AI Paper Atlas

Research map / Large language models / Agents, code and math

CLARC: C/C++ Benchmark for Robust Code Search

Kaicheng Wang, Liyan Huang, Weike Fang, Weihang Wang

ICLR 2026 · Large language models › Agents, code and math · approach: Execution-based code verification · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace identifiers with neutral names (neutralized setting)Voyage-code-3 · CLARC Group 2MRR: 92.10 -> 77.18Hurt
randomize identifier namesVoyage-code-3 · CLARC Group 2MRR: 92.10 -> 69.43Hurt
neutralize identifiersNomic · CLARC Group 2MRR: 91.61 -> 67.65Hurt
neutralize identifiersOpenAI-text-embedding-large · CLARC Group 2MRR: 81.66 -> 37.14Hurt
randomize identifiersCodeT5+ · CLARC Group 1MRR: 58.84 -> 29.52Hurt
compile to Assembly instead of C/C++Voyage-code-3 · CLARC Group 1MRR: 86.93 -> 29.02Hurt
compile to Assembly instead of C/C++OpenAI-text-embedding-large · CLARC Group 1MRR: 80.16 -> 8.61Hurt
fine-tune on standard training setCodeT5+ · CLARC Group 1 (standard)MRR: 58.84 -> 76.51Improved
fine-tune on randomized training setCodeT5+ · CLARC Group 1 (randomized)MRR: 29.52 -> 60.93Improved
fine-tune on standard training setOASIS · CLARC Group 2 (standard)MRR: 88.30 -> 78.26Hurt
fine-tune on randomized training setOASIS · CLARC Group 3 (randomized)MRR: 30.51 -> 15.53Hurt
fine-tune on neutralized training setOASIS · CLARC Group 1 (standard)MRR: 86.54 -> 87.48No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy