CoREB is a contamination-limited multitask benchmark for code search covering text-to-code, code-to-text and code-to-code tasks, with a fine-tuned reranker that delivers consistent gains where prior models do not.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Beyond Retrieval: A Multitask Benchmark and Model for Code Search
CoREB is a contamination-limited multitask benchmark for code search covering text-to-code, code-to-text and code-to-code tasks, with a fine-tuned reranker that delivers consistent gains where prior models do not.