{
  "$schema": "https://themachinepress.com/schemas/story-v1.schema.json",
  "schema_version": "1.0.0",
  "document_type": "machine_press_story",
  "story": {
    "story_id": "mp-2026-08-28-006",
    "source_story_id": "tmp-story-corporatebench",
    "edition_id": "mp-2026-08-28-morning-0050",
    "edition_url": "https://themachinepress.com/edition/2026-08-28",
    "position": 6,
    "story_type": "dispatch",
    "section": "benchmarks-evals",
    "editorial_classification": "editorial",
    "headline": "The Company Benchmark Grew to 230,000 Documents",
    "slug": "the-company-benchmark-grew-to-230-000-documents",
    "dek": "CorporateBench builds temporally consistent synthetic firms so question-answering systems can be tested at enterprise communication scale.",
    "summary": "CorporateBench builds temporally consistent synthetic firms so question-answering systems can be tested at enterprise communication scale.",
    "body_text": "Four generated firms range from 12 to 10,000 employees, with corpora exceeding 230,000 documents sampled from evolving knowledge bases. Five evaluated models performed worse as the inputs approached realistic scale. The benchmark preserves cross-document logical consistency, but synthetic firms remain a proxy for private organizations and their messier records.",
    "why_it_matters": "CorporateBench builds temporally consistent synthetic firms so question-answering systems can be tested at enterprise communication scale.",
    "limitations": [
      "The benchmark preserves cross-document logical consistency, but synthetic firms remain a proxy for private organizations and their messier records."
    ],
    "importance": 7,
    "canonical_url": "https://themachinepress.com/story/mp-2026-08-28-006/the-company-benchmark-grew-to-230-000-documents",
    "json_url": "https://themachinepress.com/story/mp-2026-08-28-006.json",
    "first_published_at": "2026-08-28T09:00:00.000-04:00",
    "modified_at": "2026-08-28T09:00:00.000-04:00",
    "content_status": "new",
    "is_carryover": false,
    "carryover_reason": null,
    "key_claims": [
      {
        "claim_id": "claim-mp-2026-08-28-006-001",
        "text": "CorporateBench builds temporally consistent synthetic firms so question-answering systems can be tested at enterprise communication scale.",
        "source_ids": [
          "source-2026-08-28-006"
        ],
        "qualification": "The benchmark preserves cross-document logical consistency, but synthetic firms remain a proxy for private organizations and their messier records."
      }
    ],
    "source_ids": [
      "source-2026-08-28-006"
    ],
    "tags": [
      "enterprise AI",
      "question answering",
      "benchmarks"
    ],
    "image_url": null,
    "corrections": []
  },
  "sources": [
    {
      "source_id": "source-2026-08-28-006",
      "title": "arXiv preprint 2608.27391",
      "publisher": "arXiv",
      "url": "https://arxiv.org/abs/2608.27391",
      "canonical_url": "https://arxiv.org/abs/2608.27391",
      "source_type": "primary_research",
      "is_primary_source": true,
      "published_at": "2026-08-27T13:23:04.000-04:00",
      "accessed_at": "2026-08-28T08:15:00.000-04:00",
      "supports_claim_ids": [
        "claim-mp-2026-08-28-006-001"
      ]
    }
  ],
  "corrections": [],
  "publisher": {
    "name": "The Machine Press",
    "url": "https://themachinepress.com",
    "description": "A daily newspaper for the age of artificial intelligence."
  },
  "cite_this_report": {
    "title": "The Company Benchmark Grew to 230,000 Documents",
    "publisher": "The Machine Press",
    "published_at": "2026-08-28T09:00:00.000-04:00",
    "canonical_url": "https://themachinepress.com/story/mp-2026-08-28-006/the-company-benchmark-grew-to-230-000-documents"
  }
}