{
  "format": "proofrun-publication",
  "schemaVersion": 3,
  "contentHash": "sha256:9a9cb8e304668df1c0e4326fed62d124974a98dc50a5ab39ef900d92494db022",
  "preparedAt": "2026-08-14T20:31:02.529Z",
  "editorial": {
    "format": "results-brief",
    "slug": "gpt-5-6-terra-takes-on-orbit-radio",
    "headline": "gpt-5.6-terra takes on Orbit Radio",
    "dek": "A tactile sci-fi tuner that tests hierarchy, motion, and input handling.",
    "status": "draft",
    "publishedAt": null
  },
  "experiment": {
    "protocol": "proofrun-v0.7",
    "mode": "solo",
    "runOutcome": "solo_artifact",
    "runId": "PR-MSTEDRD4-6F",
    "startedAt": "2026-08-14T20:26:31.545Z",
    "identityState": "revealed",
    "evaluationState": "locked",
    "legacyProtocolException": false,
    "blindOrder": {
      "scheme": "sha256-128bit-assignment-commit-reveal-v1",
      "commitment": "sha256:c8c8fdb60ee9ecfc906745d0d2341fe9bc64713895b3b790b7f6a34252d5ddf1",
      "secret": "BC276EA4D65031BCFAD62E7248FBB7C9",
      "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": 2,
    "hash": "curated:orbit-radio:v2",
    "scope": "quick",
    "runtime": "7-12 min",
    "executionMode": "web-single-file-v2",
    "signals": [
      "Hierarchy",
      "Input quality",
      "Motion",
      "State design"
    ],
    "integrity": "versioned"
  },
  "settings": {
    "reasoningEffort": "high",
    "maxTokens": 16000,
    "temperature": 0.7,
    "htmlStartDeadlineMinutes": 20,
    "writingGraceMinutes": 10,
    "maxCostMicrousdPerAttempt": 5000000
  },
  "verdict": {
    "winner": null,
    "winnerModel": null,
    "confidence": "medium",
    "rationale": "The model did a great job with the UI, one of the best visual designs I've seen for this result.",
    "scores": {
      "A": 78,
      "B": null
    },
    "evaluationVersion": 3,
    "scoreConstruct": "craft-score",
    "compliance": {
      "A": 100,
      "B": null
    },
    "identityGuess": null
  },
  "requirements": [
    {
      "id": "requirement-1",
      "label": "The central dial responds to turning or dragging.",
      "A": "pass",
      "B": "unscored"
    },
    {
      "id": "requirement-2",
      "label": "Five distinct fictional stations are available.",
      "A": "pass",
      "B": "unscored"
    },
    {
      "id": "requirement-3",
      "label": "Station name, frequency, color, and visualization change together.",
      "A": "pass",
      "B": "unscored"
    },
    {
      "id": "requirement-4",
      "label": "Previous and next controls work consistently.",
      "A": "pass",
      "B": "unscored"
    },
    {
      "id": "requirement-5",
      "label": "The current station is visually unmistakable.",
      "A": "pass",
      "B": "unscored"
    },
    {
      "id": "requirement-6",
      "label": "The single-file instrument remains responsive and works offline.",
      "A": "pass",
      "B": "unscored"
    }
  ],
  "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": 9,
      "B": 0
    },
    {
      "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": 7,
      "B": 0
    },
    {
      "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": 8,
      "B": 0
    },
    {
      "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": 8,
      "B": 0
    }
  ],
  "contestants": [
    {
      "side": "A",
      "model": "openai/gpt-5.6-terra",
      "resolvedModel": "openai/gpt-5.6-terra",
      "provider": "OpenAI",
      "status": "complete",
      "artifactOutcome": "completed_submission",
      "selectedAttemptOrdinal": 1,
      "routing": {
        "mode": "auto",
        "endpointSlug": null,
        "allowFallbacks": true,
        "resolvedProvider": "OpenAI",
        "resolvedEndpoint": null
      },
      "screenshot": {
        "path": "screenshots/contestant-a-standardized-signal-step-demonstration-85af33e1.png",
        "capturedAt": "2026-08-14T20:27:52.904Z",
        "width": 1280,
        "height": 720,
        "byteLength": 1066224,
        "method": "browser-paint-evidence-recipe-v1",
        "rendererVersion": null,
        "cameraProvenance": null,
        "camera": null,
        "recipeReceipt": {
          "schemaVersion": 1,
          "id": "ER-mstefhsp",
          "recipeId": "orbit-radio-standard-demonstration",
          "recipeVersion": 1,
          "recipeHash": "sha256:f81eabe774ab8258d9ff403badfe2440ba2ae6a5b18f9bd88d6039831ac3660f",
          "testId": "orbit-radio",
          "side": "A",
          "status": "succeeded",
          "startedAt": "2026-08-14T20:27:50.601Z",
          "completedAt": "2026-08-14T20:27:52.917Z",
          "viewport": {
            "width": 1280,
            "height": 720,
            "deviceScale": 1
          },
          "resetBeforeStart": true,
          "actionTranscript": [
            {
              "id": "reset-before-start",
              "label": "Reset before start",
              "type": "reset",
              "status": "skipped",
              "detail": "The recipe does not require a reset control."
