FOTO: Figure-Level Semantic Search for Astronomy
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
Related
- Population-level correlations in Bayesian statistics: an illustrative model for gravitational-wave astronomy
- A Deep Neural Network based Level-1 Trigger for the Magnetic Monopole Search in the SCEP Experiment
- Transitioning from ADS to SciX to Serve 21st Century Astronomy
- From Axion Detection to Dark Matter Astronomy
- Neutrino Astronomy at High Energies - An Experimental Review
BibTeX
@misc{tohfa2026foto,
title = {{FOTO: Figure-Level Semantic Search for Astronomy}},
author = {Hurum Maksora Tohfa and Francisco Villaescusa-Navarro},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.30536},
eprint = {2609.30536},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.30536},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - FOTO: Figure-Level Semantic Search for Astronomy
AU - Hurum Maksora Tohfa
AU - Francisco Villaescusa-Navarro
PY - 2026
DA - 2026/09/24
PB - arXiv
DO - 10.48550/arxiv.2609.30536
UR - https://arxiv.org/abs/2609.30536
AB - 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
ER -