{
  "abstract": "Depression has no diagnostic blood test. Language models promise tireless, consistent assessment, but can accurate raters disagree about individuals? We pre-registered 880 language-model raters, crossing 11 open models with prompting and scoring choices, and applied them to 189 interviews against the eight-item Patient Health Questionnaire. Model choice explained 30.0% of summed-symptom score variance, stable participant differences 10.5%. Two randomly drawn raters with area under the receiver operating characteristic curve (AUC) >= 0.70 disagreed on screening decisions for 40% of participants, on average. Average over-rating governed how many were flagged, yet equal-capacity raters chose differently for about one participant in five. A locked analysis of 86 new interviews reproduced the main pre-registered findings. Exploratory recalibration with 40 labelled participants raised accuracy from about 60% to 75% and halved disagreement, leaving one participant in five decided differently. Calibration repaired much of the rater dependence without securing agreement about individuals.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.08501",
  "author_total": 1,
  "authors": [
    {
      "name": "Baihan Lin"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/5pygbghsxj5zc.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.08501",
  "fulltext_url": null,
  "id": "5pygbghsxj5zc",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.08501",
  "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.AI"
    ],
    [
      "arxiv",
      "cs.CL"
    ],
    [
      "arxiv",
      "q-bio.NC"
    ],
    [
      "openalex",
      "3205|Emotion and Mood Recognition"
    ]
  ],
  "openalex": "W7220961107",
  "pdf_url": "https://arxiv.org/pdf/2610.08501",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-06",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/5pygbghsxj5zc.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:27:27Z",
      "native_id": "2610.08501",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.08501"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.NC",
      "subfield": "neuroscience"
    }
  ],
  "title": "Language-model ratings of depression reflect the rater more than the patient",
  "title_text": "Language-model ratings of depression reflect the rater more than the patient",
  "type": "preprint",
  "updated_at": "2026-10-30T12:27:27Z",
  "url": "https://research.draconitic.com/paper/5pygbghsxj5zc",
  "venue": "arXiv",
  "versions": []
}