{
  "abstract": "Reinterpreting published chemical findings requires explicit atomic structures that connect experimental observations with reactivity. Here we report Paper2CIF, an artificial intelligence (AI) agent that reconstructs sample-specific atomic structures from published chemical evidence for structure-reactivity relationship investigations. Across 171 interdisciplinary articles, Paper2CIF achieves 97.08% phase identification accuracy and 91.23% final structural accuracy, with correct structures satisfying all applicable reported constraints, including composition, site occupancy, and local coordination. Calculations on reconstructed BiVO4 structures reveal distortion-dependent spatial contributions to the transition dipole, guiding targeted synthesis toward enhanced near-edge photon conversion. The resulting BiVO4-based Z-scheme pair exhibits a 3.47-fold increase in apparent quantum yield from 4.51% to 15.64% at 475 nm, compared with a 1.03-fold increase from 18.51% to 19.02% at 365 nm. The solar-to-hydrogen efficiency increases from 0.969% to 1.448% for overall water splitting. Paper2CIF establishes atomic reconstruction as a common basis for deriving chemical mechanisms from published evidence and translating them into experimentally testable principles for materials synthesis.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Materials Science and Engineering",
    "City University of Hong Kong",
    "School of Environment",
    "University of Science and Technology of China",
    "Department of Chemistry",
    "Tsinghua University",
    "College of Chemistry and Molecular Sciences",
    "Anhui Normal University"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Qixin Zhou"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Yonghang Yue"
    },
    {
      "affs": [
        4,
        5
      ],
      "name": "Wenjie Guo"
    },
    {
      "affs": [
        4,
        5,
        6,
        7
      ],
      "name": "Yongfa Zhu"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Yan Guo",
      "orcid": "0000-0002-8626-0238"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/5ax2v5b5m8m6x.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15010164/v1",
  "fulltext_url": null,
  "id": "5ax2v5b5m8m6x",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010164/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": "W7221196749",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15010164/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-09",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/5ax2v5b5m8m6x.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:22Z",
      "native_id": "10.26434/chemrxiv.15010164",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010164/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:2505|Machine Learning in Materials Science",
      "subfield": "materials-polymers"
    }
  ],
  "title": "Paper2CIF: An AI Agent for Reconstructing Atomistic Models to Discover Structure-Reactivity Relationships",
  "title_text": "Paper2CIF: An AI Agent for Reconstructing Atomistic Models to Discover Structure-Reactivity Relationships",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:22Z",
  "url": "https://research.draconitic.com/paper/5ax2v5b5m8m6x",
  "venue": "ChemRxiv",
  "versions": []
}