{
  "$schema": "https://themachinepress.com/schemas/story-v1.schema.json",
  "schema_version": "1.0.0",
  "document_type": "machine_press_story",
  "story": {
    "story_id": "mp-2026-10-15-014",
    "source_story_id": "tmp-story-flmf-mechanical-formalization-checks",
    "edition_id": "mp-2026-10-15-morning-0097",
    "edition_url": "https://themachinepress.com/edition/2026-10-15",
    "position": 14,
    "story_type": "dispatch",
    "section": "developer-tools",
    "editorial_classification": "editorial",
    "headline": "Formal Math Gets Checks an LLM Judge Cannot Bluff",
    "slug": "formal-math-gets-checks-an-llm-judge-cannot-bluff",
    "dek": "A verification pipeline combines semantic review with numerical and vacuity tests that produce checkable failures for Lean translations.",
    "summary": "A verification pipeline combines semantic review with numerical and vacuity tests that produce checkable failures for Lean translations.",
    "body_text": "A proof assistant can accept a formally valid statement that mistranslates the source or says something vacuous. This work supplements language-model review with mechanical numerical and vacuity checks, then uses the process in an Extract-Verify-Proof pipeline for a partial formalization of the NIST Digital Library of Mathematical Functions. Across three labeled datasets, the authors report the lowest accepted-error rate among compared methods, while expert review found defects in both translations and source datasets. The result supports layered verification rather than replacing mathematical expertise.",
    "why_it_matters": "A verification pipeline combines semantic review with numerical and vacuity tests that produce checkable failures for Lean translations.",
    "limitations": [],
    "importance": 7,
    "canonical_url": "https://themachinepress.com/story/mp-2026-10-15-014/formal-math-gets-checks-an-llm-judge-cannot-bluff",
    "json_url": "https://themachinepress.com/story/mp-2026-10-15-014.json",
    "first_published_at": "2026-10-15T09:00:00.000-04:00",
    "modified_at": "2026-10-15T09:00:00.000-04:00",
    "content_status": "updated",
    "is_carryover": false,
    "carryover_reason": null,
    "key_claims": [
      {
        "claim_id": "claim-mp-2026-10-15-014-001",
        "text": "A verification pipeline combines semantic review with numerical and vacuity tests that produce checkable failures for Lean translations.",
        "source_ids": [
          "source-2026-10-15-014"
        ],
        "qualification": null
      }
    ],
    "source_ids": [
      "source-2026-10-15-014"
    ],
    "tags": [
      "Lean",
      "formal verification",
      "autoformalization"
    ],
    "image_url": null,
    "corrections": [
      {
        "correction_id": "correction-2026-10-15-001",
        "revision": 2,
        "summary": "Publication note: This October 15 edition was prepared before its scheduled 9:00 AM America/Detroit reveal, but publication was delayed by a production build failure. The original reporting and image-generation timestamps are preserved.",
        "published_at": "2026-10-15T09:00:00.000-04:00",
        "affected_story_ids": [],
        "affected_claim_ids": []
      }
    ]
  },
  "sources": [
    {
      "source_id": "source-2026-10-15-014",
      "title": "arXiv preprint 2610.20573, original v1",
      "publisher": "arXiv / submitting research authors",
      "url": "https://arxiv.org/abs/2610.20573v1",
      "canonical_url": "https://arxiv.org/abs/2610.20573v1",
      "source_type": "primary_research",
      "is_primary_source": true,
      "published_at": "2026-10-14T13:54:48.000-04:00",
      "accessed_at": "2026-10-15T08:28:29.903-04:00",
      "supports_claim_ids": [
        "claim-mp-2026-10-15-014-001"
      ]
    }
  ],
  "corrections": [
    {
      "correction_id": "correction-2026-10-15-001",
      "revision": 2,
      "summary": "Publication note: This October 15 edition was prepared before its scheduled 9:00 AM America/Detroit reveal, but publication was delayed by a production build failure. The original reporting and image-generation timestamps are preserved.",
      "published_at": "2026-10-15T09:00:00.000-04:00",
      "affected_story_ids": [],
      "affected_claim_ids": []
    }
  ],
  "publisher": {
    "name": "The Machine Press",
    "url": "https://themachinepress.com",
    "description": "A daily newspaper for the age of artificial intelligence."
  },
  "cite_this_report": {
    "title": "Formal Math Gets Checks an LLM Judge Cannot Bluff",
    "publisher": "The Machine Press",
    "published_at": "2026-10-15T09:00:00.000-04:00",
    "canonical_url": "https://themachinepress.com/story/mp-2026-10-15-014/formal-math-gets-checks-an-llm-judge-cannot-bluff"
  }
}