{
  "abstract": "Scientific dynamics forecasting is often framed as an architecture choice, although deployment is also determined by observed history, rollout feedback, compute budget, physical objective, and test distribution. We formulate protocol-dependent model selection and introduce ProtocolMatch, a compute-matched, validation-selected, and failure-preserving evaluation framework. On driven quantum-spin dynamics, we compare recurrent, patched-attention, causal-attention, and low-rank linear predictors across three independently generated datasets. The causal-attention--recurrence ordering reverses as the training set grows within a fixed two-spin task, while a linear predictor has the lowest mean error in the six-spin local-observable comparison. Restricting observed history worsens every refreshed-history view but improves every closed-loop view in the four-spin study. A latest-state MLP has lower error than persistence on every dataset under state refresh across all five cells, yet its closed-loop rank varies by system and includes finite explosive errors. Physical penalties improve targeted consistency without reliably improving prediction error, and in-distribution intervals lose most coverage after a driving-frequency shift. Thus scientific model selection should return a predictor with its protocol and report accuracy, physical validity, and shifted-distribution reliability separately.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.10239",
  "author_total": 3,
  "authors": [
    {
      "name": "Lu Wei"
    },
    {
      "name": "Yufeng Wang"
    },
    {
      "name": "Haibin Ling"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/cpyb79c66b7t0.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.10239",
  "fulltext_url": null,
  "id": "cpyb79c66b7t0",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.10239",
  "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",
      "quant-ph"
    ],
    [
      "openalex",
      "3107|Quantum many-body systems"
    ]
  ],
  "openalex": "W7221008952",
  "pdf_url": "https://arxiv.org/pdf/2610.10239",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-07",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/cpyb79c66b7t0.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:27:37Z",
      "native_id": "2610.10239",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.10239"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:quant-ph",
      "subfield": "quantum"
    }
  ],
  "title": "ProtocolMatch: Protocol-Dependent Model Selection for Scientific Dynamics Forecasting",
  "title_text": "ProtocolMatch: Protocol-Dependent Model Selection for Scientific Dynamics Forecasting",
  "type": "preprint",
  "updated_at": "2026-10-30T12:27:37Z",
  "url": "https://research.draconitic.com/paper/cpyb79c66b7t0",
  "venue": "arXiv",
  "versions": []
}