"
     ],
     "gpt-6-luna": [
      "replays/humanizer/gpt-6-luna/63f500c69cf8.json",
      "replays/humanizer/gpt-6-luna/63f500c69cf8.t2.json",
      "replays/humanizer/gpt-6-luna/63f500c69cf8.t3.json"
     ]
    }
   }
  },
  {
   "scenarioId": "65c7a56b1fd7",
   "videoIds": [
    "humanizer"
   ],
   "title": "fix(vocabularies): fix various English plurals (#1968)",
   "plainTitle": null,
   "explanation": null,
   "points": null,
   "linesChanged": null,
   "inCommonBoard": true,
   "buggyCommit": "55e4dda167bf9d4464a6a8e9463b027b2766b258",
   "fixCommit": "3e06e140a6adec85f650a90abafe11f960d9a5b2",
   "benchmarkId": "85ac6ffa3955",
   "links": {
    "dataset": {
     "task": "Humanizr__Humanizer__65c7a56b1fd7",
     "path": "harbor/Humanizr__Humanizer__65c7a56b1fd7"
    },
    "video": null,
    "replays": {
     "claude-haiku-5-5": [
      "replays/humanizer/claude-haiku-5-5/65c7a56b1fd7.json",
      "replays/humanizer/claude-haiku-5-5/65c7a56b1fd7.t2.json",
      "replays/humanizer/claude-haiku-5-5/65c7a56b1fd7.t3.json"
     ],
     "gpt-6-luna": [
      "replays/humanizer/gpt-6-luna/65c7a56b1fd7.json",
      "replays/humanizer/gpt-6-luna/65c7a56b1fd7.t2.json",
      "replays/humanizer/gpt-6-luna/65c7a56b1fd7.t3.json"
     ]
    }
   }
  },
  {
   "scenarioId": "f4ade1576bcb",
   "videoIds": [
    "humanizer"
   ],
   "title": "Fix Portuguese locale: correct milhar cardinal value and milissegundo spelling (#1967)",
   "plainTitle": null,
   "explanation": null,
   "points": null,
   "linesChanged": null,
   "inCommonBoard": true,
   "buggyCommit": "e7f110fa150f695fa45cf40053f388aa568b21bd",
   "fixCommit": "bdbf717a2a3a853b0f8ed2513038f7e4892ae171",
   "benchmarkId": "85ac6ffa3955",
   "links": {
    "dataset": {
     "task": "Humanizr__Humanizer__f4ade1576bcb",
     "path": "harbor/Humanizr__Humanizer__f4ade1576bcb"
    },
    "video": null,
    "replays": {
     "claude-haiku-5-5": [
      "replays/humanizer/claude-haiku-5-5/f4ade1576bcb.json",
      "replays/humanizer/claude-haiku-5-5/f4ade1576bcb.t2.json",
      "replays/humanizer/claude-haiku-5-5/f4ade1576bcb.t3.json"
     ],
     "gpt-6-luna": [
      "replays/humanizer/gpt-6-luna/f4ade1576bcb.json",
      "replays/humanizer/gpt-6-luna/f4ade1576bcb.t2.json",
      "replays/humanizer/gpt-6-luna/f4ade1576bcb.t3.json"
     ]
    }
   }
  },
  {
   "scenarioId": "77e7fd8f1c1b",
   "videoIds": [
    "humanizer"
   ],
   "title": "fix(security): bound suffix-scale parsing",
   "plainTitle": null,
   "explanation": null,
   "points": null,
   "linesChanged": null,
   "inCommonBoard": true,
   "buggyCommit": "bd6df6130e15c980103f2ea2c9a69ad97013a467",
   "fixCommit": "c0d671d3e7294dd2dc2c1073bc58af0df96a53f7",
   "benchmarkId": "85ac6ffa3955",
   "links": {
    "dataset": {
     "task": "Humanizr__Humanizer__77e7fd8f1c1b",
     "path": "harbor/Humanizr__Humanizer__77e7fd8f1c1b"
    },
    "video": null,
    "replays": {
     "claude-haiku-5-5": [
      "replays/humanizer/claude-haiku-5-5/77e7fd8f1c1b.json",
      "replays/humanizer/claude-haiku-5-5/77e7fd8f1c1b.t2.json",
      "replays/humanizer/claude-haiku-5-5/77e7fd8f1c1b.t3.json"
     ],
     "gpt-6-luna": [
      "replays/humanizer/gpt-6-luna/77e7fd8f1c1b.json",
      "replays/humanizer/gpt-6-luna/77e7fd8f1c1b.t2.json",
      "replays/humanizer/gpt-6-luna/77e7fd8f1c1b.t3.json"
