{
  "apiVersion": "v1",
  "methodology": "https://sourcescore.org/methodology/",
  "canonical": "https://sourcescore.org/claims/26f75f130f7b395a/",
  "claim": {
    "vertical": "ai-ml",
    "subject": "GPQA benchmark",
    "predicate": "introduced_in_paper",
    "object": "GPQA: A Graduate-Level Google-Proof Q&A Benchmark (Rein et al., 2023)",
    "confidence": 0.92,
    "sources": [
      {
        "url": "https://arxiv.org/abs/2311.12022",
        "title": "GPQA: A Graduate-Level Google-Proof Q&A Benchmark",
        "publisher": "arXiv (Rein, Hou, Stickland, Petty, Pang, Dirani, Michael, Bowman)",
        "publishedDate": "2023-11-20",
        "accessedDate": "2026-05-31",
        "type": "preprint",
        "excerpt": "We present GPQA, a challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry."
      },
      {
        "url": "https://github.com/idavidrein/gpqa",
        "title": "GPQA reference repository",
        "publisher": "David Rein (idavidrein)",
        "publishedDate": "2023-11-20",
        "accessedDate": "2026-05-31",
        "type": "github-release"
      },
      {
        "url": "https://huggingface.co/datasets/Idavidrein/gpqa",
        "title": "GPQA dataset card",
        "publisher": "Hugging Face",
        "accessedDate": "2026-05-31",
        "type": "model-card"
      }
    ],
    "publishedAt": "2026-05-31T00:00:00Z",
    "lastVerified": "2026-05-31",
    "methodologyVersion": "veritas-v0.1",
    "tags": [
      "gpqa",
      "benchmark",
      "evaluation",
      "graduate-level",
      "google-proof",
      "reasoning",
      "rein",
      "2023"
    ],
    "id": "26f75f130f7b395a",
    "statement": "GPQA benchmark introduced in paper: GPQA: A Graduate-Level Google-Proof Q&A Benchmark (Rein et al., 2023)."
  },
  "signature": {
    "algorithm": "HMAC-SHA256",
    "signedBy": "did:web:sourcescore.org",
    "signedAt": "2026-05-31T00:00:00.000Z",
    "signature": "f6855c02f1e5d0f4205f4f2579deb319788c1dbd8e1cc79d80d28ad987c0797b"
  },
  "citedAs": "GPQA benchmark introduced in paper: GPQA: A Graduate-Level Google-Proof Q&A Benchmark (Rein et al., 2023). — SourceScore Claim 26f75f130f7b395a (verified 2026-05-31, signed f6855c02…). https://sourcescore.org/claims/26f75f130f7b395a/"
}