{
  "abstract": "Generative artificial intelligence (AI) shows promise for physical simulation, yet its clinical application remains critically unexplored. We present SurgVeo, a pioneering expert-guided benchmark paired with the Surgical Plausibility Pyramid framework. Evaluating the Veo-3 and Wan2.2 models reveals a consistent plausibility gap: despite high visual fidelity, the majority of errors are surgical logic failures rather than visual quality deficits. By exposing this reliance on visual synthesis, this study provides a roadmap for developing surgical world models.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong, China",
    "Research Institute for Smart Ageing, The Hong Kong Polytechnic University, Hong Kong, China",
    "Department of Computer Science, University of Nottingham, Nottingham, UK",
    "Institute of Automation, Chinese Academy of Sciences, Beijing, China",
    "Department of Neurosurgery, The First Hospital, Shanxi Medical University, Taiyuan, China",
    "Department of Gastrointestinal Surgery, The Second Qilu Hospital, Shandong University, Jinan, China",
    "The Chair for Computer Aided Medical Procedures and Augmented Reality (CAMP), Technical University of Munich, Munich, Germany",
    "Department of Computer Science, University of Rochester, Rochester, NY, USA"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 10,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Zhen Chen",
      "orcid": "0000-0003-0255-6435"
    },
    {
      "affs": [
        2
      ],
      "name": "Qing Xu",
      "orcid": "0000-0001-6898-0269"
    },
    {
      "affs": [
        3
      ],
      "name": "Jinlin Wu"
    },
    {
      "affs": [
        4
      ],
      "name": "Biao Yang"
    },
    {
      "affs": [
        5
      ],
      "name": "Yuhao Zhai"
    },
    {
      "affs": [
        4
      ],
      "name": "Geng Guo",
      "orcid": "0000-0003-4197-0399"
    },
    {
      "affs": [
        5
      ],
      "name": "Jing Zhang"
    },
    {
      "affs": [
        5
      ],
      "name": "Yinlu Ding"
    },
    {
      "affs": [
        6
      ],
      "name": "Nassir Navab",
      "orcid": "0000-0002-6032-5611"
    },
    {
      "affs": [
        7
      ],
      "name": "Jiebo Luo"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/cwfgagrbf8at1.bib",
  "cited_by": 14,
  "doi": "10.1038/s41746-026-03276-z",
  "fulltext_url": null,
  "id": "cwfgagrbf8at1",
  "issns": [
    "2398-6352"
  ],
  "landing_url": "https://doi.org/10.1038/s41746-026-03276-z",
  "language": "en",
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2746|Surgical Simulation and Training"
    ]
  ],
  "openalex": "W7214467995",
  "pdf_url": "https://www.nature.com/articles/s41746-026-03276-z_reference.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-26",
  "publisher": "Nature Portfolio",
  "ris": "https://research.draconitic.com/paper/cwfgagrbf8at1.ris",
  "sources": [
    {
      "first_seen": "2026-11-07T13:20:59Z",
      "native_id": "W7214467995",
      "source": "openalex",
      "url": "https://doi.org/10.1038/s41746-026-03276-z"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2746|Surgical Simulation and Training",
      "subfield": "surgery"
    }
  ],
  "title": "Quantifying the plausibility gap in generative AI for surgical video generation with expert assessment",
  "title_text": "Quantifying the plausibility gap in generative AI for surgical video generation with expert assessment",
  "type": "peer-reviewed",
  "updated_at": "2026-11-08T13:20:51Z",
  "url": "https://research.draconitic.com/paper/cwfgagrbf8at1",
  "venue": "npj Digital Medicine",
  "versions": []
}