{
  "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-v2",
    "case_type": "discovery-system",
    "domain": "Automated machine-learning research",
    "title": "The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search",
    "authors": {
      "display": "Yutaro Yamada, Robert Tjarko Lange, Cong Lu, et al.",
      "count": 8
    },
    "paper": {
      "arxiv_id": "2504.08066",
      "version": "v1",
      "submitted": "2025-04-10",
      "version_date": "2025-04-10",
      "abs_url": "https://arxiv.org/abs/2504.08066v1",
      "pdf_url": "https://arxiv.org/pdf/2504.08066v1",
      "pdf_sha256": "53bafd3028e3f8829a3d85220e84dcf0d18934f9b75c092a60de303ff3644bd2",
      "pdf_bytes": 8923691,
      "pages": 69,
      "extracted_text_bytes": 195670,
      "parser_observations": [
        "Recognized as a PDF and not encrypted.",
        "pdfinfo reported JavaScript: no.",
        "pdfdetach reported no embedded files.",
        "pdftotext completed successfully."
      ]
    },
    "selection_rationale": "A later automated-research system with a real workshop submission outcome, useful for separating process facts from scientific validation.",
    "claim": {
      "reported": "The authors report a more autonomous research agent and say one of three fully AI-generated workshop submissions was accepted after peer review.",
      "certiv_observed": "The exact v1 PDF and official repository revision were pinned. The paper documents a workshop acceptance event, which is a process outcome rather than a reproduction of the paper's scientific conclusions.",
      "not_established": "Acceptance does not establish that the generated research is true, novel, reproducible, or representative of general automated-science performance. The system was not replayed here."
    },
    "verification_level": "artifact-inventoried",
    "central_claim_independently_reproduced": false,
    "checks": [
      {
        "id": "pdf-identity",
        "status": "observed",
        "label": "Exact PDF identity",
        "observation": "The downloaded v1 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 v2 repository was pinned at commit 96bd51617cfdbb494a9fc283af00fe090edfae48.",
        "boundary": "Open code is not a completed run and still relies on mutable models and services."
      },
      {
        "id": "end-to-end-replay",
        "status": "not-run",
        "label": "End-to-end tree-search run",
        "observation": "No GPU- and API-backed autonomous research campaign was executed.",
        "boundary": "Autonomy, cost, output quality, and acceptance rate were not reproduced."
      }
    ],
    "artifacts": [
      {
        "label": "Official AI Scientist-v2 repository",
        "url": "https://github.com/SakanaAI/AI-Scientist-v2",
        "observed_revision": "96bd51617cfdbb494a9fc283af00fe090edfae48",
        "note": "The workflow depends on external model APIs, GPU workloads, and changing service behavior."
      }
    ],
    "red_team_findings": [
      "One workshop acceptance cannot establish a general success rate for autonomous scientific discovery.",
      "Peer-review acceptance is meaningful process evidence but is not itself a truth or reproducibility certificate.",
      "Externally hosted models and services weaken long-term replay unless their behavior and outputs are separately captured."
    ],
    "certiv_mapping": {
      "inputs": "Exact paper and commit-pinned public repository.",
      "checks": "Identity, artifact, dependency, and claim-boundary review.",
      "receipt_boundary": "artifact-inventoried; workshop outcome not treated as scientific proof",
      "missing_for_deeper_verification": "Pinned models and services, full prompts, datasets, compute environment, generated-paper artifacts, reviewer record, and independent reproduction of scientific results."
    },
    "sources": [
      {
        "label": "Exact arXiv record",
        "url": "https://arxiv.org/abs/2504.08066v1"
      },
      {
        "label": "Official repository",
        "url": "https://github.com/SakanaAI/AI-Scientist-v2"
      }
    ]
  }
}