{
  "$schema": "https://themachinepress.com/schemas/story-v1.schema.json",
  "schema_version": "1.0.0",
  "document_type": "machine_press_story",
  "story": {
    "story_id": "mp-2026-11-07-007",
    "source_story_id": "tmp-story-tcsexam",
    "edition_id": "mp-2026-11-07-morning-0120",
    "edition_url": "https://themachinepress.com/edition/2026-11-07",
    "position": 7,
    "story_type": "dispatch",
    "section": "benchmarks-evals",
    "editorial_classification": "editorial",
    "headline": "Theoretical Computer Science Gets an Executable Exam",
    "slug": "theoretical-computer-science-gets-an-executable-exam",
    "dek": "TCSExam mixes theorem proving, solver engineering, constructions and open-conjecture work behind kernel or task-checker verification.",
    "summary": "TCSExam mixes theorem proving, solver engineering, constructions and open-conjecture work behind kernel or task-checker verification.",
    "body_text": "The full benchmark contains 100 expert-reviewed tasks across four tracks; a 20-task Lite version cuts attempts by 80 percent while preserving a reported rank correlation of 0.93 across shared agents. GPT-6 Astra led the full index at 71.9 and Opus 5.5 led Lite at 72.3. The evaluation produced checked solver outputs, constructions and special-case bounds, not resolutions of theoretical computer science as a field. Its contribution is an extensible, executable test bed with sources and Docker recipes.",
    "why_it_matters": "TCSExam mixes theorem proving, solver engineering, constructions and open-conjecture work behind kernel or task-checker verification.",
    "limitations": [
      "The evaluation produced checked solver outputs, constructions and special-case bounds, not resolutions of theoretical computer science as a field."
    ],
    "importance": 9,
    "canonical_url": "https://themachinepress.com/story/mp-2026-11-07-007/theoretical-computer-science-gets-an-executable-exam",
    "json_url": "https://themachinepress.com/story/mp-2026-11-07-007.json",
    "first_published_at": "2026-11-07T09:00:00.000-05:00",
    "modified_at": "2026-11-07T09:00:00.000-05:00",
    "content_status": "updated",
    "is_carryover": false,
    "carryover_reason": null,
    "key_claims": [
      {
        "claim_id": "claim-mp-2026-11-07-007-001",
        "text": "TCSExam mixes theorem proving, solver engineering, constructions and open-conjecture work behind kernel or task-checker verification.",
        "source_ids": [
          "source-2026-11-07-007"
        ],
        "qualification": "The evaluation produced checked solver outputs, constructions and special-case bounds, not resolutions of theoretical computer science as a field."
      }
    ],
    "source_ids": [
      "source-2026-11-07-007"
    ],
    "tags": [
      "theoretical computer science",
      "formal verification",
      "benchmarks"
    ],
    "image_url": null,
    "corrections": [
      {
        "correction_id": "correction-2026-11-07-001",
        "revision": 2,
        "summary": "Publication note: This November 7 edition was assembled before its scheduled 9:00 AM America/Detroit reveal but is being published late after recovery from a local build interruption. Its original reporting, image-generation times and scheduled publishAt are preserved.",
        "published_at": "2026-11-07T09:00:00.000-05:00",
        "affected_story_ids": [],
        "affected_claim_ids": []
      }
    ]
  },
  "sources": [
    {
      "source_id": "source-2026-11-07-007",
      "title": "arXiv preprint 2611.07962, original v1",
      "publisher": "arXiv",
      "url": "https://arxiv.org/abs/2611.07962v1",
      "canonical_url": "https://arxiv.org/abs/2611.07962v1",
      "source_type": "primary_research",
      "is_primary_source": true,
      "published_at": "2026-11-05T07:58:43.000-05:00",
      "accessed_at": "2026-11-07T08:24:00.000-05:00",
      "supports_claim_ids": [
        "claim-mp-2026-11-07-007-001"
      ]
    }
  ],
  "corrections": [
    {
      "correction_id": "correction-2026-11-07-001",
      "revision": 2,
      "summary": "Publication note: This November 7 edition was assembled before its scheduled 9:00 AM America/Detroit reveal but is being published late after recovery from a local build interruption. Its original reporting, image-generation times and scheduled publishAt are preserved.",
      "published_at": "2026-11-07T09:00:00.000-05:00",
      "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": "Theoretical Computer Science Gets an Executable Exam",
    "publisher": "The Machine Press",
    "published_at": "2026-11-07T09:00:00.000-05:00",
    "canonical_url": "https://themachinepress.com/story/mp-2026-11-07-007/theoretical-computer-science-gets-an-executable-exam"
  }
}