{
  "abstract": "I train a conditional flow matching model on the positions, photometry, and astrometry of $\\sim$ 579 million sources from the Gaia Data Release 3 Source Catalog. Using a probabilistic masking scheme during training, I develop a model capable of generating mock Gaia catalog sources with and without partial measurements of real Gaia sources. The model can produce coarse-grained mock Gaia Source Catalogs that reproduce the Milky Way disk and Magellanic Clouds, and can impute photometric and kinematic information. The model fails to reproduce small, distinct subpopulations like $ω$ Centauri. This model is a necessary step towards a foundation model trained on the entirety of Gaia data products, and provides a blueprint for future work with the upcoming Gaia Data Release 4.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.38326",
  "author_total": 1,
  "authors": [
    {
      "name": "John Soltis"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/e05jxfx663vh1.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.38326",
  "fulltext_url": null,
  "id": "e05jxfx663vh1",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.38326",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "astro-ph.GA"
    ],
    [
      "openalex",
      "3103|Stellar, planetary, and galactic studies"
    ]
  ],
  "openalex": "W7215032136",
  "pdf_url": "https://arxiv.org/pdf/2609.38326",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-29",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/e05jxfx663vh1.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:25:48Z",
      "native_id": "2609.38326",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.38326"
    }
  ],
  "subjects": [
    {
      "field": "astronomy",
      "origin": "arxiv:astro-ph.GA",
      "subfield": "galaxies"
    }
  ],
  "title": "Learning Gaia: A Generative Model Trained on the Gaia Data Release 3 Source Catalog",
  "title_text": "Learning Gaia: A Generative Model Trained on the Gaia Data Release 3 Source Catalog",
  "type": "preprint",
  "updated_at": "2026-10-30T12:25:48Z",
  "url": "https://research.draconitic.com/paper/e05jxfx663vh1",
  "venue": "arXiv",
  "versions": []
}