{
  "format": "proofrun-publication",
  "schemaVersion": 3,
  "contentHash": "sha256:dd2bccfa455de50682e34b0024f6dda1997ebc131586150077b31b674120104e",
  "preparedAt": "2026-08-20T15:32:43.481Z",
  "editorial": {
    "format": "results-brief",
    "slug": "glm-5-3-and-gemini-3-7-flash-an-incomplete-orbit-radio-run",
    "headline": "glm-5.3 and gemini-3.7-flash: an incomplete Orbit Radio run",
    "dek": "One model produced a reviewable artifact and the other did not. Proofrun preserves the artifact assessment and the failure record without declaring an automatic head-to-head winner.",
    "status": "draft",
    "publishedAt": null
  },
  "experiment": {
    "protocol": "proofrun-v0.7",
    "mode": "duel",
    "runOutcome": "incomplete_comparison",
    "runId": "PR-MT1I9RG1-80",
    "startedAt": "2026-08-20T12:37:32.959Z",
    "identityState": "revealed",
    "evaluationState": "locked",
    "legacyProtocolException": false,
    "blindOrder": {
      "scheme": "sha256-128bit-assignment-commit-reveal-v1",
      "commitment": "sha256:bb9a65aa75a6826dbfa2036e45a926f1aacf2a2d50367463a7a24f5b7bb60416",
      "secret": "366C267432ED3A0267EFE5B141A08448",
      "verified": true
    }
  },
  "test": {
    "id": "orbit-radio",
    "title": "Orbit Radio",
    "category": "Interface design",
    "summary": "A tactile sci-fi tuner that tests hierarchy, motion, and input handling.",
    "prompt": "Create a one-screen browser instrument called ORBIT RADIO. A large central dial tunes between five fictional deep-space signals. Turning or dragging the dial must change the station name, frequency, color, and an animated signal visualization. Add compact previous/next controls and make the current station unmistakable. Use one self-contained HTML file with vanilla CSS and JavaScript, no external assets or libraries, and make it responsive.",
    "origin": "curated",
    "version": 3,
    "hash": "curated:orbit-radio:v3",
    "scope": "quick",
    "runtime": "7-12 min",
    "executionMode": "web-single-file-v2",
    "signals": [
      "Hierarchy",
      "Input quality",
      "Motion",
      "State design"
    ],
    "integrity": "versioned"
  },
  "settings": {
    "reasoningEffort": "high",
    "maxTokens": 32000,
    "temperature": 0.7,
    "htmlStartDeadlineMinutes": 20,
    "writingGraceMinutes": 10,
    "maxCostMicrousdPerAttempt": 5000000
  },
  "verdict": {
    "winner": null,
    "winnerModel": null,
    "confidence": "medium",
    "rationale": "Hard to review this incomplete artifact, barely anything to interact with, from what I can see the UI is okay but uninspired.",
    "scores": {
      "A": null,
      "B": 11
    },
    "evaluationVersion": 3,
    "scoreConstruct": "craft-score",
    "compliance": {
      "A": null,
      "B": 0
    },
    "identityGuess": {
      "recordedAt": "2026-08-20T12:53:52.779Z",
      "mapping": {
        "A": "z-ai/glm-5.3",
        "B": "google/gemini-3.7-flash"
      },
      "confidence": "high",
      "abstained": false
    }
  },
  "requirements": [
    {
      "id": "requirement-1",
      "label": "The central dial responds to turning or dragging.",
      "A": "unscored",
      "B": "fail"
    },
    {
      "id": "requirement-2",
      "label": "Five distinct fictional stations are available.",
      "A": "unscored",
      "B": "fail"
    },
    {
      "id": "requirement-3",
      "label": "Station name, frequency, color, and visualization change together.",
      "A": "unscored",
      "B": "fail"
    },
    {
      "id": "requirement-4",
      "label": "Previous and next controls work consistently.",
      "A": "unscored",
      "B": "fail"
    },
    {
      "id": "requirement-5",
      "label": "The current station is visually unmistakable.",
      "A": "unscored",
      "B": "fail"
    },
    {
      "id": "requirement-6",
      "label": "The single-file instrument remains responsive and works offline.",
      "A": "unscored",
      "B": "fail"
    }
  ],
  "criteria": [
    {
      "id": "visual-design",
      "label": "Visual design",
      "description": "Hierarchy, composition, typography, color, polish, and coherent visual judgment.",