     ]
    }
   }
  }
 ],
 "runs": [
  {
   "videoId": "humanizer",
   "modelId": "claude-haiku-5-5",
   "scenarioId": "142664ee5a9a",
   "passed": true,
   "reproducedFirst": null,
   "durationSeconds": 551.329,
   "tokens": null,
   "costUSD": null,
   "timedOut": false,
   "blindOverall": null,
   "replay": "replays/humanizer/claude-haiku-5-5/142664ee5a9a.json",
   "agentCli": "claude-code",
   "agentCliSource": "RunDocument.agent",
   "runSetId": "6320ec6baf32",
   "trialIndex": 1,
   "trialCount": 3,
   "runId": "e64c027e7753"
  },
  {
   "videoId": "humanizer",
   "modelId": "claude-haiku-5-5",
   "scenarioId": "63f500c69cf8",
   "passed": true,
   "reproducedFirst": null,
   "durationSeconds": 847.503,
   "tokens": null,
   "costUSD": null,
   "timedOut": false,
   "blindOverall": null,
   "replay": "replays/humanizer/claude-haiku-5-5/63f500c69cf8.json",
   "agentCli": "claude-code",
   "agentCliSource": "RunDocument.agent",
   "runSetId": "6320ec6baf32",
   "trialIndex": 1,
   "trialCount": 3,
   "runId": "e64c027e7753"
  },
  {
   "videoId": "humanizer",
   "modelId": "claude-haiku-5-5",
   "scenarioId": "65c7a56b1fd7",
   "passed": false,
   "reproducedFirst": null,
   "durationSeconds": 522.037,
   "tokens": null,
   "costUSD": null,
   "timedOut": false,
   "blindOverall": null,
   "replay": "replays/humanizer/claude-haiku-5-5/65c7a56b1fd7.json",
   "agentCli": "claude-code",
   "agentCliSource": "RunDocument.agent",
   "runSetId": "6320ec6baf32",
   "trialIndex": 1,
   "trialCount": 3,
   "runId": "e64c027e7753"
  },
  {
   "videoId": "humanizer",
   "modelId": "claude-haiku-5-5",
   "scenarioId": "f4ade1576bcb",
   "passed": true,
   "reproducedFirst": null,
   "durationSeconds": 320.679,
   "tokens": null,
   "costUSD": null,
   "timedOut": false,
   "blindOverall": null,
   "replay": "replays/humanizer/claude-haiku-5-5/f4ade1576bcb.json",
   "agentCli": "claude-code",
   "agentCliSource": "RunDocument.agent",
   "runSetId": "6320ec6baf32",
   "trialIndex": 1,
   "trialCount": 3,
   "runId": "e64c027e7753"
  },
  {
   "videoId": "humanizer",
   "modelId": "claude-haiku-5-5",
   "scenarioId": "77e7fd8f1c1b",
   "passed": false,
   "reproducedFirst": null,
   "durationSeconds": 456.256,
   "tokens": null,
   "costUSD": null,
   "timedOut": false,
   "blindOverall": null,
   "replay": "replays/humanizer/claude-haiku-5-5/77e7fd8f1c1b.json",
   "agentCli": "claude-code",
   "agentCliSource": "RunDocument.agent",
   "runSetId": "6320ec6baf32",
   "trialIndex": 1,
   "trialCount": 3,
   "runId": "e64c027e7753"
  },
  {
   "videoId": "humanizer",
   "modelId": "claude-haiku-5-5",
   "scenarioId": "142664ee5a9a",
   "passed": true,
   "reproducedFirst": null,
   "durationSeconds": 183.955,
   "tokens": null,
   "costUSD": null,
   "timedOut": false,
   "blindOverall": null,
   "replay": "replays/humanizer/claude-haiku-5-5/142664ee5a9a.t2.json",
   "agentCli": "claude-code",
   "agentCliSource": "RunDocument.agent",
   "runSetId": "6320ec6baf32",
   "trialIndex": 2,
   "trialCount": 3,
   "runId": "0e7cd0c46595"
  },
  {
   "videoId": "humanizer",
   "modelId": "claude-haiku-5-5",
   "scenarioId": "63f500c69cf8",
   "passed": true,
   "reproducedFirst": null,
   "durationSeconds": 129.18,
   "tokens": null,
   "costUSD": null,
   "timedOut": false,
   "blindOverall": null,
