{
  "abstract": "We report a three-month autonomous research-agent program testing five solid-state-physics-inspired compression mappings on pretrained language models, with predictions committed to git before any pilot data and a 3-sigma gate deciding PASS or SHELVE. The common anchor -- area-law / Kohn-nearsighted decay of the one-particle density matrix -- has a distance face (P001 Wannier, P002 tight-binding) and a rank face (P003 DMRG-truncated MLPs, P005 Wilson-RG, P011 tensor-train embeddings). P005 was pre-empted at Phase 1; three of four Phase-3 pilots were falsified. On the attention face, GPT-2-medium attention-versus-distance is best fit by a stretched exponential in 12 of 16 median-layer heads once probe padding is excluded, and a tight-binding cutoff costs +96% perplexity (P002); on Pythia-160M the Wannier sparsity 0.054 +/- 0.004 is indistinguishable from PCA, random-Haar and identity baselines (P001). On the rank face, per-token tensor-train bond dimension does not track surprisal (r = 0.016 vs a pre-registered 0.65) and the format inflates rather than compresses (P011). P003 is mixed: its scaling claim shelved (r = -0.434), its MPO premise died at stage-0, and its cross-paper check, r = 0.523 as first written, collapses to 0.047 under the same correction, leaving both cross-paper checks null. The results invert the pre-registered prediction that most attention heads behave like Kohn-nearsighted insulators, pointing instead to critical, glassy or heavy-tailed regimes; the inversion is specific to the <= 350M scale tested, while the rank-face no-gain result held to 7-8B. We contribute the pre-registration + 3-sigma + cluster-framing + append-only-catalogue discipline -- including why our own enforcement gate was designed but not deployed -- four pre-registered negative results with full data release, and the inversion. The catalogue holds eighteen concluded studies, seventeen negative.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.34292",
  "author_total": 1,
  "authors": [
    {
      "name": "Jun-qiang Lu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/esmq7jh7nm9g3.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.34292",
  "fulltext_url": null,
  "id": "esmq7jh7nm9g3",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.34292",
  "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",
      "cond-mat.dis-nn"
    ],
    [
      "arxiv",
      "cond-mat.mtrl-sci"
    ],
    [
      "arxiv",
      "cond-mat.other"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "openalex",
      "1702|Topic Modeling"
    ]
  ],
  "openalex": "W7214799051",
  "pdf_url": "https://arxiv.org/pdf/2609.34292",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-28",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/esmq7jh7nm9g3.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:25:12Z",
      "native_id": "2609.34292",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.34292"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:cond-mat.dis-nn",
      "subfield": "condensed-matter"
    }
  ],
  "title": "Pre-registered tests of solid-state-physics-inspired LLM compression: a cluster-level negative result at small-language-model scale",
  "title_text": "Pre-registered tests of solid-state-physics-inspired LLM compression: a cluster-level negative result at small-language-model scale",
  "type": "preprint",
  "updated_at": "2026-10-30T12:25:12Z",
  "url": "https://research.draconitic.com/paper/esmq7jh7nm9g3",
  "venue": "arXiv",
  "versions": []
}