{
  "abstract": "The inverse design of materials with specific desired properties, such as high-temperature superconductivity, represents a formidable challenge in materials science due to the vastness of chemical and structural space. We present a guided diffusion framework to accelerate the discovery of novel superconductors. A DiffCSP foundation model is pretrained on the Alexandria Database and fine-tuned on 7183 superconductors with first-principles-derived labels. Employing classifier-free guidance, we sample 200,000 structures, which lead to 34,027 unique candidates. A multistage screening process that combines machine learning and density functional theory (DFT) calculations to assess stability and electronic properties, identifies 773 candidates with DFT-calculated T c > 5 K. Notably, our generative model demonstrates effective property-driven design. Our computational findings were validated against experimental synthesis and characterization performed as part of this work, which highlighted challenges in sparsely charted chemistries and disorder. This end-to-end workflow accelerates superconductor discovery while underscoring the challenge of predicting and synthesizing experimentally realizable materials.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Physics, University of Florida, Gainesville, FL, USA",
    "Quantum Theory Project, University of Florida, Gainesville, FL, USA",
    "Department of Materials Science and Engineering, University of Florida, Gainesville, FL, USA",
    "Department of Aerospace Engineering and Mechanics, University of Minnesota, Minneapolis, MN, USA",
    "Department of Chemistry, University of Florida, Gainesville, FL, USA",
    "Center for Neural Science, New York University, New York, NY, USA",
    "Center for Soft Matter Research, Department of Physics, New York University, New York, NY, USA",
    "Courant Institute of Mathematical Sciences, New York University, New York, NY, USA",
    "Simons Center for Computational Physical Chemistry, New York University, New York, NY, USA"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 16,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Pawan Prakash"
    },
    {
      "affs": [
        2,
        1
      ],
      "name": "Jason B. Gibson"
    },
    {
      "affs": [
        0
      ],
      "name": "Z. Li",
      "orcid": "0000-0002-3934-9053"
    },
    {
      "affs": [
        0
      ],
      "name": "Gabriele Di Gianluca"
    },
    {
      "affs": [
        0
      ],
      "name": "Juan Esquivel"
    },
    {
      "affs": [
        3
      ],
      "name": "Eric G. Fuemmeler",
      "orcid": "0009-0002-0526-8850"
    },
    {
      "affs": [
        2,
        0
      ],
      "name": "Benjamin Geisler",
      "orcid": "0000-0003-0864-2908"
    },
    {
      "affs": [
        0
      ],
      "name": "Jung Soo Kim",
      "orcid": "0000-0002-3901-6785"
    },
    {
      "affs": [
        4,
        1
      ],
      "name": "Adrian Roitberg",
      "orcid": "0000-0003-3963-8784"
    },
    {
      "affs": [
        3
      ],
      "name": "Ellad B. Tadmor",
      "orcid": "0000-0003-3311-6299"
    },
    {
      "affs": [
        4,
        1
      ],
      "name": "Mingjie Liu",
      "orcid": "0000-0002-5341-4448"
    },
    {
      "affs": [
        5,
        6,
        7,
        8
      ],
      "name": "Stefano Martiniani",
      "orcid": "0000-0003-2028-2175"
    },
    {
      "affs": [
        0
      ],
      "name": "Gregory R. Stewart",
      "orcid": "0000-0001-7251-1684"
    },
    {
      "affs": [
        0
      ],
      "name": "J. J. Hamlin",
      "orcid": "0000-0002-8685-153X"
    },
    {
      "affs": [
        0
      ],
      "name": "P. J. Hirschfeld",
      "orcid": "0000-0003-0375-7386"
    },
    {
      "affs": [
        2,
        0,
        1
      ],
      "name": "Richard G. Hennig",
      "orcid": "0000-0003-4933-7686"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/bhvkrs46wj5e7.bib",
  "cited_by": 12,
  "doi": "10.1038/s41524-026-02117-7",
  "fulltext_url": null,
  "id": "bhvkrs46wj5e7",
  "issns": [
    "2057-3960"
  ],
  "landing_url": "https://doi.org/10.1038/s41524-026-02117-7",
  "language": "en",
  "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": "W4415337892",
  "pdf_url": "https://www.nature.com/articles/s41524-026-02117-7_reference.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-05-28",
  "publisher": "Nature Portfolio",
  "ris": "https://research.draconitic.com/paper/bhvkrs46wj5e7.ris",
  "sources": [
    {
      "first_seen": "2026-11-07T13:21:06Z",
      "native_id": "W4415337892",
      "source": "openalex",
      "url": "https://doi.org/10.1038/s41524-026-02117-7"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:2505|Machine Learning in Materials Science",
      "subfield": "materials-polymers"
    }
  ],
  "title": "Guided diffusion for the discovery of new superconductors",
  "title_text": "Guided diffusion for the discovery of new superconductors",
  "type": "peer-reviewed",
  "updated_at": "2026-11-09T13:21:22Z",
  "url": "https://research.draconitic.com/paper/bhvkrs46wj5e7",
  "venue": "npj Computational Materials",
  "versions": []
}