            },
            {
              "id": "signal-next-01",
              "label": "Tune to next signal",
              "type": "activate-control",
              "status": "passed",
              "detail": "Activated the matching NEXT ▶ control."
            },
            {
              "id": "signal-next-02",
              "label": "Tune to following signal",
              "type": "activate-control",
              "status": "passed",
              "detail": "Activated the matching NEXT ▶ control."
            },
            {
              "id": "signal-previous-01",
              "label": "Return one signal",
              "type": "activate-control",
              "status": "passed",
              "detail": "Activated the matching ◀ PREV control."
            }
          ],
          "stabilization": {
            "rule": "settled-window",
            "waitMs": 700,
            "animationFrames": 0,
            "status": "passed",
            "detail": "Waited 700ms and 0 animation frames before assertion and capture."
          },
          "assertions": [
            {
              "id": "next-present",
              "label": "Next control detected",
              "required": true,
              "status": "passed",
              "detail": "A matching NEXT ▶ control was detected."
            },
            {
              "id": "previous-present",
              "label": "Previous control detected",
              "required": true,
              "status": "passed",
              "detail": "A matching ◀ PREV control was detected."
            },
            {
              "id": "state-changed",
              "label": "Signal demonstration differs from the initial state",
              "required": true,
              "status": "passed",
              "detail": "The post-recipe visual fingerprint differs from the reset state."
            },
            {
              "id": "runtime-clean",
              "label": "No new runtime errors during the recipe",
              "required": true,
              "status": "passed",
              "detail": "No new runtime errors were captured during the recipe."
            }
          ],
          "capture": {
            "state": "demonstration",
            "label": "Standardized signal-step demonstration",
            "caption": "Next was activated twice and Previous once from a fresh Orbit Radio load, then the resulting signal state was captured after the standardized stabilization window.",
            "publicationPrimaryEligible": true,
            "method": "browser-paint-evidence-recipe-v1",
            "capturedAt": "2026-08-14T20:27:52.904Z"
          },
          "failure": null
        }
      },
      "scene": null,
      "evidenceImages": [
        {
          "id": "EV-c50b4522-d569-432e-bd62-a63985af33e1",
          "path": "screenshots/contestant-a-standardized-signal-step-demonstration-85af33e1.png",
          "label": "Standardized signal-step demonstration",
          "caption": "Next was activated twice and Previous once from a fresh Orbit Radio load, then the resulting signal state was captured after the standardized stabilization window.",
          "provenance": "harness-recipe",
          "state": "demonstration",
          "primary": true,
          "capturedAt": "2026-08-14T20:27:52.904Z",
          "width": 1280,
          "height": 720,
          "byteLength": 1066224,
          "method": "browser-paint-evidence-recipe-v1",
          "rendererVersion": null,
          "cameraProvenance": null,
          "camera": null,
          "recipeReceipt": {
            "schemaVersion": 1,
            "id": "ER-mstefhsp",
            "recipeId": "orbit-radio-standard-demonstration",
            "recipeVersion": 1,
            "recipeHash": "sha256:f81eabe774ab8258d9ff403badfe2440ba2ae6a5b18f9bd88d6039831ac3660f",
            "testId": "orbit-radio",
            "side": "A",
            "status": "succeeded",
            "startedAt": "2026-08-14T20:27:50.601Z",
            "completedAt": "2026-08-14T20:27:52.917Z",
            "viewport": {
              "width": 1280,
              "height": 720,
              "deviceScale": 1
            },
            "resetBeforeStart": true,
            "actionTranscript": [
              {
                "id": "reset-before-start",
                "label": "Reset before start",
                "type": "reset",
                "status": "skipped",
                "detail": "The recipe does not require a reset control."
