{
  "abstract": "Adapting a pre-trained machine-learning interatomic potential for non-equilibrium defect dynamics and plasticity requires improving defect accuracy without degrading the near-equilibrium elastic and vibrational response. Here we achieve this balance for the aluminium MACE potential QP17 by integrating conditional readout uncertainty, iterative full-parameter updates and protocol-compatible relative-energy anchoring. Sensitivities over 144 linear readout weights guide acquisition, with within-batch covariance updates and evolving neural representations. After four active-learning rounds (32 acquired configurations and 400 gradient updates), force-uncertainty acquisition reduces mean development force error from 22.43 to 21.52 meV/Angstrom, outperforming random sampling (22.70), geometry-diversity selection (22.46) and uniform training across all 104 candidate labels (22.71) under the same update budget. All three force-uncertainty runs satisfy bulk-mechanical retention criteria: historical relative-energy error decreases from 0.375 to 0.207 meV/atom, while harmonic phonon root-mean-square drift remains below 0.05 THz. Matched objective ablations reveal that relative-energy anchoring suppresses harmonic drift. Out-of-sample evaluations across planar faults, twin boundaries and grain boundaries demonstrate transferable gains in defect energies and deviatoric stresses, even though virial stresses are never fitted. A closed-loop molecular dynamics and density functional theory (MD-DFT) pilot confirms that automated acceptance gating intercepts updates that violate historical elastic-group energy or vibrational tolerances. Together, these components establish a retention-constrained fine-tuning protocol for improving plastic-deformation observables while preserving the tested bulk mechanical response.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.35653",
  "author_total": 4,
  "authors": [
    {
      "name": "Yue Wu"
    },
    {
      "name": "Yuan Tian"
    },
    {
      "name": "Deng Pan"
    },
    {
      "name": "Mingwei Chen"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/bre2dpbe6bv84.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.35653",
  "fulltext_url": null,
  "id": "bre2dpbe6bv84",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.35653",
  "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",
      "cond-mat.mtrl-sci"
    ],
    [
      "openalex",
      "2505|Machine Learning in Materials Science"
    ]
  ],
  "openalex": "W7223877569",
  "pdf_url": "https://arxiv.org/pdf/2610.35653",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-26",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/bre2dpbe6bv84.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:35:35Z",
      "native_id": "2610.35653",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.35653"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:cond-mat.mtrl-sci",
      "subfield": "condensed-matter"
    }
  ],
  "title": "Retention-constrained fine-tuning of a pre-trained aluminium MACE potential for non-equilibrium defect dynamics and plasticity",
  "title_text": "Retention-constrained fine-tuning of a pre-trained aluminium MACE potential for non-equilibrium defect dynamics and plasticity",
  "type": "preprint",
  "updated_at": "2026-10-30T12:35:35Z",
  "url": "https://research.draconitic.com/paper/bre2dpbe6bv84",
  "venue": "arXiv",
  "versions": []
}