{
  "abstract": "Patient-facing triage requires an appropriate care recommendation and recognition of when information is insufficient. We evaluate whether Jev, a decision model that returns probabilities over predefined actions, supports both judgments. Using CARE-Bench, we compare Jev with four general-purpose language models and three input-independent baselines across 925 decision points from 439 public cases. On the public test subset, Jev ranks fourth of five models by macro-F1 (0.461) but has the lowest observed multiclass Brier score (0.610), an 18.7\\% improvement over uniform prediction (case-bootstrap 95\\% interval, 4.9--31.1\\%). Noul has lower binary Brier than Choice (0.215 versus 0.276). A evaluation of 453 HealthBench conversations again gives Jev the lowest observed Brier score (0.299), but measures a distinct emergency-referral judgment. Jev combines lower probability error with missed clarification needs in the four-action task. Asking about information sufficiency separately increases recall but also produces frequent unnecessary clarification assignments.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.24692",
  "author_total": 5,
  "authors": [
    {
      "name": "Liang You"
    },
    {
      "name": "Zhiyin Zhou"
    },
    {
      "name": "Dawei Tang"
    },
    {
      "name": "Chuchu Wu"
    },
    {
      "name": "Jingzhuo Hu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/754zjbdk14p1e.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.24692",
  "fulltext_url": null,
  "id": "754zjbdk14p1e",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.24692",
  "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",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.AP"
    ],
    [
      "openalex",
      "2718|Artificial Intelligence in Healthcare and Education"
    ]
  ],
  "openalex": "W7223068368",
  "pdf_url": "https://arxiv.org/pdf/2610.24692",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-17",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/754zjbdk14p1e.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:33:54Z",
      "native_id": "2610.24692",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.24692"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.AP",
      "subfield": "statistics"
    }
  ],
  "title": "Native Probability Outputs for Clinical Triage: An Evaluation of Calibration and Decision Accuracy",
  "title_text": "Native Probability Outputs for Clinical Triage: An Evaluation of Calibration and Decision Accuracy",
  "type": "preprint",
  "updated_at": "2026-10-30T12:33:54Z",
  "url": "https://research.draconitic.com/paper/754zjbdk14p1e",
  "venue": "arXiv",
  "versions": []
}