Metraipolis › archive › dc_42e797604642

A trust layer for fast pedestal-stability surrogates: calibrated error bars, out-of-distribution alarms and few-shot recalibration — arXiv:2611.06597

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.06597
License (as archived): CC0-1.0
Archived: 2026-11-05T18:22:20.244Z
SHA-256 of the archived text: 3770952c47d29a80c18463fc3e70a36f857d77accf229bc1e22f65e6ef4699e4
Stable URL of this page: https://metraipolis.com/documento/dc_42e797604642

How to cite

A trust layer for fast pedestal-stability surrogates: calibrated error bars, out-of-distribution alarms and few-shot recalibration — arXiv:2611.06597 — arXiv (en), https://arxiv.org/abs/2611.06597 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_42e797604642 (Metraipolis archive dc_42e797604642, sha256 3770952c47d29a80c18463fc3e70a36f857d77accf229bc1e22f65e6ef4699e4)

BibTeX

@misc{dc42e797604642,
  title = {A trust layer for fast pedestal-stability surrogates: calibrated error bars, out-of-distribution alarms and few-shot recalibration — arXiv:2611.06597},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.06597},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_42e797604642; sha256 3770952c47d29a80c18463fc3e70a36f857d77accf229bc1e22f65e6ef4699e4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06597. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Plasma Physics (physics.plasm-ph).
Pagina del lavoro: https://arxiv.org/abs/2611.06597 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-05T18:15:49.020Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).