{
  "abstract": "Normal-inverse-gamma (NIG) regression is not uniquely identifiable from its marginal Student-t likelihood: the likelihood determines three combinations of four NIG parameters and is constant along a one-dimensional fiber. We identify that fiber using independent physical measurement. As an initial embodiment, a reconstruction network receives one noisy filtered-backprojection (FBP) image and is first trained only by Student-t negative log-likelihood to estimate the three identifiable coordinates (gamma, alpha, c). The network is then frozen; repeated physical-noise realizations propagated through its reconstruction output form a Monte Carlo (MC) teacher label for output-domain aleatoric variance. An aleatoric head attached to frozen features learns this label, after which (beta, nu) are recovered algebraically. On 30 held-out simulated objects at five photon levels, one-image predictions achieved pooled Spearman correlations of 0.832-0.951 against independent 400-repeat references, median within-image correlations were 0.834-0.947, and 98.81-99.55% of evaluated pixels satisfied the algebraic admissibility condition. The method needs no KL term, reference prior, evidence regularizer, or cross-loss weight.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.29599",
  "author_total": 1,
  "authors": [
    {
      "name": "Ge Wang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/20yabz841mvej.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.29599",
  "fulltext_url": null,
  "id": "20yabz841mvej",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.29599",
  "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",
      "physics.med-ph"
    ],
    [
      "openalex",
      "2741|Medical Imaging Techniques and Applications"
    ]
  ],
  "openalex": "W7214339449",
  "pdf_url": "https://arxiv.org/pdf/2609.29599",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/20yabz841mvej.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:24:11Z",
      "native_id": "2609.29599",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.29599"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:physics.med-ph",
      "subfield": "biological-medical"
    }
  ],
  "title": "PEEL: Physics-Enabled Evidential Learning for Identifiable Uncertainty in CT Imaging",
  "title_text": "PEEL: Physics-Enabled Evidential Learning for Identifiable Uncertainty in CT Imaging",
  "type": "preprint",
  "updated_at": "2026-10-30T12:24:11Z",
  "url": "https://research.draconitic.com/paper/20yabz841mvej",
  "venue": "arXiv",
  "versions": []
}