{
  "abstract": "LLM workflows and agents rely on a set of binary decisions like allow/block an input, or discard/retain a retrieved document. When human deferral is unavailable, uncertain cases must still receive an action. We study System One decision scores in this setting by defaulting to a conservative fallback when uncertain, and controlling the false omission risk within the subset of inputs assigned the utility-maximizing action. Across six datasets covering moderation, safety, and reranking, we compare general System One models with task baselines and a local open-weights fine-tuned System One model. We show that naive baselines for threshold selection exceed the target risk in roughly half of settings with defined test risk, compared with 7.8\\% for Learn Then Test (LTT), which leverages finite-sample statistical guarantees. Our results show why relying on a probability-like interface is insufficient for deployment decisions and how risk-budgeted selection trades useful action against observed error.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.19811",
  "author_total": 2,
  "authors": [
    {
      "name": "Soundouss Messoudi"
    },
    {
      "name": "Youness Mansar"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/3r3e0c0kd1bgx.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.19811",
  "fulltext_url": null,
  "id": "3r3e0c0kd1bgx",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.19811",
  "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.ML"
    ],
    [
      "openalex",
      "3311|Ethics and Social Impacts of AI"
    ]
  ],
  "openalex": "W7222232158",
  "pdf_url": "https://arxiv.org/pdf/2610.19811",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-14",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/3r3e0c0kd1bgx.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:29:42Z",
      "native_id": "2610.19811",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.19811"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Calibration and Risk-Budgeted Decisions with System One Models",
  "title_text": "Calibration and Risk-Budgeted Decisions with System One Models",
  "type": "preprint",
  "updated_at": "2026-10-30T12:29:42Z",
  "url": "https://research.draconitic.com/paper/3r3e0c0kd1bgx",
  "venue": "arXiv",
  "versions": []
}