{
  "abstract": "Physical diagnostics recorded during simulation can organize a sharply varying response, but using them as surrogate inputs normally requires another calculation at prediction. We construct a physical-state-supervised Gaussian process surrogate that learns these diagnostics from design variables. Cross-fitted state estimates augment a retained design representation; a global Gaussian process and an optional soft mixture of response-band experts use identical inputs. On a database of 1,987 paired one-dimensional implosions, learned burn-weighted states from calculations without alpha-particle heating reduce mean squared log-response error by 60.25% and 52.98% for the global predictor on random holdout and design-space extrapolation. Random-projection and shuffled-state supervision do not reproduce these gains. For CH, matched-input comparisons show that experts help at smaller training budgets but contribute little at 1,000 designs with this representation. A thermal-feedback benchmark validates the complete learned-state procedure, while 3,000 newly calculated Be/Cocktail designs expose weaker extrapolation gains and cases where experts degrade accuracy. A conditional state-error bound separates encoding sensitivity from routing effects. An open Python implementation reproduces the archived predictions and is released with the data, per-design results, and measured costs. Physical-state supervision is thus a useful representation for finite-data surrogates, whereas expert specialization should be selected by validation.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.13822",
  "author_total": 3,
  "authors": [
    {
      "name": "Chang Liu"
    },
    {
      "name": "Hao Shen"
    },
    {
      "name": "Chuanying Li"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/5rqbxbp50m7pf.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.13822",
  "fulltext_url": null,
  "id": "5rqbxbp50m7pf",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.13822",
  "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"
    ],
    [
      "arxiv",
      "physics.plasm-ph"
    ],
    [
      "openalex",
      "1702|Gaussian Processes and Bayesian Inference"
    ]
  ],
  "openalex": "W7221527700",
  "pdf_url": "https://arxiv.org/pdf/2610.13822",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-09",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/5rqbxbp50m7pf.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:28:36Z",
      "native_id": "2610.13822",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.13822"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:physics.comp-ph",
      "subfield": "computational"
    },
    {
      "field": "physics",
      "origin": "arxiv:physics.plasm-ph",
      "subfield": "plasma"
    }
  ],
  "title": "Physical-state supervision for design-only Gaussian process surrogates of implosion simulations",
  "title_text": "Physical-state supervision for design-only Gaussian process surrogates of implosion simulations",
  "type": "preprint",
  "updated_at": "2026-10-30T12:28:36Z",
  "url": "https://research.draconitic.com/paper/5rqbxbp50m7pf",
  "venue": "arXiv",
  "versions": []
}