{
  "abstract": "Astronomy papers carry much of their content in figures, but literature search indexes text, so there is no way to find a plot by describing what it shows. We present FOTO, a figure-level search tool over 482,750 captions from 53,839 peer-reviewed astro-ph papers. Each figure is indexed once by its title and caption, embedded with a 110M-parameter open model that runs locally, and a large language model is applied only to the retrieved shortlist, where it verifies real figures rather than generating references to ones that do not exist. Held to the harder figure-level criterion, FOTO recovers the target for 29 to 79% of queries at recall 20 depending on register, against 6 to 20% for Pathfinder and 8 to 16% for Semantic Scholar on the easier paper-level criterion, and it beats the paid embedding API it replaced. Reranking the shortlist then raises recall at 1 from 0.667 to 0.875 on detailed queries and from 0.071 to 0.571 on vague ones. Openly available models match or beat paid LLM models for verification",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.30536",
  "author_total": 2,
  "authors": [
    {
      "name": "Hurum Maksora Tohfa"
    },
    {
      "name": "Francisco Villaescusa-Navarro"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/802tqc1sf579z.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.30536",
  "fulltext_url": null,
  "id": "802tqc1sf579z",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.30536",
  "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.IM"
    ],
    [
      "openalex",
      "1710|Information Retrieval and Search Behavior"
    ]
  ],
  "openalex": "W7214604815",
  "pdf_url": "https://arxiv.org/pdf/2609.30536",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-24",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/802tqc1sf579z.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:24:52Z",
      "native_id": "2609.30536",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.30536"
    }
  ],
  "subjects": [
    {
      "field": "astronomy",
      "origin": "arxiv:astro-ph.IM",
      "subfield": "instrumentation-methods"
    }
  ],
  "title": "FOTO: Figure-Level Semantic Search for Astronomy",
  "title_text": "FOTO: Figure-Level Semantic Search for Astronomy",
  "type": "preprint",
  "updated_at": "2026-10-30T12:24:52Z",
  "url": "https://research.draconitic.com/paper/802tqc1sf579z",
  "venue": "arXiv",
  "versions": []
}