      "weight": 30,
      "anchors": {
        "low": "Confusing or unfinished",
        "mid": "Competent and readable",
        "high": "Distinctive and exceptional"
      },
      "A": 5,
      "B": 3
    },
    {
      "id": "interaction",
      "label": "Interaction & usability",
      "description": "Discoverability, responsiveness, feedback, control quality, and interaction feel.",
      "weight": 30,
      "anchors": {
        "low": "Frustrating or broken",
        "mid": "Usable with rough edges",
        "high": "Immediate and delightful"
      },
      "A": 5,
      "B": 1
    },
    {
      "id": "technical-robustness",
      "label": "Technical robustness",
      "description": "Runtime correctness, edge-case handling, performance, responsiveness, and code reliability.",
      "weight": 30,
      "anchors": {
        "low": "Repeatable failures",
        "mid": "Mostly sound with risks",
        "high": "Stable under scrutiny"
      },
      "A": 5,
      "B": 1
    },
    {
      "id": "originality",
      "label": "Originality",
      "description": "Useful creative choices that go beyond a generic first solution without harming clarity.",
      "weight": 10,
      "anchors": {
        "low": "Generic or derivative",
        "mid": "Some authored character",
        "high": "Memorable and purposeful"
      },
      "A": 5,
      "B": 5
    }
  ],
  "contestants": [
    {
      "side": "A",
      "model": "z-ai/glm-5.3",
      "resolvedModel": "z-ai/glm-5.3",
      "provider": "Z.AI",
      "status": "truncated",
      "artifactOutcome": "invalid_or_non_reviewable_artifact",
      "selectedAttemptOrdinal": 1,
      "routing": {
        "mode": "auto",
        "endpointSlug": null,
        "allowFallbacks": true,
        "resolvedProvider": "Z.AI",
        "resolvedEndpoint": null
      },
      "screenshot": {
        "path": "screenshots/contestant-a-matched-initial-state-855067c0.png",
        "capturedAt": "2026-08-20T12:54:14.537Z",
        "width": 1280,
        "height": 720,
        "byteLength": 20831,
        "method": "browser-paint-isolated-v1",
        "rendererVersion": null,
        "cameraProvenance": null,
        "camera": null,
        "recipeReceipt": null
      },
      "scene": null,
      "artifact": null,
      "evidenceImages": [
        {
          "id": "EV-59e42303-49d9-4e3a-9c47-ecb0855067c0",
          "path": "screenshots/contestant-a-matched-initial-state-855067c0.png",
          "label": "Matched initial state",
          "caption": "Fresh artifact state captured at the same fixed 1280 × 720 viewport as the other contestant.",
          "provenance": "harness-matched",
          "state": "initial",
          "primary": true,
          "capturedAt": "2026-08-20T12:54:14.537Z",
          "width": 1280,
          "height": 720,
          "byteLength": 20831,
          "method": "browser-paint-isolated-v1",
          "rendererVersion": null,
          "cameraProvenance": null,
          "camera": null,
          "recipeReceipt": null
        }
      ],
      "generation": {
        "startedAt": "2026-08-20T12:37:33.162Z",
        "finishedAt": "2026-08-20T12:45:06.176Z",
        "wallTimeMs": 453014,
        "firstActivityMs": 4821,
        "htmlStartMs": null,
        "lastActivityMs": 452991,
        "activityChunks": 15944,
        "finishReason": "length",
        "reasoningEffort": "high"
      },
      "usage": {
        "inputTokens": 179,
        "visibleTokens": 56,
        "reasoningTokens": 15944,
        "cachedTokens": 0,
        "totalTokens": 16179,
        "cost": 0.0706506,
        "costSource": "openrouter-reported"
      },
      "evidence": {
        "artifactIssues": [
          "Token ceiling reached; the artifact is truncated.",
          "Visible response is unusually short for a complete web artifact.",
          "The model did not return a complete HTML document.",
          "Extracted artifact is below the minimum reviewable size.",
          "The web artifact is not reviewable because it contains no meaningful rendered document content.",
          "Preview appears visually blank: no visible elements or text were detected."
