Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Sabotage Detection on DSTS (Distributed Sub-Threshold Sabotage)
Loading...
0.048
Max Power (A)
Monitor A
0.0456
0.0468
0.048
0.0492
Jun 9, 2026
Max Power (A)
SPRT Power (B)
AUC Gap (SPRT - A_max)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Max Power (A)
SPRT Power (B)
AUC Gap (SPRT - A_max)
Monitor A
Gate=Monitor A blindne...
2026.06
0.048
-
-
Monitor B (SPRT)
Gate=Detectability ban...
2026.06
-
0.688
0.438
Feedback
Search any
task
Search any
task
