{
  "schema_version": "remakebench.public-evidence.v1",
  "snapshot": {
    "benchmark_id": "tech-review-001",
    "benchmark_version": "v1",
    "immutable": true
  },
  "result_id": "space-flight-game-gpt-5.6-sol-ultra-pre-request-snapshot",
  "task": {
    "id": "space-flight-game-threejs",
    "title": "Three.js explorable star-system flight game",
    "benchmark_prompt_version": "v1"
  },
  "configuration": {
    "id": "sol-ultra",
    "model": "gpt-5.6-sol",
    "reasoning": "Ultra",
    "provider_agent": "OpenAI Codex"
  },
  "status": "partial_token_timing_and_source_ledger",
  "measurements": {
    "wall_clock_seconds": 2264.2,
    "wall_clock_display": "37:44.2",
    "total_processed_tokens": 25899289,
    "reported_cost_usd": 17.94
  },
  "cost_provenance": {
    "currency": "USD",
    "reported_total_basis": "per-ledger rounded total",
    "calculation_location": "api_cost.total_usd",
    "calculated_total_usd": 17.941646,
    "estimate_type": "user-supplied API-equivalent pre-request snapshot",
    "pricing_basis": null,
    "pricing_mode": "standard short-context rates as supplied; per-call long-context buckets were not supplied",
    "cache_write_assumption": null,
    "verified_live_pricing": null,
    "pricing_accessed_on": null,
    "pricing_sources": [
      "https://developers.openai.com/api/docs/pricing"
    ]
  },
  "primary_artifact": {
    "kind": "threejs-space-flight-game-primary-component",
    "sha256": "ea4a13f7873e1ef004ca05d5c88263cf3b50f5b7bf7aca196824d3f0388a4e93"
  },
  "public_standardized_captures": [
    {
      "kind": "poster",
      "url": "/campaign/browser/space-flight-sol.webp"
    },
    {
      "kind": "video",
      "url": "/campaign/browser/space-flight-sol.mp4"
    }
  ],
  "caveats": [
    "The supplied metrics name gpt-5.6-sol; that model ID is used instead of the surrounding GPT 5.5 label.",
    "This is a pre-request snapshot. The bundled post-generation meta.json represents a later, larger session and is not substituted for the supplied snapshot.",
    "The supplied cost applies standard short-context rates to the aggregate tokens. Per-call long-context usage was not supplied, so no context-bucket adjustment has been inferred.",
    "Wall-clock is end-to-end latency, not model-only compute. Cache-read tokens are discounted, so total processed tokens overstate cost as uncached volume."
  ],
  "missing_evidence": [
    "browser and hardware environment",
    "local FPS",
    "final capture",
    "blind-evaluation record"
  ],
  "source_provenance": {
    "harness_commit": "3f14507a8ce536d68a1f472f34f4c1a64c511f82",
    "source_record_sha256": "bc5346796faaa40bb40d8164694eabb7f502471dec45447119f8aeb69ab31d52",
    "primary_artifact_sha256_verified_at_source_commit": true
  }
}