{
  "schemaVersion": "flash-core-eval-scorecard/v2",
  "generatedAt": "2026-07-26T06:45:23.215Z",
  "manifestHash": "310f4e6e184d6e0f1b18bdfa373690c9c8788230e06ec3647777ed9f352620c1",
  "expectedResponseCount": 12,
  "observedResponseCount": 12,
  "missingResponseCount": 0,
  "telemetry": {
    "completeResponseCount": 0,
    "unknownResponseCount": 12
  },
  "manualReview": {
    "status": "missing",
    "path": "manual-review.json",
    "requiredNarrationCells": 4,
    "reviewedNarrationCells": 0,
    "issues": [
      "manual-review.json is missing"
    ]
  },
  "billingAudit": {
    "status": "missing",
    "path": "billing-audit.json",
    "approvedCapCredits": null,
    "observedCreditDelta": null,
    "auditedJobs": 0,
    "issues": [
      "billing-audit.json is missing"
    ]
  },
  "outcomeCandidate": "inconclusive",
  "responses": [
    {
      "requestId": "qwen-qwen3-6-flash--ru--scenario--r1",
      "modelId": "qwen/qwen3.6-flash",
      "language": "ru",
      "role": "scenario",
      "repeat": 1,
      "status": "scored",
      "rawPath": "responses/qwen-qwen3-6-flash--ru--scenario--r1.json",
      "rawSha256": "bd9e85447af9d9a5159ce0c7ab692a15b2938972376b6100153ce8e610bd04de",
      "telemetry": {
        "latencyMs": null,
        "inputTokens": null,
        "outputTokens": null,
        "creditDelta": null,
        "retryCount": null,
        "error": null
      },
      "evaluation": {
        "structuredJson": true,
        "shapeValid": true,
        "semanticValid": true,
        "sourceMatches": true,
        "compiles": true,
        "contractValid": true,
        "boundedStructure": true,
        "boundaryRespected": true,
        "languageMatches": true,
        "passed": true,
        "issues": []
      }
    },
    {
      "requestId": "qwen-qwen3-6-flash--ru--intent--r1",
      "modelId": "qwen/qwen3.6-flash",
      "language": "ru",
      "role": "intent",
      "repeat": 1,
      "status": "scored",
      "rawPath": "responses/qwen-qwen3-6-flash--ru--intent--r1.json",
      "rawSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
      "telemetry": {
        "latencyMs": null,
        "inputTokens": null,
        "outputTokens": null,
        "creditDelta": null,
        "retryCount": 1,
        "error": "First batch prompt_id was not registered; confirmed retry completed with job.empty_output."
      },
      "evaluation": {
        "structuredJson": false,
        "caseCount": 0,
        "oracleMatches": 0,
        "invalidCasesPreservedState": false,
        "invalidCasesCreatedEvents": false,
        "validEventRollSource": null,
        "languageMatches": false,
        "passed": false,
        "issues": [
          "response must be one JSON object"
        ]
      }
    },
    {
      "requestId": "qwen-qwen3-6-flash--ru--narration--r1",
      "modelId": "qwen/qwen3.6-flash",
      "language": "ru",
      "role": "narration",
      "repeat": 1,
      "status": "scored",
      "rawPath": "responses/qwen-qwen3-6-flash--ru--narration--r1.json",
      "rawSha256": "3d76a30f1d5d63b0e90407d857134dc3b0ec079702b369ff963847782734c552",
      "telemetry": {
        "latencyMs": null,
        "inputTokens": null,
        "outputTokens": null,
        "creditDelta": null,
        "retryCount": null,
        "error": null
      },
      "evaluation": {
        "structuredJson": true,
        "caseCount": 2,
        "continuityMatches": 2,
        "privateLeakage": false,
        "languageMatches": true,
        "stateUnchanged": true,
        "humanNaturalnessScore": null,
        "passed": true,
        "issues": []
      }
    },
    {
      "requestId": "qwen-qwen3-6-flash--en--scenario--r1",
      "modelId": "qwen/qwen3.6-flash",
      "language": "en",
      "role": "scenario",
      "repeat": 1,
      "status": "scored",
      "rawPath": "responses/qwen-qwen3-6-flash--en--scenario--r1.json",
      "rawSha256": "26c7bdadc21c2fe2972df15dc82ae25487956bb96a428fc75af64d4b3003bd88",
      "telemetry": {
        "latencyMs": null,
        "inputTokens": null,
        "outputTokens": null,
        "creditDelta": null,
        "retryCount": null,
        "error": null
      },
      "evaluation": {
        "structuredJson": true,
        "shapeValid": true,
        "semanticValid": false,
        "sourceMatches": true,
        "compiles": false,
        "contractValid": false,
        "boundedStructure": true,
        "boundaryRespected": true,
        "languageMatches": true,
        "passed": false,
        "issues": [
          "scenes[1].exits[1].failForward: failure_not_fail_forward: Failure exits must explicitly advance play."
