{
  "abstract": "AI for Science aims not only to predict complex physical systems from data, but also to extract mathematical structure and physically testable representations from learned models. Here, a train--prune--readout--rewrite workflow is developed that separates physical-domain grounding from three increasingly stringent analysis claims: algebraically equivalent readout of a trained predictor, compact teacher-faithful symbolic rewriting on the sampled physical domain, and transformation-based tests of learned internal representations. The workflow is implemented with complex-valued Kolmogorov--Arnold networks, whose explicit edge functions enable post-pruning analytic readout of the retained computation. In analytically controlled single-qubit tasks, rewriting recovered the quadratic structure of purity, whereas von Neumann entropy yielded only a domain-bounded symbolic surrogate; physics-aligned variable grouping preserved symbolic fidelity. For two-qubit entanglement-related tasks, shared learning exposed a common internal representation whose physical content was interrogated directly. Local-unitary transformations rejected a direct invariant-coordinate interpretation, while fixed-decoder transfer showed that the shared activation carries Pauli-correlation information in a transformation-consistent form. Task-related invariant spectral features were subsequently recovered through low-order nonlinear readouts. Separate predictive tests retained high accuracy for three-qubit classification and controlled ten-qubit purity regression with over one million complex inputs. These results establish an evidence-resolved framework for distinguishing physical grounding, readable computation, faithful symbolic compression and transformation-tested physical structure in constrained complex-valued scientific learning.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.15139",
  "author_total": 4,
  "authors": [
    {
      "name": "Siran Zhang"
    },
    {
      "name": "Shuming Cheng"
    },
    {
      "name": "Xiang Li"
    },
    {
      "name": "Jinyi Liu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/d5akv3c3ystvj.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.15139",
  "fulltext_url": null,
  "id": "d5akv3c3ystvj",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.15139",
  "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",
      "quant-ph"
    ],
    [
      "openalex",
      "1702|Quantum Computing Algorithms and Architecture"
    ]
  ],
  "openalex": "W7213252425",
  "pdf_url": "https://arxiv.org/pdf/2609.15139",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-14",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/d5akv3c3ystvj.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:21:25Z",
      "native_id": "2609.15139",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.15139"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:quant-ph",
      "subfield": "quantum"
    }
  ],
  "title": "A train--prune--readout--rewrite workflow for interpretable quantum learning",
  "title_text": "A train--prune--readout--rewrite workflow for interpretable quantum learning",
  "type": "preprint",
  "updated_at": "2026-10-30T12:21:25Z",
  "url": "https://research.draconitic.com/paper/d5akv3c3ystvj",
  "venue": "arXiv",
  "versions": []
}