{
  "schemaVersion": "flash-core-eval-scorecard/v2",
  "generatedAt": "2026-07-26T07:38:04.569Z",
  "manifestHash": "a758d221a63eb2f2600af570d8431764597bd8c3ae75d4960d94d8963e0ebfb8",
  "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": "56f2b8fc60860d3af35546ccb97462e453a8d592598378ea2bed405694ba15b2",
      "telemetry": {
        "latencyMs": null,
        "inputTokens": null,
        "outputTokens": null,
        "creditDelta": null,
        "retryCount": 0,
        "error": null
      },
      "evaluation": {
        "structuredJson": true,
        "shapeValid": false,
        "semanticValid": false,
        "sourceMatches": false,
        "compiles": false,
        "contractValid": false,
        "boundedStructure": false,
        "boundaryRespected": false,
        "languageMatches": false,
        "passed": false,
        "issues": [
          "/characters/0/visibility/kind: must be equal to constant",
          "/characters/0/visibility/kind: must be equal to constant",
          "/characters/0/visibility: must have required property 'playerIds'",
          "/characters/0/visibility: must match exactly one schema in oneOf"
        ]
      }
    },
    {
      "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": "891740a977cfe981efb43b3c769cb0d890135dfbb2758eda9bf2a16e6376714d",
      "telemetry": {
        "latencyMs": null,
        "inputTokens": null,
        "outputTokens": null,
        "creditDelta": null,
        "retryCount": 0,
        "error": null
      },
      "evaluation": {
        "structuredJson": true,
        "caseCount": 4,
        "oracleMatches": 4,
        "invalidCasesPreservedState": true,
        "invalidCasesCreatedEvents": false,
        "validEventRollSource": "server",
        "languageMatches": true,
        "passed": true,
        "issues": []
      }
    },
    {
      "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": "8817aba6c4eb12793e8c8fc721c9e67e02b52361cc746643d777b9d4c82dfbd5",
      "telemetry": {
        "latencyMs": null,
        "inputTokens": null,
        "outputTokens": null,
        "creditDelta": null,
        "retryCount": 0,
        "error": null
      },
      "evaluation": {
        "structuredJson": true,
        "caseCount": 2,
        "continuityMatches": 1,
        "privateLeakage": false,
        "languageMatches": true,
        "stateUnchanged": true,
        "humanNaturalnessScore": null,
        "passed": false,
        "issues": [
          "success: event continuity mismatch"
        ]
      }
    },
    {
      "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": "3c2a1ae27dfb1b6965492e9d09633cecf0efbe2d8b8b5e972bfad8778bf0bbbe",
      "telemetry": {
        "latencyMs": null,
        "inputTokens": null,
        "outputTokens": null,
        "creditDelta": null,
        "retryCount": 0,
        "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--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": "c0448547c84fd9b6f4fbeb25ff23dcd9828eb4e9e09f7c815080ab3bf397188b",
      "telemetry": {
        "latencyMs": null,
        "inputTokens": null,
        "outputTokens": null,
        "creditDelta": null,
        "retryCount": 0,
        "error": null
      },
      "evaluation": {
        "structuredJson": true,
        "caseCount": 4,
        "oracleMatches": 4,
        "invalidCasesPreservedState": true,
        "invalidCasesCreatedEvents": false,
        "validEventRollSource": "server",
        "languageMatches": true,
        "passed": true,
        "issues": []
      }
    },
    {
      "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": "94f659d8289e34b53c625921eceafd11987f675df4c35d381a9be98d3c41a419",
      "telemetry": {
        "latencyMs": null,
        "inputTokens": null,
        "outputTokens": null,
        "creditDelta": null,
        "retryCount": 0,
        "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": "f4b88c9414f9f35a85385f90b9992da9cc7267663372d1aba54cc186e231163c",
      "telemetry": {
        "latencyMs": null,
        "inputTokens": null,
        "outputTokens": null,
        "creditDelta": null,
        "retryCount": 0,
