{
  "abstract": "Bone science literature spans biology, mechanics, materials science, and clinical medicine, and its volume makes reliable knowledge synthesis increasingly difficult. General-purpose large language models (LLMs) answer fluently but under-represent this niche domain, cannot cite specific evidence, and offer no mechanism to be corrected durably. Here we present BoneGraph, a domain-specialised system for bone science delivered as a five-tab web application over a shared substrate: a curated full-text corpus of 7,449 documents embedded into 248,629 passage vectors using SPECTER2, a scientific-paper embedding model, and a bone knowledge graph of 1,597 concepts with 1,699 causal relations. The five tabs are: (I) Chat, retrieval-augmented question answering with server-rebuilt inline citations; (II) Search, raw semantic retrieval with no LLM in the loop; (III) Reasoning, a self-correcting loop in which a deterministic physics check and a literature/knowledge-graph critic constrain the answer, and a user's feedback becomes a durable, per-user rule; (IV) Vision, a bone-region classifier trained on frozen BiomedCLIP features that grounds a vision-language model, guarded against out-of-distribution inputs and augmented with image-embedding correction memory; and (V) Mechanics, integrating our previous data-driven image mechanics (D2IM) model that predicts displacement and strain fields from a single undeformed micro-CT image. All inference is performed locally, without third-party API calls, and the public beta is served at bonegraph.org. Retrieval attains a mean reciprocal rank (MRR) of 0.928 on a 30-question, seven-domain benchmark, and the Vision classifier attains 92.6% accuracy on the held-out MURA (MUsculoskeletal RAdiographs) dataset. A grounded-reasoning benchmark shows that, with the correct passage, BoneGraph raises answer accuracy from 42% to 78%. BoneGraph makes a major contribution to bone-science informatics: to our knowledge it is the first domain-specialised system to unify curated retrieval, deterministic physics-grounded self-correction, and durable per-user learning for bone science.",
  "abstract_shown": true,
  "affiliations": [
    "University of Greenwich"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "name": "J. Valijonov"
    },
    {
      "name": "P. Soar"
    },
    {
      "name": "J. Le Houx"
    },
    {
      "affs": [
        0
      ],
      "name": "G. Tozzi"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/9eq1q9zzvypky.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.17.752482",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.09.17.752482v1.full",
  "id": "9eq1q9zzvypky",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.09.17.752482v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "bioengineering"
    ],
    [
      "openalex",
      "1710|Information Retrieval and Search Behavior"
    ]
  ],
  "openalex": "W7213594577",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.09.17.752482v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-17",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/9eq1q9zzvypky.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:23:09Z",
      "native_id": "10.64898/2026.09.17.752482",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.09.17.752482v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioengineering",
      "subfield": "systems-synthetic"
    }
  ],
  "title": "BoneGraph: A Domain-Specialised, Self-Correcting Reasoning System for Bone Science Retrieval, Grounded Inference, and Image Mechanics",
  "title_text": "BoneGraph: A Domain-Specialised, Self-Correcting Reasoning System for Bone Science Retrieval, Grounded Inference, and Image Mechanics",
  "type": "preprint",
  "updated_at": "2026-10-30T12:23:09Z",
  "url": "https://research.draconitic.com/paper/9eq1q9zzvypky",
  "venue": "bioRxiv",
  "versions": []
}