   "replay": "replays/humanizer/claude-haiku-5-5/63f500c69cf8.t2.json",
   "agentCli": "claude-code",
   "agentCliSource": "RunDocument.agent",
   "runSetId": "6320ec6baf32",
   "trialIndex": 2,
   "trialCount": 3,
   "runId": "0e7cd0c46595"
  },
  {
   "videoId": "humanizer",
   "modelId": "claude-haiku-5-5",
   "scenarioId": "65c7a56b1fd7",
   "passed": false,
   "reproducedFirst": null,
   "durationSeconds": 335.5,
   "tokens": null,
   "costUSD": null,
   "timedOut": false,
   "blindOverall": null,
   "replay": "replays/humanizer/claude-haiku-5-5/65c7a56b1fd7.t2.json",
   "agentCli": "claude-code",
   "agentCliSource": "RunDocument.agent",
   "runSetId": "6320ec6baf32",
   "trialIndex": 2,
   "trialCount": 3,
   "runId": "0e7cd0c46595"
  },
  {
   "videoId": "humanizer",
   "modelId": "claude-haiku-5-5",
   "scenarioId": "f4ade1576bcb",
   "passed": true,
   "reproducedFirst": null,
   "durationSeconds": 109.639,
   "tokens": null,
   "costUSD": null,
   "timedOut": false,
   "blindOverall": null,
   "replay": "replays/humanizer/claude-haiku-5-5/f4ade1576bcb.t2.json",
   "agentCli": "claude-code",
   "agentCliSource": "RunDocument.agent",
   "runSetId": "6320ec6baf32",
   "trialIndex": 2,
   "trialCount": 3,
   "runId": "0e7cd0c46595"
  },
  {
   "videoId": "humanizer",
   "modelId": "claude-haiku-5-5",
   "scenarioId": "77e7fd8f1c1b",
   "passed": false,
   "reproducedFirst": null,
   "durationSeconds": 505.124,
   "tokens": null,
   "costUSD": null,
   "timedOut": false,
   "blindOverall": null,
   "replay": "replays/humanizer/claude-haiku-5-5/77e7fd8f1c1b.t2.json",
   "agentCli": "claude-code",
   "agentCliSource": "RunDocument.agent",
   "runSetId": "6320ec6baf32",
   "trialIndex": 2,
   "trialCount": 3,
   "runId": "0e7cd0c46595"
  },
  {
   "videoId": "humanizer",
   "modelId": "claude-haiku-5-5",
   "scenarioId": "142664ee5a9a",
   "passed": true,
   "reproducedFirst": null,
   "durationSeconds": 163.197,
   "tokens": null,
   "costUSD": null,
   "timedOut": false,
   "blindOverall": null,
   "replay": "replays/humanizer/claude-haiku-5-5/142664ee5a9a.t3.json",
   "agentCli": "claude-code",
   "agentCliSource": "RunDocument.agent",
   "runSetId": "6320ec6baf32",
   "trialIndex": 3,
   "trialCount": 3,
   "runId": "c6cb6799ffda"
  },
  {
   "videoId": "humanizer",
   "modelId": "claude-haiku-5-5",
   "scenarioId": "63f500c69cf8",
   "passed": true,
   "reproducedFirst": null,
   "durationSeconds": 183.276,
   "tokens": null,
   "costUSD": null,
   "timedOut": false,
   "blindOverall": null,
   "replay": "replays/humanizer/claude-haiku-5-5/63f500c69cf8.t3.json",
   "agentCli": "claude-code",
   "agentCliSource": "RunDocument.agent",
   "runSetId": "6320ec6baf32",
   "trialIndex": 3,
   "trialCount": 3,
   "runId": "c6cb6799ffda"
  },
  {
   "videoId": "humanizer",
   "modelId": "claude-haiku-5-5",
   "scenarioId": "65c7a56b1fd7",
   "passed": false,
   "reproducedFirst": null,
   "durationSeconds": 326.834,
   "tokens": null,
   "costUSD": null,
   "timedOut": false,
   "blindOverall": null,
   "replay": "replays/humanizer/claude-haiku-5-5/65c7a56b1fd7.t3.json",
   "agentCli": "claude-code",
   "agentCliSource": "RunDocument.agent",
   "runSetId": "6320ec6baf32",
   "trialIndex": 3,
   "trialCount": 3,
   "runId": "c6cb6799ffda"
  },
  {
   "videoId": "humanizer",
