{
  "abstract": "Magnetic interatomic potentials need to account for coupled lattice and spin degrees of freedom, yet constructing reliable training sets remains costly because noncollinear first-principles labels are expensive. Active learning can mitigate this cost, provided that the uncertainty estimate is physically meaningful for the magnetic-response targets that drive spin reorientation. Here we extend the $\\mathrm{e}^2\\mathrm{IP}$ evidential framework to magnetic machine-learning interatomic potentials by formulating the projected spin-force likelihood and the corresponding epistemic uncertainty in the tangent plane orthogonal to the local spin direction. This construction prevents the uncertainty model from allocating probability mass to a radial spin component that is absent from the constrained-moment supervision. Using bulk BiFeO$_3$ and monolayer CrTe$_2$ as benchmark systems, we show that the resulting tangent-plane epistemic uncertainty indicator $U_{\\mathrm{epi}}^{\\mathrm{sf}}$ correlates strongly with prediction error and selects more informative configurations than random sampling, simultaneously improving energy, force, and projected spin-force accuracy. These results demonstrate a physically interpretable and data-efficient route for constructing uncertainty-aware magnetic machine-learning interatomic potentials.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": "Journal reference: Physical Review Materials 2026",
  "arxiv": "2605.12353",
  "author_total": 3,
  "authors": [
    {
      "name": "Yang Cheng"
    },
    {
      "name": "Hongyu Yu"
    },
    {
      "name": "Hongjun Xiang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/e7ssytg5taxj7.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2605.12353",
  "fulltext_url": null,
  "id": "e7ssytg5taxj7",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2605.12353",
  "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",
      "physics.comp-ph"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2605.12353",
  "pmcid": null,
  "pmid": null,
  "published": "2026-07-25",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/e7ssytg5taxj7.ris",
  "sources": [
    {
      "first_seen": "2026-11-03T12:20:58Z",
      "native_id": "2605.12353",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2605.12353"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:physics.comp-ph",
      "subfield": "computational"
    }
  ],
  "title": "Tangent-Plane Evidential Uncertainty in Active Learning for Magnetic Interatomic Potentials",
  "title_text": "Tangent-Plane Evidential Uncertainty in Active Learning for Magnetic Interatomic Potentials",
  "type": "preprint",
  "updated_at": "2026-11-05T15:20:17Z",
  "url": "https://research.draconitic.com/paper/e7ssytg5taxj7",
  "venue": "arXiv",
  "versions": [
    {
      "doi": "10.1103/9hcx-wmmm",
      "pid": null,
      "relation": "published-as",
      "title": null,
      "venue": null
    }
  ]
}