{
  "abstract": "We test whether researchers can delegate the writing of a complete catalyst study to a large language model while retaining scientific judgment. Our case study concerns molecular dual-atom site catalysts for the oxygen reduction reaction, where stabilizing an adsorbed intermediate can make its subsequent reduction less favorable. Using density functional theory calculations on 88 catalysts, we explain this balance through adsorption free energies and the overpotential volcano. We then use adsorbate specific ridge models to predict adsorption energies for 1,260 additional structures and identify candidates for further study. Among candidates with low predicted overpotentials, we find predominantly Fe adsorption centers, with separate structural patterns associated with S bridges and 1,2phenylenediamine. To communicate the reasoning behind these choices, we guided a large language model with explicit scientific writing instructions and refined its explanations through repeated scientific and editorial review. The resulting article is the demonstration: we delegate manuscript preparation while retaining responsibility for its scientific meaning. This approach to accelerating catalyst discovery with artificial intelligence offers researchers an opportunity to concentrate on scientific investigation while guiding how their results are communicated.",
  "abstract_shown": true,
  "affiliations": [
    "Institute of Chemistry, University of Tartu, Ravila 14a, Tartu, Estonia, 50411",
    "Department of Chemistry, University of Latvia, Jelgavas iela 1, Riga, Latvia, LV-1004"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 6,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Denis Savchenko"
    },
    {
      "affs": [
        0
      ],
      "name": "Bruno Ina cio da Silva Roux Leite"
    },
    {
      "affs": [
        0
      ],
      "name": "Timmo-Henrik Pukk"
    },
    {
      "affs": [
        0
      ],
      "name": "Ba Long Nguyen"
    },
    {
      "affs": [
        1
      ],
      "name": "Vladislav Ivanistsev"
    },
    {
      "affs": [
        0
      ],
      "name": "Nadezda Kongi",
      "orcid": "0000-0001-9680-0421"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/fq5qveq3tf4f6.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15010768/v1",
  "fulltext_url": null,
  "id": "fq5qveq3tf4f6",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010768/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": "W7223132363",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15010768/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-21",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/fq5qveq3tf4f6.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:24Z",
      "native_id": "10.26434/chemrxiv.15010768",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010768/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:2505|Machine Learning in Materials Science",
      "subfield": "materials-polymers"
    }
  ],
  "title": "Accelerating Catalyst Discovery with Artificial Intelligence Using Molecular Dual-Atom Site Catalysts as a Case Study",
  "title_text": "Accelerating Catalyst Discovery with Artificial Intelligence Using Molecular Dual-Atom Site Catalysts as a Case Study",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:24Z",
  "url": "https://research.draconitic.com/paper/fq5qveq3tf4f6",
  "venue": "ChemRxiv",
  "versions": []
}