{
  "abstract": "Evaluating model uncertainty on real-world data is challenging because each instance provides only a single observed label, leaving true conditional class probabilities unknown. To address this, we introduce ProbabilityBench, a benchmark that provides exact, instance-level class probabilities across three simulated text-based domains: peer review, covert information transfer, and credit risk. By explicitly defining the full data-generating process for each environment, we analytically compute both exact class probabilities and Bayes error. Furthermore, we provide a theoretical guarantee that rendering these cases into natural-language memos strictly preserves their underlying generative probabilities. This exactness enables direct measurement of reported probability quality via KL divergence. Across 16 evaluated models, most models on the observed cost-quality Pareto frontiers are decision models, including Jev and Perplexity Decider. Finally, ProbabilityBench serves as a meta-evaluation framework, leveraging known ground-truth values to benchmark the accuracy of standard calibration metrics and Bayes-error estimators themselves.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.17016",
  "author_total": 4,
  "authors": [
    {
      "name": "Yuyang Dai"
    },
    {
      "name": "Yuting Tang"
    },
    {
      "name": "Futoshi Futami"
    },
    {
      "name": "Takashi Ishida"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/1g4vfb2346ynm.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.17016",
  "fulltext_url": null,
  "id": "1g4vfb2346ynm",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.17016",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1702|Adversarial Robustness in Machine Learning"
    ]
  ],
  "openalex": "W7221813087",
  "pdf_url": "https://arxiv.org/pdf/2610.17016",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-12",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/1g4vfb2346ynm.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:29:26Z",
      "native_id": "2610.17016",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.17016"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "ProbabilityBench: Model Evaluation and Calibration with Exact Ground-Truth Uncertainty",
  "title_text": "ProbabilityBench: Model Evaluation and Calibration with Exact Ground-Truth Uncertainty",
  "type": "preprint",
  "updated_at": "2026-10-30T12:29:26Z",
  "url": "https://research.draconitic.com/paper/1g4vfb2346ynm",
  "venue": "arXiv",
  "versions": []
}