{
  "schema": "certiv_public_ai_discovery_dossier_v1",
  "corpus_id": "certiv-ai-discovery-2026-07-16",
  "reviewed_at": "2026-07-16",
  "evidence_boundary": "These are Certiv-authored test dossiers, not author-issued Certiv receipts. A pinned PDF proves file identity only. A passing selected replay records one bounded observation; it does not independently reproduce a paper's central claim or establish truth, novelty, priority, safety, or correct interpretation.",
  "case": {
    "slug": "ai-scientist-v1",
    "case_type": "discovery-system",
    "domain": "Automated machine-learning research",
    "title": "The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery",
    "authors": {
      "display": "Chris Lu, Cong Lu, Robert Tjarko Lange, Jakob Foerster, Jeff Clune, and David Ha",
      "count": 6
    },
    "paper": {
      "arxiv_id": "2408.06292",
      "version": "v3",
      "submitted": "2024-08-12",
      "version_date": "2024-09-01",
      "abs_url": "https://arxiv.org/abs/2408.06292v3",
      "pdf_url": "https://arxiv.org/pdf/2408.06292v3",
      "pdf_sha256": "e911f90b0114d5e3fc23a0000177ea670fa9ed79d5f9a664efa2980fdb350507",
      "pdf_bytes": 11731143,
      "pages": 186,
      "extracted_text_bytes": 510675,
      "parser_observations": [
        "Recognized as a PDF and not encrypted.",
        "pdfinfo reported JavaScript: no.",
        "pdfdetach reported no embedded files.",
        "pdftotext completed successfully."
      ]
    },
    "selection_rationale": "An end-to-end automated-research system whose evaluation language tests whether Certiv distinguishes a simulated review threshold from real peer review or scientific correctness.",
    "claim": {
      "reported": "The authors report an automated workflow that generates ideas, edits code, runs experiments, writes papers, and evaluates them with an automated reviewer.",
      "certiv_observed": "The exact v3 PDF and public repository revision were pinned. The paper's headline acceptance language is explicitly based on an automated reviewer's threshold.",
      "not_established": "The generated papers were not shown by this dossier to be correct, novel, reproducible, or accepted by a real conference review process. The full workflow was not replayed."
    },
    "verification_level": "artifact-inventoried",
    "central_claim_independently_reproduced": false,
    "checks": [
      {
        "id": "pdf-identity",
        "status": "observed",
        "label": "Exact PDF identity",
        "observation": "The downloaded v3 PDF matched the recorded SHA-256, byte count, and page count.",
        "boundary": "This establishes file identity only."
      },
      {
        "id": "repository-inventory",
        "status": "observed",
        "label": "Public code inventory",
        "observation": "The official repository was pinned at commit 1de1dbc1f4ee2c5f61e9c94348d55eb51d7fa2eb.",
        "boundary": "The repository still requires models, API credentials, GPU resources, and external services."
      },
      {
        "id": "end-to-end-replay",
        "status": "not-run",
        "label": "End-to-end autonomous research run",
        "observation": "No model-funded, GPU-backed workflow was executed.",
        "boundary": "No generated paper or cost claim was reproduced."
      }
    ],
    "artifacts": [
      {
        "label": "Official AI Scientist repository",
        "url": "https://github.com/SakanaAI/AI-Scientist",
        "observed_revision": "1de1dbc1f4ee2c5f61e9c94348d55eb51d7fa2eb",
        "note": "Open code still depends on third-party models, APIs, external services, and substantial compute."
      }
    ],
    "red_team_findings": [
      "Passing an automated review threshold is not the same event as acceptance by human peer review.",
      "A generated manuscript is an output artifact, not proof that its scientific statements are true.",
      "Cost and autonomy claims depend on model versions, service behavior, templates, and external resources that can drift."
    ],
    "certiv_mapping": {
      "inputs": "Exact paper and commit-pinned public code.",
      "checks": "Identity, repository, dependency, and claim-semantics review.",
      "receipt_boundary": "artifact-inventoried; no end-to-end run",
      "missing_for_deeper_verification": "Pinned model identities, prompts, API behavior, templates, datasets, GPU environment, cost ledger, and independent review of each generated paper."
    },
    "sources": [
      {
        "label": "Exact arXiv record",
        "url": "https://arxiv.org/abs/2408.06292v3"
      },
      {
        "label": "Official repository",
        "url": "https://github.com/SakanaAI/AI-Scientist"
      }
    ]
  }
}