   "modelId": "claude-haiku-5-5",
   "scenarioId": "f4ade1576bcb",
   "passed": true,
   "reproducedFirst": null,
   "durationSeconds": 134.563,
   "tokens": null,
   "costUSD": null,
   "timedOut": false,
   "blindOverall": null,
   "replay": "replays/humanizer/claude-haiku-5-5/f4ade1576bcb.t3.json",
   "agentCli": "claude-code",
   "agentCliSource": "RunDocument.agent",
   "runSetId": "6320ec6baf32",
   "trialIndex": 3,
   "trialCount": 3,
   "runId": "c6cb6799ffda"
  },
  {
   "videoId": "humanizer",
   "modelId": "claude-haiku-5-5",
   "scenarioId": "77e7fd8f1c1b",
   "passed": false,
   "reproducedFirst": null,
   "durationSeconds": 536.67,
   "tokens": null,
   "costUSD": null,
   "timedOut": false,
   "blindOverall": null,
   "replay": "replays/humanizer/claude-haiku-5-5/77e7fd8f1c1b.t3.json",
   "agentCli": "claude-code",
   "agentCliSource": "RunDocument.agent",
   "runSetId": "6320ec6baf32",
   "trialIndex": 3,
   "trialCount": 3,
   "runId": "c6cb6799ffda"
  },
  {
   "videoId": "humanizer",
   "modelId": "gpt-6-luna",
   "scenarioId": "142664ee5a9a",
   "passed": true,
   "reproducedFirst": null,
   "durationSeconds": 225.176,
   "tokens": null,
   "costUSD": null,
   "timedOut": false,
   "blindOverall": null,
   "replay": "replays/humanizer/gpt-6-luna/142664ee5a9a.json",
   "agentCli": "codex",
   "agentCliSource": "RunDocument.agent",
   "runSetId": "084ebaf2cbb4",
   "trialIndex": 1,
   "trialCount": 3,
   "runId": "007e36c0288d"
  },
  {
   "videoId": "humanizer",
   "modelId": "gpt-6-luna",
   "scenarioId": "63f500c69cf8",
   "passed": true,
   "reproducedFirst": null,
   "durationSeconds": 322.259,
   "tokens": null,
   "costUSD": null,
   "timedOut": false,
   "blindOverall": null,
   "replay": "replays/humanizer/gpt-6-luna/63f500c69cf8.json",
   "agentCli": "codex",
   "agentCliSource": "RunDocument.agent",
   "runSetId": "084ebaf2cbb4",
   "trialIndex": 1,
   "trialCount": 3,
   "runId": "007e36c0288d"
  },
  {
   "videoId": "humanizer",
   "modelId": "gpt-6-luna",
   "scenarioId": "65c7a56b1fd7",
   "passed": false,
   "reproducedFirst": null,
   "durationSeconds": 263.005,
   "tokens": null,
   "costUSD": null,
   "timedOut": false,
   "blindOverall": null,
   "replay": "replays/humanizer/gpt-6-luna/65c7a56b1fd7.json",
   "agentCli": "codex",
   "agentCliSource": "RunDocument.agent",
   "runSetId": "084ebaf2cbb4",
   "trialIndex": 1,
   "trialCount": 3,
   "runId": "007e36c0288d"
  },
  {
   "videoId": "humanizer",
   "modelId": "gpt-6-luna",
   "scenarioId": "f4ade1576bcb",
   "passed": false,
   "reproducedFirst": null,
   "durationSeconds": 228.092,
   "tokens": null,
   "costUSD": null,
   "timedOut": false,
   "blindOverall": null,
   "replay": "replays/humanizer/gpt-6-luna/f4ade1576bcb.json",
   "agentCli": "codex",
   "agentCliSource": "RunDocument.agent",
   "runSetId": "084ebaf2cbb4",
   "trialIndex": 1,
   "trialCount": 3,
   "runId": "007e36c0288d"
  },
  {
   "videoId": "humanizer",
   "modelId": "gpt-6-luna",
   "scenarioId": "77e7fd8f1c1b",
   "passed": false,
   "reproducedFirst": null,
   "durationSeconds": 167.211,
   "tokens": null,
   "costUSD": null,
   "timedOut": false,
   "blindOverall": null,
   "replay": "replays/humanizer/gpt-6-luna/77e7fd8f1c1b.json",
   "agentCli": "codex",
   "agentCliSource": "RunDocument.agent",
   "runSetId": "084ebaf2cbb4",
