{
  "abstract": "WardBench is a synthetic FHIR R4 agent benchmark for joint utility and policy compliance under role, HL7 PurposeOfUse, patient-stateful FHIR Consent, and PSY labels. Built on Synthea (seed 20261019): 120 main tasks (allowed, denied, boundary, adversarial), plus control and permitted twins, graded deterministically on trajectories (access, action, disclosure).\n\nThis draft reports a local 11-model evaluation (S1-S20b).\n\nDraft status: held-out official evaluation is pending clinician/DPO review of the assumed policy table, results are not a legal compliance certification (HIPAA/GDPR/EHDS).\n\nCode and review packet: https://github.com/WardBench/wardbench",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 1,
  "authors": [
    {
      "name": "Vadim Nareyko",
      "orcid": "0009-0004-1828-9102"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/53xzgsmyhs9x6.bib",
  "cited_by": 0,
  "doi": "10.5281/zenodo.23664058",
  "fulltext_url": null,
  "id": "53xzgsmyhs9x6",
  "issns": [],
  "landing_url": "https://zenodo.org/records/23664058",
  "language": "eng",
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [],
  "openalex": null,
  "pdf_url": "https://zenodo.org/api/records/23664058/files/wardbench_preprint.pdf/content",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-26",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/53xzgsmyhs9x6.ris",
  "sources": [
    {
      "first_seen": "2026-11-09T12:20:57Z",
      "native_id": "23664058",
      "source": "zenodo",
      "url": "https://zenodo.org/records/23664058"
    }
  ],
  "subjects": [],
  "title": "WardBench: Evaluating Policy Compliance, Dynamic FHIR Consent, and Construct Validity in Clinical EHR Agents",
  "title_text": "WardBench: Evaluating Policy Compliance, Dynamic FHIR Consent, and Construct Validity in Clinical EHR Agents",
  "type": "preprint",
  "updated_at": "2026-11-09T12:20:57Z",
  "url": "https://research.draconitic.com/paper/53xzgsmyhs9x6",
  "venue": "Zenodo",
  "versions": []
}