{
  "format": "proofrun-publication",
  "schemaVersion": 3,
  "contentHash": "sha256:828ab0d2a0f5ec64fa258964148301b79f9f4ce767da46382d0ce185e4216538",
  "preparedAt": "2026-08-12T09:27:27.296Z",
  "editorial": {
    "slug": "deepseek-v4-flash-0731-vs-hy3-weather-story",
    "headline": "deepseek-v4-flash-0731 vs hy3: Weather Story",
    "dek": "Turns the same small dataset into a useful, visually opinionated forecast.",
    "status": "draft",
    "publishedAt": null
  },
  "experiment": {
    "protocol": "proofrun-v0.7",
    "mode": "duel",
    "runOutcome": "head_to_head",
    "runId": "PR-MSP08AE0-1E",
    "startedAt": "2026-08-11T18:39:16.632Z",
    "identityState": "revealed",
    "evaluationState": "locked",
    "legacyProtocolException": false
  },
  "test": {
    "id": "weather-story",
    "title": "Weather Story",
    "category": "Data visualization",
    "summary": "Turns the same small dataset into a useful, visually opinionated forecast.",
    "prompt": "Design a polished one-page weather experience for Helsinki using this fixed six-hour temperature sequence: 12 degrees, 13 degrees, 15 degrees, 14 degrees, 11 degrees, 9 degrees. Show the progression visually, highlight the warmest hour, and include wind and rain probability as invented but clearly labeled demo data. Add one meaningful hover or tap interaction. Use one offline HTML file with vanilla CSS and JavaScript; no libraries, APIs, or external assets.",
    "origin": "curated",
    "version": 1,
    "hash": "curated:weather-story:v1",
    "scope": "quick",
    "runtime": "8-12 min",
    "executionMode": "web-single-file-v2",
    "signals": [
      "Data clarity",
      "Visual encoding",
      "Responsiveness",
      "Restraint"
    ],
    "integrity": "versioned"
  },
  "settings": {
    "reasoningEffort": "high",
    "maxTokens": 32000,
    "temperature": 0.7,
    "htmlStartDeadlineMinutes": 20,
    "writingGraceMinutes": 10,
    "maxCostMicrousdPerAttempt": 5000000
  },
  "verdict": {
    "winner": "A",
    "winnerModel": "deepseek/deepseek-v4-flash-0731",
    "confidence": "medium",
    "rationale": "Contestant A's result is visually much more interesting and polished.",
    "scores": {
      "A": 92,
      "B": 90
    }
  },
  "requirements": [
    {
      "id": "requirement-1",
      "label": "All six supplied temperature values are represented accurately.",
      "A": "pass",
      "B": "pass"
    },
    {
      "id": "requirement-2",
      "label": "The temperature progression is communicated visually.",
      "A": "pass",
      "B": "pass"
    },
    {
      "id": "requirement-3",
      "label": "The 15-degree warmest hour is clearly highlighted.",
      "A": "pass",
      "B": "pass"
    },
    {
      "id": "requirement-4",
      "label": "Wind and rain probability are clearly labeled as demo data.",
      "A": "pass",
      "B": "pass"
    },
    {
      "id": "requirement-5",
      "label": "At least one meaningful hover or tap interaction works.",
      "A": "pass",
      "B": "pass"
    },
    {
      "id": "requirement-6",
      "label": "The single-file experience remains responsive and works offline.",
      "A": "pass",
      "B": "pass"
    }
  ],
  "criteria": [
    {
      "id": "requirement-fit",
      "label": "Requirement fit",
      "description": "How completely and accurately the artifact satisfies the frozen brief.",
      "weight": 25,
      "anchors": {
        "low": "Major requirements missing",
        "mid": "Core brief met with gaps",
        "high": "Complete and exact"
      },
      "A": 10,
      "B": 10
    },
    {
      "id": "information-clarity",
      "label": "Information clarity",
      "description": "Accuracy, hierarchy, visual encoding, labels, and ease of reading the supplied data.",
      "weight": 25,
      "anchors": {
        "low": "Misleading or unclear",
        "mid": "Readable with minor ambiguity",
        "high": "Immediate and precise"
      },
      "A": 8,
      "B": 9
    },
    {
      "id": "visual-design",
      "label": "Visual design",
      "description": "Hierarchy, composition, typography, color, polish, and coherent visual judgment.",
      "weight": 20,
      "anchors": {
        "low": "Confusing or unfinished",
        "mid": "Competent and readable",
        "high": "Distinctive and exceptional"
      },
      "A": 9,
      "B": 6
    },
    {
      "id": "interaction",
      "label": "Interaction & usability",
      "description": "Discoverability, responsiveness, feedback, control quality, and interaction feel.",
      "weight": 15,
      "anchors": {
        "low": "Frustrating or broken",
        "mid": "Usable with rough edges",
        "high": "Immediate and delightful"
      },
      "A": 9,
      "B": 10
    },
    {
      "id": "technical-robustness",
      "label": "Technical robustness",
      "description": "Runtime correctness, edge-case handling, performance, responsiveness, and code reliability.",
      "weight": 15,
      "anchors": {
        "low": "Repeatable failures",
        "mid": "Mostly sound with risks",
        "high": "Stable under scrutiny"
      },
      "A": 10,