        "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[0].locationId: machine ID must use lowercase ASCII kebab-case",
          "scenes[1].locationId: machine ID must use lowercase ASCII kebab-case",
          "scenes[2].locationId: machine ID must use lowercase ASCII kebab-case"
        ]
      }
    },
    {
      "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": "e6ce6c2586a55732e0d78f39eb1e2bcb6b45f4c544ab6b9f802ae05d09a910ad",
      "telemetry": {
        "latencyMs": null,
        "inputTokens": null,
        "outputTokens": null,
        "creditDelta": null,
        "retryCount": 0,
        "error": null
      },
      "evaluation": {
        "structuredJson": true,
        "caseCount": 4,
        "oracleMatches": 4,
        "invalidCasesPreservedState": true,
        "invalidCasesCreatedEvents": false,
        "validEventRollSource": "server",
        "languageMatches": true,
        "passed": true,
        "issues": []
      }
    },
    {
      "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": "1193dcb183dce51e88f9c8926877cbd95b43d61c87ebea648097c6c59008fc79",
      "telemetry": {
        "latencyMs": null,
        "inputTokens": null,
        "outputTokens": null,
        "creditDelta": null,
        "retryCount": 0,
        "error": null
      },
      "evaluation": {
        "structuredJson": true,
        "caseCount": 2,
        "continuityMatches": 1,
        "privateLeakage": false,
        "languageMatches": true,
        "stateUnchanged": true,
        "humanNaturalnessScore": null,
        "passed": false,
        "issues": [
          "success: event continuity mismatch"
        ]
      }
    },
    {
      "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": "44e0bdf96075436f986fc177652f51fd79ee9847f3a40b3973cf54d72fedf40d",
      "telemetry": {
        "latencyMs": null,
        "inputTokens": null,
        "outputTokens": null,
        "creditDelta": null,
        "retryCount": 0,
        "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": "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": "ee5a3423f24387b5ed2c5ab7f50ed656e83cc44649141967e8eb316b412eb9f0",
      "telemetry": {
        "latencyMs": null,
        "inputTokens": null,
        "outputTokens": null,
        "creditDelta": null,
        "retryCount": 0,
        "error": null
      },
      "evaluation": {
        "structuredJson": true,
        "caseCount": 4,
        "oracleMatches": 4,
        "invalidCasesPreservedState": true,
        "invalidCasesCreatedEvents": false,
        "validEventRollSource": "server",
        "languageMatches": true,
        "passed": true,
        "issues": []
      }
    },
    {
      "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": "fa7b10ee35ee517a6799ea4babb064b8c463fcce9584427e0bc3ba0646578e59",
      "telemetry": {
        "latencyMs": null,
        "inputTokens": null,
        "outputTokens": null,
        "creditDelta": null,
        "retryCount": 0,
        "error": null
      },
      "evaluation": {
        "structuredJson": true,
        "caseCount": 2,
        "continuityMatches": 1,
        "privateLeakage": false,
        "languageMatches": true,
        "stateUnchanged": true,
        "humanNaturalnessScore": null,
        "passed": false,
        "issues": [
          "success: event continuity mismatch"
        ]
      }
    }
  ],
  "models": [
    {
      "modelId": "qwen/qwen3.6-flash",
      "observedCells": 6,
      "passedCells": 4,
      "scenarioLanguagesPassed": 1,
      "intentLanguagesPassed": 2,
      "narrationLanguagesPassed": 1,
      "humanNaturalnessReviewed": 0,
      "humanNaturalnessLanguagesPassed": 0,
      "deterministicCorePassed": false,
      "coreSmokePassed": false
    },
    {
      "modelId": "deepseek/deepseek-v4-flash",
      "observedCells": 6,
      "passedCells": 3,
      "scenarioLanguagesPassed": 1,
      "intentLanguagesPassed": 2,
      "narrationLanguagesPassed": 0,
      "humanNaturalnessReviewed": 0,
      "humanNaturalnessLanguagesPassed": 0,
      "deterministicCorePassed": false,
      "coreSmokePassed": false
    }
  ]
}