Scientific Code Search at Scale: A Multi-Domain Dataset and Benchmark
Abstract
Scientists increasingly rely on open-source tools to support their research workflows, yet discovering relevant software among over 600 million GitHub repositories remains challenging. Existing code search benchmarks focus on general software engineering tasks and fail to capture the domain-specific vocabulary and needs of scientific computing. We present a curated corpus of 5,264 high-quality, domain-classified scientific repositories spanning five NASA Science Mission Directorate divisions -- Earth Science, Astrophysics, Planetary Science, Heliophysics, and Biological & Physical Sciences -- enriched with cleaned READMEs, extracted topics, and additional context from crawled links. Building on this corpus, we introduce two novel information retrieval benchmarks: (1) a repository search benchmark with 219 expert-curated queries designed by domain scientists, and (2) a large-scale code snippet retrieval benchmark containing 117,950 code snippets and 119,720 queries across seven programming languages. Baseline evaluations on repository search reveal significant performance variation across scientific domains. Code snippet retrieval proves equally challenging, with substantial variation driven by differing documentation practices, coding standards, and programming language conventions across scientific communities. All datasets and benchmarks are publicly released on HuggingFace to support research on scientific tool discovery.
Cite
@article{arxiv.2607.05443,
title = {Scientific Code Search at Scale: A Multi-Domain Dataset and Benchmark},
author = {Nishan Pantha and Pranath Reddy Kumbam and Sajil Awale and Pushwitha Krishnappa and Muthukumaran Ramasubramanian and Nidhi Jha and Emily Foshee and Ankur Kumar and Rachel Slank and Ashkbiz Danehkar and Rahul Ramachandran},
journal= {arXiv preprint arXiv:2607.05443},
year = {2026}
}
Comments
Datasets and benchmarks publicly released on HuggingFace. Code released on GitHub