      "B": 10
    }
  ],
  "contestants": [
    {
      "side": "A",
      "model": "deepseek/deepseek-v4-flash-0731",
      "resolvedModel": "deepseek/deepseek-v4-flash-0731",
      "provider": "Decart",
      "status": "complete",
      "artifactOutcome": "completed_submission",
      "selectedAttemptOrdinal": 2,
      "routing": {
        "mode": "auto",
        "endpointSlug": null,
        "allowFallbacks": true,
        "resolvedProvider": "Decart",
        "resolvedEndpoint": null
      },
      "screenshot": {
        "path": "screenshots/contestant-a-capture-lab-interaction-state-9c63614e.png",
        "capturedAt": "2026-08-11T19:14:40.701Z",
        "width": 1280,
        "height": 720,
        "byteLength": 416029,
        "method": "browser-paint-capture-lab-v1",
        "rendererVersion": null,
        "cameraProvenance": null,
        "camera": null
      },
      "scene": null,
      "evidenceImages": [
        {
          "id": "EV-c9a32b29-51a8-43bb-b8e3-67289c63614e",
          "path": "screenshots/contestant-a-capture-lab-interaction-state-9c63614e.png",
          "label": "Capture Lab interaction state",
          "caption": "State manually created by the reviewer in the isolated Capture Lab, The colored temperature bars are visible in the running artifact but were omitted by the standardized serialized capture renderer.",
          "provenance": "harness-current-state",
          "state": "manual",
          "primary": true,
          "capturedAt": "2026-08-11T19:14:40.701Z",
          "width": 1280,
          "height": 720,
          "byteLength": 416029,
          "method": "browser-paint-capture-lab-v1",
          "rendererVersion": null,
          "cameraProvenance": null,
          "camera": null
        }
      ],
      "generation": {
        "startedAt": "2026-08-11T18:46:02.918Z",
        "finishedAt": "2026-08-11T18:49:35.507Z",
        "wallTimeMs": 212589,
        "firstActivityMs": 807,
        "htmlStartMs": 162484,
        "lastActivityMs": 212513,
        "activityChunks": 2230,
        "finishReason": "stop",
        "reasoningEffort": "high"
      },
      "usage": {
        "inputTokens": 185,
        "visibleTokens": 4267,
        "reasoningTokens": 13561,
        "cachedTokens": 0,
        "totalTokens": 18013,
        "cost": 0.002580552,
        "costSource": "openrouter-reported"
      },
      "evidence": {
        "artifactIssues": [],
        "runtimeErrors": [],
        "previewAudit": {
          "textCharacters": 209,
          "visibleElements": 35,
          "bodyChildren": 3,
          "documentCharacters": 226812
        },
        "probe": {
          "status": "passed",
          "durationMs": 491,
          "viewport": {
            "width": 536,
            "height": 520
          },
          "actions": [
            {
              "id": "resize",
              "label": "Narrow viewport",
              "status": "passed",
              "detail": "536 x 520 viewport exercised"
            },
            {
              "id": "click",
              "label": "Single click",
              "status": "passed",
              "detail": "Dispatched one complete pointer and mouse click sequence"
            },
            {
              "id": "drag",
              "label": "Short drag",
              "status": "passed",
              "detail": "Dispatched a bounded six-step diagonal drag"
            },
            {
              "id": "burst",
              "label": "Five-point burst",
              "status": "passed",
              "detail": "Dispatched five bounded clicks across the interaction surface"
            },
            {
              "id": "reset",
              "label": "Reset control",
              "status": "skipped",
              "detail": "No reset, clear, or restart control was detected"
            }
          ],
          "issues": [],
          "errors": []
        }
      }
    },
    {
      "side": "B",
      "model": "tencent/hy3",
      "resolvedModel": "tencent/hy3",
      "provider": "Tencent",
      "status": "complete",
      "artifactOutcome": "completed_submission",
      "selectedAttemptOrdinal": 1,
      "routing": {
        "mode": "auto",
        "endpointSlug": null,
        "allowFallbacks": true,
        "resolvedProvider": "Tencent",
        "resolvedEndpoint": null
      },
      "screenshot": {
        "path": "screenshots/contestant-b-capture-lab-interaction-state-1127ec35.png",
        "capturedAt": "2026-08-11T19:31:43.688Z",
        "width": 1280,
        "height": 720,
        "byteLength": 511104,
        "method": "browser-paint-capture-lab-v1",
        "rendererVersion": null,
        "cameraProvenance": null,
        "camera": null
      },
      "scene": null,
      "evidenceImages": [
        {
          "id": "EV-861ba9fc-689f-4531-a649-ad531127ec35",
          "path": "screenshots/contestant-b-capture-lab-interaction-state-1127ec35.png",
          "label": "Capture Lab interaction state",
          "caption": "State manually created by the reviewer in the isolated Capture Lab.",
          "provenance": "harness-current-state",