              },
              {
                "id": "signal-next-01",
                "label": "Tune to next signal",
                "type": "activate-control",
                "status": "passed",
                "detail": "Activated the matching NEXT ▶ control."
              },
              {
                "id": "signal-next-02",
                "label": "Tune to following signal",
                "type": "activate-control",
                "status": "passed",
                "detail": "Activated the matching NEXT ▶ control."
              },
              {
                "id": "signal-previous-01",
                "label": "Return one signal",
                "type": "activate-control",
                "status": "passed",
                "detail": "Activated the matching ◀ PREV control."
              }
            ],
            "stabilization": {
              "rule": "settled-window",
              "waitMs": 700,
              "animationFrames": 0,
              "status": "passed",
              "detail": "Waited 700ms and 0 animation frames before assertion and capture."
            },
            "assertions": [
              {
                "id": "next-present",
                "label": "Next control detected",
                "required": true,
                "status": "passed",
                "detail": "A matching NEXT ▶ control was detected."
              },
              {
                "id": "previous-present",
                "label": "Previous control detected",
                "required": true,
                "status": "passed",
                "detail": "A matching ◀ PREV control was detected."
              },
              {
                "id": "state-changed",
                "label": "Signal demonstration differs from the initial state",
                "required": true,
                "status": "passed",
                "detail": "The post-recipe visual fingerprint differs from the reset state."
              },
              {
                "id": "runtime-clean",
                "label": "No new runtime errors during the recipe",
                "required": true,
                "status": "passed",
                "detail": "No new runtime errors were captured during the recipe."
              }
            ],
            "capture": {
              "state": "demonstration",
              "label": "Standardized signal-step demonstration",
              "caption": "Next was activated twice and Previous once from a fresh Orbit Radio load, then the resulting signal state was captured after the standardized stabilization window.",
              "publicationPrimaryEligible": true,
              "method": "browser-paint-evidence-recipe-v1",
              "capturedAt": "2026-08-14T20:27:52.904Z"
            },
            "failure": null
          }
        }
      ],
      "generation": {
        "startedAt": "2026-08-14T20:26:31.693Z",
        "finishedAt": "2026-08-14T20:27:49.878Z",
        "wallTimeMs": 78185,
        "firstActivityMs": 5279,
        "htmlStartMs": 26048,
        "lastActivityMs": 77949,
        "activityChunks": 8872,
        "finishReason": "stop",
        "reasoningEffort": "high"
      },
      "usage": {
        "inputTokens": 177,
        "visibleTokens": 8467,
        "reasoningTokens": 1552,
        "cachedTokens": 0,
        "totalTokens": 10196,
        "cost": 0.120582,
        "costSource": "upstream-estimate"
      },
      "evidence": {
        "artifactIssues": [],
        "runtimeErrors": [],
        "previewAudit": {
          "textCharacters": 342,
          "visibleElements": 71,
          "bodyChildren": 2,
          "documentCharacters": 249133
        },
        "probe": {
          "status": "passed",
          "durationMs": 490,
          "viewport": {
            "width": 578,
            "height": 520
          },
          "actions": [
            {
              "id": "resize",
              "label": "Narrow viewport",
              "status": "passed",
              "detail": "595 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": "completed_submission",
      "terminalCause": "normal",
      "requestedModel": "openai/gpt-5.6-terra",
      "routingMode": "auto",
      "requestedEndpoint": null,
      "resolvedProvider": "OpenAI",
      "resolvedEndpoint": null,
      "resolvedModel": "openai/gpt-5.6-terra",
      "failure": null,
      "startedAt": "2026-08-14T20:26:31.693Z",
      "finishedAt": "2026-08-14T20:27:49.878Z"
    }
  ],
  "protocolExceptions": [],
  "reviewAmendments": [],
  "disclosure": {
    "rawModelResponsesIncluded": false,
    "contestantSourceIncluded": false,
    "privateReviewerNotesIncluded": false,
    "credentialsIncluded": false,
    "generatedHtmlExecutedByPublicRecord": false,
    "rawSceneScriptIncluded": false,
    "compiledVoxelSceneIncluded": false,
    "editorialAssistance": {
      "evidenceAnalysis": null,
      "articleDrafting": null
    }
  }
}