Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Early Failure Detection on RoboCasa (Unseen)

76.3ROC-AUC (q=0.25)

ActProbe

60.764.7568.872.85Jun 7, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
76.3
2026.06
73.8
2026.06
70.3
2026.06
65.9
2026.06
65.5
2026.06
64.7
2026.06
61.5
2026.06
61.3