   "trialIndex": 1,
   "trialCount": 3,
   "runId": "007e36c0288d"
  },
  {
   "videoId": "humanizer",
   "modelId": "gpt-6-luna",
   "scenarioId": "142664ee5a9a",
   "passed": true,
   "reproducedFirst": null,
   "durationSeconds": 78.398,
   "tokens": null,
   "costUSD": null,
   "timedOut": false,
   "blindOverall": null,
   "replay": "replays/humanizer/gpt-6-luna/142664ee5a9a.t2.json",
   "agentCli": "codex",
   "agentCliSource": "RunDocument.agent",
   "runSetId": "084ebaf2cbb4",
   "trialIndex": 2,
   "trialCount": 3,
   "runId": "5ea4ee1477c1"
  },
  {
   "videoId": "humanizer",
   "modelId": "gpt-6-luna",
   "scenarioId": "63f500c69cf8",
   "passed": true,
   "reproducedFirst": null,
   "durationSeconds": 141.138,
   "tokens": null,
   "costUSD": null,
   "timedOut": false,
   "blindOverall": null,
   "replay": "replays/humanizer/gpt-6-luna/63f500c69cf8.t2.json",
   "agentCli": "codex",
   "agentCliSource": "RunDocument.agent",
   "runSetId": "084ebaf2cbb4",
   "trialIndex": 2,
   "trialCount": 3,
   "runId": "5ea4ee1477c1"
  },
  {
   "videoId": "humanizer",
   "modelId": "gpt-6-luna",
   "scenarioId": "65c7a56b1fd7",
   "passed": false,
   "reproducedFirst": null,
   "durationSeconds": 237.626,
   "tokens": null,
   "costUSD": null,
   "timedOut": false,
   "blindOverall": null,
   "replay": "replays/humanizer/gpt-6-luna/65c7a56b1fd7.t2.json",
   "agentCli": "codex",
   "agentCliSource": "RunDocument.agent",
   "runSetId": "084ebaf2cbb4",
   "trialIndex": 2,
   "trialCount": 3,
   "runId": "5ea4ee1477c1"
  },
  {
   "videoId": "humanizer",
   "modelId": "gpt-6-luna",
   "scenarioId": "f4ade1576bcb",
   "passed": true,
   "reproducedFirst": null,
   "durationSeconds": 127.855,
   "tokens": null,
   "costUSD": null,
   "timedOut": false,
   "blindOverall": null,
   "replay": "replays/humanizer/gpt-6-luna/f4ade1576bcb.t2.json",
   "agentCli": "codex",
   "agentCliSource": "RunDocument.agent",
   "runSetId": "084ebaf2cbb4",
   "trialIndex": 2,
   "trialCount": 3,
   "runId": "5ea4ee1477c1"
  },
  {
   "videoId": "humanizer",
   "modelId": "gpt-6-luna",
   "scenarioId": "77e7fd8f1c1b",
   "passed": false,
   "reproducedFirst": null,
   "durationSeconds": 184.951,
   "tokens": null,
   "costUSD": null,
   "timedOut": false,
   "blindOverall": null,
   "replay": "replays/humanizer/gpt-6-luna/77e7fd8f1c1b.t2.json",
   "agentCli": "codex",
   "agentCliSource": "RunDocument.agent",
   "runSetId": "084ebaf2cbb4",
   "trialIndex": 2,
   "trialCount": 3,
   "runId": "5ea4ee1477c1"
  },
  {
   "videoId": "humanizer",
   "modelId": "gpt-6-luna",
   "scenarioId": "142664ee5a9a",
   "passed": true,
   "reproducedFirst": null,
   "durationSeconds": 95.56,
   "tokens": null,
   "costUSD": null,
   "timedOut": false,
   "blindOverall": null,
   "replay": "replays/humanizer/gpt-6-luna/142664ee5a9a.t3.json",
   "agentCli": "codex",
   "agentCliSource": "RunDocument.agent",
   "runSetId": "084ebaf2cbb4",
   "trialIndex": 3,
   "trialCount": 3,
   "runId": "dd97856c5080"
  },
  {
   "videoId": "humanizer",
   "modelId": "gpt-6-luna",
   "scenarioId": "63f500c69cf8",
   "passed": true,
   "reproducedFirst": null,
   "durationSeconds": 166.767,
   "tokens": null,
   "costUSD": null,
   "timedOut": false,
   "blindOverall": null,
   "replay": "replays/humanizer/gpt-6-luna/63f500c69cf8.t3.json",
