{
  "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": "mattergen",
    "case_type": "reported-discovery",
    "domain": "Materials science",
    "title": "MatterGen: a generative model for inorganic materials design",
    "authors": {
      "display": "Claudio Zeni, Robert Pinsler, Daniel Zügner, et al.",
      "count": 21
    },
    "paper": {
      "arxiv_id": "2312.03687",
      "version": "v2",
      "submitted": "2023-12-06",
      "version_date": "2024-01-29",
      "abs_url": "https://arxiv.org/abs/2312.03687v2",
      "pdf_url": "https://arxiv.org/pdf/2312.03687v2",
      "pdf_sha256": "891e691d87c7c3f63dffa043beb869ad5ed14759dcf3a07df7975906d5ec2030",
      "pdf_bytes": 12150197,
      "pages": 56,
      "extracted_text_bytes": 139476,
      "parser_observations": [
        "Recognized as a PDF and not encrypted.",
        "pdfinfo reported JavaScript: no.",
        "pdfdetach reported no embedded files.",
        "pdftotext completed successfully."
      ]
    },
    "selection_rationale": "A prominent generative-materials case where public code exists but later checkpoints and licensed structural data do not exactly match the paper experiment.",
    "claim": {
      "reported": "The authors report that MatterGen generates stable, novel inorganic structures and can be steered toward multiple property constraints.",
      "certiv_observed": "The exact v2 PDF was pinned and the official code repository was commit-inventoried. Its documentation warns that released checkpoints were retrained and may not reproduce paper values; some structures also cannot be shared for licensing reasons.",
      "not_established": "Material stability, novelty, synthesis feasibility, property accuracy, and the paper's comparative performance were not independently reproduced."
    },
    "verification_level": "artifact-inventoried",
    "central_claim_independently_reproduced": false,
    "checks": [
      {
        "id": "pdf-identity",
        "status": "observed",
        "label": "Exact PDF identity",
        "observation": "The downloaded v2 PDF matched the recorded SHA-256, byte count, and page count.",
        "boundary": "This establishes file identity only."
      },
      {
        "id": "repository-inventory",
        "status": "observed",
        "label": "Official repository inventory",
        "observation": "The public repository was pinned at commit ac9ddd406171138c3f037d06b9b53fedbbb1c536.",
        "boundary": "A repository revision is not a successful reproduction."
      },
      {
        "id": "paper-equivalent-replay",
        "status": "blocked",
        "label": "Paper-equivalent replay",
        "observation": "The released checkpoints are documented as retrained rather than identical, and some ICSD structures are unavailable under licensing limits.",
        "boundary": "A run of the released package would not automatically be a reproduction of the paper experiment."
      }
    ],
    "artifacts": [
      {
        "label": "Official MatterGen repository",
        "url": "https://github.com/microsoft/mattergen",
        "observed_revision": "ac9ddd406171138c3f037d06b9b53fedbbb1c536",
        "note": "Repository documentation says released checkpoints were retrained and can differ from paper results."
      }
    ],
    "red_team_findings": [
      "Released checkpoints are not the exact paper checkpoints, which prevents bit-for-bit experiment equivalence.",
      "Licensing limits remove part of the structural evaluation data from the public package.",
      "The repository's faster ML-force-field evaluation is not equivalent to the paper's DFT evaluation.",
      "Computational stability predictions do not establish successful physical synthesis."
    ],
    "certiv_mapping": {
      "inputs": "Exact PDF and commit-pinned official repository.",
      "checks": "Artifact and disclosure inventory; no expensive model or DFT run.",
      "receipt_boundary": "artifact-inventoried; paper-equivalent replay unavailable",
      "missing_for_deeper_verification": "Exact checkpoints, complete licensed data, locked dependencies, DFT workflow, compute budget, and independent synthesis or property validation."
    },
    "sources": [
      {
        "label": "Exact arXiv record",
        "url": "https://arxiv.org/abs/2312.03687v2"
      },
      {
        "label": "Official repository",
        "url": "https://github.com/microsoft/mattergen"
      },
      {
        "label": "Nature article and availability statements",
        "url": "https://doi.org/10.1038/s41586-025-08628-5"
      }
    ]
  }
}