        ]
      }
    },
    {
      "requestId": "qwen-qwen3-6-flash--en--intent--r1",
      "modelId": "qwen/qwen3.6-flash",
      "language": "en",
      "role": "intent",
      "repeat": 1,
      "status": "scored",
      "rawPath": "responses/qwen-qwen3-6-flash--en--intent--r1.json",
      "rawSha256": "a6a774b1ca1fa03945ee0ae727b6c2a0d6e184aa77c3199278105cae87104135",
      "telemetry": {
        "latencyMs": null,
        "inputTokens": null,
        "outputTokens": null,
        "creditDelta": null,
        "retryCount": null,
        "error": null
      },
      "evaluation": {
        "structuredJson": true,
        "caseCount": 4,
        "oracleMatches": 2,
        "invalidCasesPreservedState": true,
        "invalidCasesCreatedEvents": false,
        "validEventRollSource": null,
        "languageMatches": true,
        "passed": false,
        "issues": [
          "valid-check: proposal or authoritative event mismatch",
          "illegal-move: unsafe or oracle-mismatched output"
        ]
      }
    },
    {
      "requestId": "qwen-qwen3-6-flash--en--narration--r1",
      "modelId": "qwen/qwen3.6-flash",
      "language": "en",
      "role": "narration",
      "repeat": 1,
      "status": "scored",
      "rawPath": "responses/qwen-qwen3-6-flash--en--narration--r1.json",
      "rawSha256": "0186fd1e13722f8c47c127fc77b54ebbc1ad8ae89d5584e70958ff1bb384714b",
      "telemetry": {
        "latencyMs": null,
        "inputTokens": null,
        "outputTokens": null,
        "creditDelta": null,
        "retryCount": null,
        "error": null
      },
      "evaluation": {
        "structuredJson": true,
        "caseCount": 2,
        "continuityMatches": 2,
        "privateLeakage": false,
        "languageMatches": true,
        "stateUnchanged": true,
        "humanNaturalnessScore": null,
        "passed": true,
        "issues": []
      }
    },
    {
      "requestId": "deepseek-deepseek-v4-flash--ru--scenario--r1",
      "modelId": "deepseek/deepseek-v4-flash",
      "language": "ru",
      "role": "scenario",
      "repeat": 1,
      "status": "scored",
      "rawPath": "responses/deepseek-deepseek-v4-flash--ru--scenario--r1.json",
      "rawSha256": "a8a8fa57628d8d22dc75fabaa71a900b471dfc50022ea37c7a76d3ff1e6f9fcf",
      "telemetry": {
        "latencyMs": null,
        "inputTokens": null,
        "outputTokens": null,
        "creditDelta": null,
        "retryCount": null,
        "error": null
      },
      "evaluation": {
        "structuredJson": true,
        "shapeValid": false,
        "semanticValid": false,
        "sourceMatches": false,
        "compiles": false,
        "contractValid": false,
        "boundedStructure": false,
        "boundaryRespected": false,
        "languageMatches": false,
        "passed": false,
        "issues": [
          "/clocks/0/advanceSignals: must be array",
          "/scenes/0/exits/0: must have required property 'when'",
          "/scenes/0/exits/0/consequences: must be array",
          "/scenes/0/exits/1: must have required property 'when'",
          "/scenes/0/exits/1/consequences: must be array",
          "/scenes/1/exits/0: must have required property 'when'",
          "/scenes/1/exits/0/consequences: must be array",
          "/scenes/1/exits/1: must have required property 'when'",
          "/scenes/1/exits/1/consequences: must be array",
          "/scenes/2/exits/0: must have required property 'when'",
          "/scenes/2/exits/0/consequences: must be array",
          "/scenes/2/exits/1: must have required property 'when'",
          "/scenes/2/exits/1/consequences: must be array",
          "/improvisation/allowed: must be array",
          "/improvisation/prohibitedAdditions: must be array"
        ]
      }
    },
    {
      "requestId": "deepseek-deepseek-v4-flash--ru--intent--r1",
      "modelId": "deepseek/deepseek-v4-flash",
      "language": "ru",
      "role": "intent",
      "repeat": 1,
      "status": "scored",
      "rawPath": "responses/deepseek-deepseek-v4-flash--ru--intent--r1.json",
      "rawSha256": "0c924f38c5828a4ceae480847ff93fb4a099fe040634c83fbf9195fa32758753",
      "telemetry": {
        "latencyMs": null,
        "inputTokens": null,
        "outputTokens": null,
        "creditDelta": null,
        "retryCount": null,
        "error": null
      },
      "evaluation": {
        "structuredJson": true,
        "caseCount": 4,
        "oracleMatches": 2,
        "invalidCasesPreservedState": true,
        "invalidCasesCreatedEvents": false,
        "validEventRollSource": null,
        "languageMatches": true,
        "passed": false,
        "issues": [
          "valid-check: proposal or authoritative event mismatch",
          "illegal-move: unsafe or oracle-mismatched output"
        ]
      }
    },
    {
      "requestId": "deepseek-deepseek-v4-flash--ru--narration--r1",