   "agentCli": "codex",
   "agentCliSource": "RunDocument.agent",
   "runSetId": "084ebaf2cbb4",
   "trialIndex": 3,
   "trialCount": 3,
   "runId": "dd97856c5080"
  },
  {
   "videoId": "humanizer",
   "modelId": "gpt-6-luna",
   "scenarioId": "65c7a56b1fd7",
   "passed": false,
   "reproducedFirst": null,
   "durationSeconds": 105.749,
   "tokens": null,
   "costUSD": null,
   "timedOut": false,
   "blindOverall": null,
   "replay": "replays/humanizer/gpt-6-luna/65c7a56b1fd7.t3.json",
   "agentCli": "codex",
   "agentCliSource": "RunDocument.agent",
   "runSetId": "084ebaf2cbb4",
   "trialIndex": 3,
   "trialCount": 3,
   "runId": "dd97856c5080"
  },
  {
   "videoId": "humanizer",
   "modelId": "gpt-6-luna",
   "scenarioId": "f4ade1576bcb",
   "passed": true,
   "reproducedFirst": null,
   "durationSeconds": 131.285,
   "tokens": null,
   "costUSD": null,
   "timedOut": false,
   "blindOverall": null,
   "replay": "replays/humanizer/gpt-6-luna/f4ade1576bcb.t3.json",
   "agentCli": "codex",
   "agentCliSource": "RunDocument.agent",
   "runSetId": "084ebaf2cbb4",
   "trialIndex": 3,
   "trialCount": 3,
   "runId": "dd97856c5080"
  },
  {
   "videoId": "humanizer",
   "modelId": "gpt-6-luna",
   "scenarioId": "77e7fd8f1c1b",
   "passed": false,
   "reproducedFirst": null,
   "durationSeconds": 291.658,
   "tokens": null,
   "costUSD": null,
   "timedOut": false,
   "blindOverall": null,
   "replay": "replays/humanizer/gpt-6-luna/77e7fd8f1c1b.t3.json",
   "agentCli": "codex",
   "agentCliSource": "RunDocument.agent",
   "runSetId": "084ebaf2cbb4",
   "trialIndex": 3,
   "trialCount": 3,
   "runId": "dd97856c5080"
  }
 ],
 "leaderboard": {
  "basis": "5 bugs, every trial counts; fixed = bugs resolved in at least half their trials",
  "bugCount": 5,
  "maxPoints": null,
  "omittedBugCount": 0,
  "rows": [
   {
    "modelId": "claude-haiku-5-5",
    "videoId": "humanizer",
    "fixed": 3,
    "of": 5,
    "points": null,
    "costUSD": null,
    "timeSeconds": 1768.6,
    "tokens": null,
    "runCount": 5,
    "statistics": {
     "bugCount": 5,
     "trialsPerBug": 3,
     "trialCount": 15,
     "resolveRate": {
      "mean": 0.6,
      "low": 0.2,
      "high": 1
     },
     "passAtK": [
      {
       "k": 1,
       "value": 0.6
      },
      {
       "k": 2,
       "value": 0.6
      },
      {
       "k": 3,
       "value": 0.6
      }
     ],
     "firstTryRate": 0.5333,
     "feedbackGain": 0.0667,
     "confidence": 0.95,
     "bootstrapSamples": 2000,
     "seed": 166
    },
    "trials": 3,
    "runSetId": "6320ec6baf32"
   },
   {
    "modelId": "gpt-6-luna",
    "videoId": "humanizer",
    "fixed": 3,
    "of": 5,
    "points": null,
    "costUSD": null,
    "timeSeconds": 922.2,
    "tokens": null,
    "runCount": 5,
    "statistics": {
     "bugCount": 5,
     "trialsPerBug": 3,
     "trialCount": 15,
     "resolveRate": {
      "mean": 0.5333,
      "low": 0.1333,
      "high": 0.9333
     },
     "passAtK": [
      {
       "k": 1,
       "value": 0.5333
      },
      {
       "k": 2,
       "value": 0.6
      },
      {
       "k": 3,
       "value": 0.6
      }
     ],
     "firstTryRate": 0.5333,
     "feedbackGain": 0,
     "confidence": 0.95,
     "bootstrapSamples": 2000,
     "seed": 166
    },
    "trials": 3,
    "runSetId": "084ebaf2cbb4"
   }
  ]
 }
}