{
  "abstract": "Machine-learning surrogates of linear peeling-ballooning stability now run in milliseconds, but they are mostly deployed as point estimators: they do not say how wrong they may be, or when a query lies outside what they were trained on. For a fusion company designing a new device, every equilibrium of interest is outside the training data of existing surrogates, so this is the case that matters. We describe a model-agnostic trust layer for stability surrogates, made of conformal error bars, out-of-distribution alarms that route doubtful cases to the physics code, and recalibration from a few simulations of a new design, and we test it with pre-registered hypotheses. On a large public dataset of JET-like equilibria with ideal-MHD growth rates, the error bars hold their nominal coverage in distribution and fall short under a shift in plasma shape; a few dozen simulations of the new shape, or routing the cases the alarms flag, restore it. On resistive BOUT++ surrogates, the bars stay calibrated on held-out runs, the alarm flags tokamaks absent from training, and a scenario scan is screened in seconds instead of hours. Across equilibria from the SPARC library and the DIII-D coil set, a surrogate trained on our own graded BOUT++ labels beats the baseline on unseen equilibria, while a surrogate trained elsewhere ranks the same cases backwards and its alarm declines them. Building our own neural-operator surrogate, the harness exposed two input defects whose fix closed its gap to a simple network. For every surrogate tested, the trust layer keeps coverage near target, with a bar width set by that surrogate's own error. Not every pre-registered hypothesis held, and we report those results and the limits of all of them.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2611.06597",
  "author_total": 1,
  "authors": [
    {
      "name": "Amin Vakhshouri"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/d0e8t2xg8sdfj.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2611.06597",
  "fulltext_url": null,
  "id": "d0e8t2xg8sdfj",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2611.06597",
  "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.LG"
    ],
    [
      "arxiv",
      "physics.plasm-ph"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2611.06597",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-04",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/d0e8t2xg8sdfj.ris",
  "sources": [
    {
      "first_seen": "2026-11-05T15:20:56Z",
      "native_id": "2611.06597",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2611.06597"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:physics.plasm-ph",
      "subfield": "plasma"
    }
  ],
  "title": "A trust layer for fast pedestal-stability surrogates: calibrated error bars, out-of-distribution alarms and few-shot recalibration",
  "title_text": "A trust layer for fast pedestal-stability surrogates: calibrated error bars, out-of-distribution alarms and few-shot recalibration",
  "type": "preprint",
  "updated_at": "2026-11-09T00:20:20Z",
  "url": "https://research.draconitic.com/paper/d0e8t2xg8sdfj",
  "venue": "arXiv",
  "versions": []
}