{
  "$schema": "https://themachinepress.com/schemas/story-v1.schema.json",
  "schema_version": "1.0.0",
  "document_type": "machine_press_story",
  "story": {
    "story_id": "mp-2026-08-19-004",
    "source_story_id": "tmp-story-institution-specific-phi-audit",
    "edition_id": "mp-2026-08-19-morning-0041",
    "edition_url": "https://themachinepress.com/edition/2026-08-19",
    "position": 4,
    "story_type": "dispatch",
    "section": "research",
    "editorial_classification": "editorial",
    "headline": "The Gold Standard Had Missed the Hospital’s Own Names",
    "slug": "the-gold-standard-had-missed-the-hospital-s-own-names",
    "dek": "Institution-specific prompting found locally meaningful protected-health identifiers and exposed 227 omissions in the reference annotations.",
    "summary": "Institution-specific prompting found locally meaningful protected-health identifiers and exposed 227 omissions in the reference annotations.",
    "body_text": "Across 100 pediatric-oncology notes containing 5,322 annotated PHI spans, the best prompted LLM exceeded two purpose-built de-identification systems in the authors’ comparison. Naming institution-specific categories recovered 48 of 61 misses, and re-annotation confirmed 227 additional PHI spans surfaced by model outputs. No tested multi-agent setup beat the calibrated single pass, and the result belongs to one hospital dataset rather than a universal de-identification guarantee.",
    "why_it_matters": "Institution-specific prompting found locally meaningful protected-health identifiers and exposed 227 omissions in the reference annotations.",
    "limitations": [],
    "importance": 9,
    "canonical_url": "https://themachinepress.com/story/mp-2026-08-19-004/the-gold-standard-had-missed-the-hospital-s-own-names",
    "json_url": "https://themachinepress.com/story/mp-2026-08-19-004.json",
    "first_published_at": "2026-08-19T09:00:00.000-04:00",
    "modified_at": "2026-08-19T09:00:00.000-04:00",
    "content_status": "new",
    "is_carryover": false,
    "carryover_reason": null,
    "key_claims": [
      {
        "claim_id": "claim-mp-2026-08-19-004-001",
        "text": "Institution-specific prompting found locally meaningful protected-health identifiers and exposed 227 omissions in the reference annotations.",
        "source_ids": [
          "source-2026-08-19-004"
        ],
        "qualification": null
      }
    ],
    "source_ids": [
      "source-2026-08-19-004"
    ],
    "tags": [
      "de-identification",
      "health records",
      "privacy",
      "LLMs"
    ],
    "image_url": null,
    "corrections": []
  },
  "sources": [
    {
      "source_id": "source-2026-08-19-004",
      "title": "arXiv preprint 2608.17051",
      "publisher": "arXiv",
      "url": "https://arxiv.org/abs/2608.17051",
      "canonical_url": "https://arxiv.org/abs/2608.17051",
      "source_type": "primary_research",
      "is_primary_source": true,
      "published_at": "2026-08-16T20:00:00.000-04:00",
      "accessed_at": "2026-08-19T08:22:00.000-04:00",
      "supports_claim_ids": [
        "claim-mp-2026-08-19-004-001"
      ]
    }
  ],
  "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 Gold Standard Had Missed the Hospital’s Own Names",
    "publisher": "The Machine Press",
    "published_at": "2026-08-19T09:00:00.000-04:00",
    "canonical_url": "https://themachinepress.com/story/mp-2026-08-19-004/the-gold-standard-had-missed-the-hospital-s-own-names"
  }
}