          "state": "manual",
          "primary": true,
          "capturedAt": "2026-08-11T19:31:43.688Z",
          "width": 1280,
          "height": 720,
          "byteLength": 511104,
          "method": "browser-paint-capture-lab-v1",
          "rendererVersion": null,
          "cameraProvenance": null,
          "camera": null
        }
      ],
      "generation": {
        "startedAt": "2026-08-11T18:39:17.001Z",
        "finishedAt": "2026-08-11T18:41:38.219Z",
        "wallTimeMs": 141218,
        "firstActivityMs": 6591,
        "htmlStartMs": 115881,
        "lastActivityMs": 140851,
        "activityChunks": 6240,
        "finishReason": "stop",
        "reasoningEffort": "high"
      },
      "usage": {
        "inputTokens": 191,
        "visibleTokens": 3022,
        "reasoningTokens": 11910,
        "cachedTokens": 0,
        "totalTokens": 15123,
        "cost": 0.007909308,
        "costSource": "openrouter-reported"
      },
      "evidence": {
        "artifactIssues": [],
        "runtimeErrors": [],
        "previewAudit": {
          "textCharacters": 380,
          "visibleElements": 50,
          "bodyChildren": 2,
          "documentCharacters": 216790
        },
        "probe": {
          "status": "passed",
          "durationMs": 493,
          "viewport": {
            "width": 536,
            "height": 520
          },
          "actions": [
            {
              "id": "resize",
              "label": "Narrow viewport",
              "status": "passed",
              "detail": "536 x 520 viewport exercised"
            },
            {
              "id": "click",
              "label": "Single click",
              "status": "passed",
              "detail": "Dispatched one complete pointer and mouse click sequence"
            },
            {
              "id": "drag",
              "label": "Short drag",
              "status": "passed",
              "detail": "Dispatched a bounded six-step diagonal drag"
            },
            {
              "id": "burst",
              "label": "Five-point burst",
              "status": "passed",
              "detail": "Dispatched five bounded clicks across the interaction surface"
            },
            {
              "id": "reset",
              "label": "Reset control",
              "status": "skipped",
              "detail": "No reset, clear, or restart control was detected"
            }
          ],
          "issues": [],
          "errors": []
        }
      }
    }
  ],
  "attempts": [
    {
      "side": "A",
      "ordinal": 1,
      "retryOfOrdinal": null,
      "lifecycle": "terminal",
      "artifactOutcome": "truncated_submission",
      "terminalCause": "token_ceiling",
      "requestedModel": "deepseek/deepseek-v4-flash-0731",
      "routingMode": "auto",
      "requestedEndpoint": null,
      "resolvedProvider": "Baidu",
      "resolvedEndpoint": null,
      "resolvedModel": "deepseek/deepseek-v4-flash-0731",
      "failure": null,
      "startedAt": "2026-08-11T18:39:17.001Z",
      "finishedAt": "2026-08-11T18:45:30.566Z"
    },
    {
      "side": "A",
      "ordinal": 2,
      "retryOfOrdinal": 1,
      "lifecycle": "terminal",
      "artifactOutcome": "completed_submission",
      "terminalCause": "normal",
      "requestedModel": "deepseek/deepseek-v4-flash-0731",
      "routingMode": "auto",
      "requestedEndpoint": null,
      "resolvedProvider": "Decart",
      "resolvedEndpoint": null,
      "resolvedModel": "deepseek/deepseek-v4-flash-0731",
      "failure": null,
      "startedAt": "2026-08-11T18:46:02.918Z",
      "finishedAt": "2026-08-11T18:49:35.507Z"
    },
    {
      "side": "B",
      "ordinal": 1,
      "retryOfOrdinal": null,
      "lifecycle": "terminal",
      "artifactOutcome": "completed_submission",
      "terminalCause": "normal",
      "requestedModel": "tencent/hy3",
      "routingMode": "auto",
      "requestedEndpoint": null,
      "resolvedProvider": "Tencent",
      "resolvedEndpoint": null,
      "resolvedModel": "tencent/hy3",
      "failure": null,
      "startedAt": "2026-08-11T18:39:17.001Z",
      "finishedAt": "2026-08-11T18:41:38.219Z"
    }
  ],
  "protocolExceptions": [],
  "reviewAmendments": [],
  "disclosure": {
    "rawModelResponsesIncluded": false,
    "contestantSourceIncluded": false,
    "privateReviewerNotesIncluded": false,
    "credentialsIncluded": false,
    "generatedHtmlExecutedByPublicRecord": false,
    "rawSceneScriptIncluded": false,
    "compiledVoxelSceneIncluded": false,
    "editorialAssistance": {
      "evidenceAnalysis": {
        "model": "openai/gpt-5.6-sol",
        "promptVersion": "evidence-analyst-v3",
        "blind": true,
        "cost": 0.20455375,
        "acceptedFindings": 9,
        "rejectedFindings": 0,
        "calibration": {
          "promptVersion": "evaluator-calibration-v1",
          "repeatConsistency": 0,
          "swapConsistency": 0.222,
          "positionSensitivity": 0.778,
          "rating": "insufficient",
          "createdAt": "2026-08-11T19:25:34.108Z"
        }
      },
      "articleDrafting": null
    }
  }
}