        ],
        "runtimeErrors": [],
        "previewAudit": {
          "textCharacters": 0,
          "visibleElements": 0,
          "bodyChildren": 0,
          "documentCharacters": 222056
        },
        "probe": null
      }
    },
    {
      "side": "B",
      "model": "google/gemini-3.7-flash",
      "resolvedModel": "google/gemini-3.7-flash",
      "provider": "Google AI Studio",
      "status": "truncated",
      "artifactOutcome": "truncated_submission",
      "selectedAttemptOrdinal": 1,
      "routing": {
        "mode": "auto",
        "endpointSlug": null,
        "allowFallbacks": true,
        "resolvedProvider": "Google AI Studio",
        "resolvedEndpoint": null
      },
      "screenshot": {
        "path": "screenshots/contestant-b-matched-initial-state-0902c60a.png",
        "capturedAt": "2026-08-20T12:54:16.774Z",
        "width": 1280,
        "height": 720,
        "byteLength": 480414,
        "method": "browser-paint-isolated-v1",
        "rendererVersion": null,
        "cameraProvenance": null,
        "camera": null,
        "recipeReceipt": null
      },
      "scene": null,
      "artifact": null,
      "evidenceImages": [
        {
          "id": "EV-b9f722c9-9f73-4e4a-9a8b-d7160902c60a",
          "path": "screenshots/contestant-b-matched-initial-state-0902c60a.png",
          "label": "Matched initial state",
          "caption": "Fresh artifact state captured at the same fixed 1280 × 720 viewport as the other contestant.",
          "provenance": "harness-matched",
          "state": "initial",
          "primary": true,
          "capturedAt": "2026-08-20T12:54:16.774Z",
          "width": 1280,
          "height": 720,
          "byteLength": 480414,
          "method": "browser-paint-isolated-v1",
          "rendererVersion": null,
          "cameraProvenance": null,
          "camera": null,
          "recipeReceipt": null
        }
      ],
      "generation": {
        "startedAt": "2026-08-20T12:37:33.162Z",
        "finishedAt": "2026-08-20T12:38:17.881Z",
        "wallTimeMs": 44719,
        "firstActivityMs": 2199,
        "htmlStartMs": 14834,
        "lastActivityMs": 44585,
        "activityChunks": 442,
        "finishReason": "length",
        "reasoningEffort": "high"
      },
      "usage": {
        "inputTokens": 174,
        "visibleTokens": 12385,
        "reasoningTokens": 3563,
        "cachedTokens": 0,
        "totalTokens": 16122,
        "cost": 0.0599355,
        "costSource": "openrouter-reported"
      },
      "evidence": {
        "artifactIssues": [
          "Token ceiling reached; the artifact is truncated.",
          "The closing HTML tag is missing.",
          "The closing body tag is missing."
        ],
        "runtimeErrors": [],
        "previewAudit": {
          "textCharacters": 644,
          "visibleElements": 104,
          "bodyChildren": 3,
          "documentCharacters": 256355
        },
        "probe": {
          "status": "passed",
          "durationMs": 506,
          "viewport": {
            "width": 527,
            "height": 520
          },
          "actions": [
            {
              "id": "resize",
              "label": "Narrow viewport",
              "status": "passed",
              "detail": "647 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": "invalid_or_non_reviewable_artifact",
      "terminalCause": "token_ceiling",
      "requestedModel": "z-ai/glm-5.3",
      "routingMode": "auto",
      "requestedEndpoint": null,
      "resolvedProvider": "Z.AI",
      "resolvedEndpoint": null,
      "resolvedModel": "z-ai/glm-5.3",
      "failure": null,
      "startedAt": "2026-08-20T12:37:33.162Z",
      "finishedAt": "2026-08-20T12:45:06.176Z"
    },
    {
      "side": "B",
      "ordinal": 1,
      "retryOfOrdinal": null,
      "lifecycle": "terminal",
      "artifactOutcome": "truncated_submission",
      "terminalCause": "token_ceiling",
      "requestedModel": "google/gemini-3.7-flash",
      "routingMode": "auto",
      "requestedEndpoint": null,
      "resolvedProvider": "Google AI Studio",
      "resolvedEndpoint": null,
      "resolvedModel": "google/gemini-3.7-flash",
      "failure": null,
      "startedAt": "2026-08-20T12:37:33.162Z",
      "finishedAt": "2026-08-20T12:38:17.881Z"
    }
  ],
  "protocolExceptions": [],
  "reviewAmendments": [],
  "disclosure": {
    "rawModelResponsesIncluded": false,
    "contestantSourceIncluded": false,
    "privateReviewerNotesIncluded": false,
    "credentialsIncluded": false,
    "generatedHtmlExecutedByPublicRecord": false,
    "generatedHtmlExecutedByJournal": false,
    "generatedHtmlAvailableInIsolatedSandbox": false,
    "rawSceneScriptIncluded": false,
    "compiledVoxelSceneIncluded": false,
    "editorialAssistance": {
      "evidenceAnalysis": null,
      "articleDrafting": null
    }
  }
}