CLAIM-2026-10-14-01

CRBugBench mines human-verified bugs from repository history and pairs each with the pull request that introduced it, comprising 1,000 review tasks across 98 open-source GitHub repositories plus 800 tasks from proprietary repositories at one large company.

Why it matters

Eight hundred of the tasks come from one company's own code. That split is the only part of the benchmark that resembles your repository.

Sources

• arxiv2026when