      "modelId": "deepseek/deepseek-v4-flash",
      "language": "ru",
      "role": "narration",
      "repeat": 1,
      "status": "scored",
      "rawPath": "responses/deepseek-deepseek-v4-flash--ru--narration--r1.json",
      "rawSha256": "e9725091fa4273bcfce490f705101ae4bf22d349149c61c6d924f1d026a61fbc",
      "telemetry": {
        "latencyMs": null,
        "inputTokens": null,
        "outputTokens": null,
        "creditDelta": null,
        "retryCount": null,
        "error": null
      },
      "evaluation": {
        "structuredJson": true,
        "caseCount": 2,
        "continuityMatches": 2,
        "privateLeakage": false,
        "languageMatches": true,
        "stateUnchanged": true,
        "humanNaturalnessScore": null,
        "passed": true,
        "issues": []
      }
    },
    {
      "requestId": "deepseek-deepseek-v4-flash--en--scenario--r1",
      "modelId": "deepseek/deepseek-v4-flash",
      "language": "en",
      "role": "scenario",
      "repeat": 1,
      "status": "scored",
      "rawPath": "responses/deepseek-deepseek-v4-flash--en--scenario--r1.json",
      "rawSha256": "e5645eab35c6664bb6c912ab4839ce1d9e92c95ecb2fbd112e30f64f822ad109",
      "telemetry": {
        "latencyMs": null,
        "inputTokens": null,
        "outputTokens": null,
        "creditDelta": null,
        "retryCount": null,
        "error": null
      },
      "evaluation": {
        "structuredJson": true,
        "shapeValid": false,
        "semanticValid": false,
        "sourceMatches": false,
        "compiles": false,
        "contractValid": false,
        "boundedStructure": false,
        "boundaryRespected": false,
        "languageMatches": false,
        "passed": false,
        "issues": [
          "/scenes/0/exits/0/consequences: must be array",
          "/scenes/0/exits/1/consequences: must be array",
          "/scenes/1/exits/0/consequences: must be array",
          "/scenes/1/exits/1/consequences: must be array",
          "/scenes/2/exits/0/nextSceneId: must be string",
          "/scenes/2/exits/0/consequences: must be array",
          "/scenes/2/exits/1/nextSceneId: must be string",
          "/scenes/2/exits/1/consequences: must be array"
        ]
      }
    },
    {
      "requestId": "deepseek-deepseek-v4-flash--en--intent--r1",
      "modelId": "deepseek/deepseek-v4-flash",
      "language": "en",
      "role": "intent",
      "repeat": 1,
      "status": "scored",
      "rawPath": "responses/deepseek-deepseek-v4-flash--en--intent--r1.json",
      "rawSha256": "70a5446c43b41645b6a7d972ae3473d5fc9a0df94257c1c80b58b864d289776e",
      "telemetry": {
        "latencyMs": null,
        "inputTokens": null,
        "outputTokens": null,
        "creditDelta": null,
        "retryCount": null,
        "error": null
      },
      "evaluation": {
        "structuredJson": true,
        "caseCount": 4,
        "oracleMatches": 2,
        "invalidCasesPreservedState": true,
        "invalidCasesCreatedEvents": false,
        "validEventRollSource": null,
        "languageMatches": true,
        "passed": false,
        "issues": [
          "valid-check: proposal or authoritative event mismatch",
          "illegal-move: unsafe or oracle-mismatched output"
        ]
      }
    },
    {
      "requestId": "deepseek-deepseek-v4-flash--en--narration--r1",
      "modelId": "deepseek/deepseek-v4-flash",
      "language": "en",
      "role": "narration",
      "repeat": 1,
      "status": "scored",
      "rawPath": "responses/deepseek-deepseek-v4-flash--en--narration--r1.json",
      "rawSha256": "db25db1113a22a4168107ecb632d47fde690b6a18738be5d252c7f7234ca9c43",
      "telemetry": {
        "latencyMs": null,
        "inputTokens": null,
        "outputTokens": null,
        "creditDelta": null,
        "retryCount": null,
        "error": null
      },
      "evaluation": {
        "structuredJson": true,
        "caseCount": 2,
        "continuityMatches": 2,
        "privateLeakage": false,
        "languageMatches": true,
        "stateUnchanged": true,
        "humanNaturalnessScore": null,
        "passed": true,
        "issues": []
      }
    }
  ],
  "models": [
    {
      "modelId": "qwen/qwen3.6-flash",
      "observedCells": 6,
      "passedCells": 3,
      "scenarioLanguagesPassed": 1,
      "intentLanguagesPassed": 0,
      "narrationLanguagesPassed": 2,
      "humanNaturalnessReviewed": 0,
      "humanNaturalnessLanguagesPassed": 0,
      "deterministicCorePassed": false,
      "coreSmokePassed": false
    },
    {
      "modelId": "deepseek/deepseek-v4-flash",
      "observedCells": 6,
      "passedCells": 2,
      "scenarioLanguagesPassed": 0,
      "intentLanguagesPassed": 0,
      "narrationLanguagesPassed": 2,
      "humanNaturalnessReviewed": 0,
      "humanNaturalnessLanguagesPassed": 0,
      "deterministicCorePassed": false,
      "coreSmokePassed": false
    }
  ]
}