A multi-domain corpus of 5,264 scientific GitHub repos plus two IR benchmarks (219 expert queries; 117,950 snippets / 119,720 queries) shows large domain- and documentation-driven gaps in scientific code search.
The vault: A comprehensive multilingual dataset for advancing code understanding and generation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Scientific Code Search at Scale: A Multi-Domain Dataset and Benchmark
A multi-domain corpus of 5,264 scientific GitHub repos plus two IR benchmarks (219 expert queries; 117,950 snippets / 119,720 queries) shows large domain- and documentation-driven gaps in scientific code search.