silentbug Benchmark
Explore score history ↗Evaluates agents on detecting silent ML training defects across 18 CPU-only PyTorch tasks, scoring patch application, metric recovery, localization, minimality, and false positives.
- Released
- 2026-08-20
- Evaluates
- Language & Knowledge, Software & AI Compute, cs.AI
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-name-audit-deferred
silentbug code
No reported scores are on record for this benchmark yet.