You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Benchmark of 770 real-world AI software faults collected from 105 open-source repositories across 76 organizations, spanning traditional machine learning, deep learning, large language model infras…
A curated dataset of thousands residual Python bugs with paired fixed versions and multi-level natural language descriptions for fault injection and repair research.
A curated dataset of thousands residual Python bugs with paired fixed versions and multi-level natural language descriptions for fault injection and repair research.
Benchmark of 770 real-world AI software faults collected from 105 open-source repositories across 76 organizations, spanning traditional machine learning, deep learning, large language model infras…