{
  "abstract": "Panvascular intervention research requires evidence workflows that preserve source identity, outcome definitions and observation windows. We developed PanVasc Research, an executable research framework, and evaluated a fixed local Qwen3-4B model using two complementary tasks. Fifty ClinicalTrials.gov records from five vascular query strata generated 200 source-fidelity tests with intact evidence or controlled removal of the requested source, primary outcome or timeframe, plus 50 clean controls. A separate 100-statement sample from the official NLI4CT test set assessed clinical-trial entailment and evidence selection against existing expert labels. Generic and checklist prompts used identical evidence and maximum generation budgets; each output was also evaluated with an input-only deterministic contract. Registry exact accuracy was 51/200 (25.5%) with the generic prompt and 77/200 (38.5%) with the checklist; intact-case agreement was 50/50 and 48/50. The rule baseline recovered 200/200 tuples. NLI label accuracy was 48/100 (48.0%) and 50/100 (50.0%), respectively. The source contract retained 35 and 31 incorrect NLI labels in the two arms. Registry references establish fidelity to a registration snapshot, while NLI4CT concerns breast-cancer trials and does not validate vascular expertise. The framework also retains provenance-recorded literature retrieval, structured research planning and local numerical analysis. These experiments support a bounded assessment of source handling and semantic failure, rather than a new foundation model or autonomous scientific discovery. A proposed endpoint representation identifies the additional domain annotation and independent validation required for a panvascular research model.",
  "abstract_shown": true,
  "affiliations": [
    "Zhongshan Hospital, Fudan University"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 7,
  "authors": [
    {
      "name": "L. You"
    },
    {
      "name": "Y. Guo"
    },
    {
      "name": "W. Wang"
    },
    {
      "name": "Z. Peng"
    },
    {
      "name": "X. Zhong"
    },
    {
      "affs": [
        0
      ],
      "name": "L. Shen"
    },
    {
      "name": "J. Ge"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/93psg2p1vc2cz.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.22.752857",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.09.22.752857v1.full",
  "id": "93psg2p1vc2cz",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.09.22.752857v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "bioinformatics"
    ],
    [
      "openalex",
      "2718|Artificial Intelligence in Healthcare and Education"
    ]
  ],
  "openalex": "W7214627083",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.09.22.752857v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-22",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/93psg2p1vc2cz.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:24:58Z",
      "native_id": "10.64898/2026.09.22.752857",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.09.22.752857v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "PanVasc Research for AI assisted evidence analysis in panvascular intervention",
  "title_text": "PanVasc Research for AI assisted evidence analysis in panvascular intervention",
  "type": "preprint",
  "updated_at": "2026-10-30T12:24:58Z",
  "url": "https://research.draconitic.com/paper/93psg2p1vc2cz",
  "venue": "bioRxiv",
  "versions": []
}