{
  "abstract": "Machine learning for polymer design requires structured, sample-level records linking polymer identity, synthesis, composition, molecular-weight characteristics, processing conditions, and measured properties. Yet decades of polymer data remain dispersed across the texts, tables, figures, and supporting information of the literature, where individual values are often separated from the samples and experimental context they describe. Here we introduce PolyReader, an LLM agent for provenance-aware extraction of polymer data from scientific papers. Rather than treating a paper as a single block of text, PolyReader represents the manuscript and supporting information as navigable hierarchical section trees. The agent surveys this structure, selectively reads relevant pages, follows cross-references between documents, and integrates dispersed evidence into schema-validated, per-sample records. The resulting extracted fields are thus linked to its source document and page. On a benchmark of 42 polymer papers evaluated by trained annotators, PolyReader achieved F1 scores of 0.92–0.96 across 11 property categories, with comparable performance across three LLM models. Holding the LLM model, parsed document representation, and output schema fixed, PolyReader improved F1 by 13–17 points over single-pass prompting. These results show that reliable polymer-data extraction depends not only on recognizing individual values, but on reconstructing the sample-level relationships distributed throughout a paper. PolyReader produces records that are directly auditable against the primary literature, providing a scalable foundation for constructing traceable polymer datasets for machine learning. The extraction pipeline and benchmark annotations are released for reuse in the community.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Chemistry and Materials Science",
    "Xi’an Jiaotong-Liverpool University",
    "Department of Chemistry",
    "University of Liverpool",
    "College of Carbon Neutrality Future Technology, State Key Laboratory of Heavy Oil Processing",
    "China University of Petroleum (Beijing"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 6,
  "authors": [
    {
      "affs": [
        0,
        1,
        2,
        3
      ],
      "name": "Yuwei Shi"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Xinyan Zhong"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Yuqi Wei"
    },
    {
      "affs": [
        0,
        1,
        2,
        3
      ],
      "name": "Heechae Choi"
    },
    {
      "affs": [
        4,
        5
      ],
      "name": "Tianhang Zhou"
    },
    {
      "affs": [
        0,
        1,
        2,
        3
      ],
      "name": "Zhenghao Wu",
      "orcid": "0000-0003-2862-4432"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/f8wgk6tbvg0w1.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15008614/v1",
  "fulltext_url": null,
  "id": "f8wgk6tbvg0w1",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008614/v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2505|Machine Learning in Materials Science"
    ]
  ],
  "openalex": "W7212138867",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008614/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-10",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/f8wgk6tbvg0w1.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:19Z",
      "native_id": "10.26434/chemrxiv.15008614",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008614/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:2505|Machine Learning in Materials Science",
      "subfield": "materials-polymers"
    }
  ],
  "title": "PolyReader: an agentic LLM pipeline for extracting structured data from unstructured polymer scientific literature",
  "title_text": "PolyReader: an agentic LLM pipeline for extracting structured data from unstructured polymer scientific literature",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:19Z",
  "url": "https://research.draconitic.com/paper/f8wgk6tbvg0w1",
  "venue": "ChemRxiv",
  "versions": []
}