{
  "abstract": "Human reference labels used to evaluate medical AI can vary across readers and annotation workflows. We quantified agreement of a fixed pathology AI system with a future qualified reader without treating inferred consensus as error-free biological truth. Linked Evaluation and Unbiased NuCLS multirater data were analyzed using a fixed external HoVer-Net decision vector. The selected frame contained 1,144 anchors, 52 fields of view, five slides/patients, and five primary readers. The target was fixed-AI agreement with a future reader, with descriptive contrast $Δ=θ_E-θ_U$. Analyses included raw agreement and iMRMC benchmarks, reader-only and shared-detectability Bayesian models, structural sensitivities, adversarial simulations, and predictive assessment. Among 5,188 reader-anchor pairs observed in both conditions, 19.62% changed AI-agreement state, while raw agreement was 0.5466 in Unbiased and 0.5473 in Evaluation. The reader-only model gave $Δ=-0.0008$ (95% CrI, $-0.0033$ to $0.0008$), and the shared-detectability model gave $Δ\\approx0$ ($-0.0140$ to $0.0127$). Across structural perturbations, absolute agreement ranged from 0.420 to 0.646 in Unbiased and 0.409 to 0.640 in Evaluation. Frozen adversarial simulations met the comparative-stability criterion (median $R=0.295$; 14/16 model-scenario cells had $R<1$). Held-out-AI prediction supported shared predictive information, but varied by slide composition. The Evaluation-minus-Unbiased contrast was comparatively stable, whereas absolute agreement was structurally sensitive. These findings do not establish equivalence, causal assistance effects, biological accuracy, or new-patient transportability. Evaluations using variable human references should report reader population, selected frame, observation mechanism, and structural sensitivity.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.14642",
  "author_total": 1,
  "authors": [
    {
      "name": "Hammed A. Olayinka"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/3kvxyc88feypd.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.14642",
  "fulltext_url": null,
  "id": "3kvxyc88feypd",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.14642",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "q-bio.QM"
    ],
    [
      "arxiv",
      "stat.AP"
    ],
    [
      "arxiv",
      "stat.CO"
    ],
    [
      "arxiv",
      "stat.ME"
    ],
    [
      "openalex",
      "1702|AI in cancer detection"
    ]
  ],
  "openalex": "W7221765551",
  "pdf_url": "https://arxiv.org/pdf/2610.14642",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-10",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/3kvxyc88feypd.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:29:21Z",
      "native_id": "2610.14642",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.14642"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.QM",
      "subfield": "bioinformatics"
    },
    {
      "field": "mathematics",
      "origin": "arxiv:stat.AP",
      "subfield": "statistics"
    }
  ],
  "title": "Bayesian Uncertainty Quantification of Breast-Cancer Pathology AI Agreement under Reader- and Annotation-Condition-Dependent Reference Labels",
  "title_text": "Bayesian Uncertainty Quantification of Breast-Cancer Pathology AI Agreement under Reader- and Annotation-Condition-Dependent Reference Labels",
  "type": "preprint",
  "updated_at": "2026-10-30T12:29:26Z",
  "url": "https://research.draconitic.com/paper/3kvxyc88feypd",
  "venue": "arXiv",
  "versions": []
}