Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mislabel Detection on pol
Loading...
0.97
AUROC
KNN
-0.0076
0.2462
0.5
0.7538
May 5, 2026
May 7, 2026
May 10, 2026
May 12, 2026
May 15, 2026
May 17, 2026
May 20, 2026
AUROC
Updated 13d ago
Evaluation Results
Method
Method
Links
AUROC
KNN
N=10,000, d=48
2026.05
0.97
LSH-Shapley
N=10,000, d=48
2026.05
0.957
G-Shapley
N=10,000, d=48
2026.05
0.636
DS
N=10,000, d=48
2026.05
0.547
DB
N=10,000, d=48
2026.05
0.491
sv-soft
variant=soft
2026.05
0.31
inf
2026.05
0.14
beta-mc
variant=mc
2026.05
0.07
rand
2026.05
0.07
bv-mc
variant=mc
2026.05
0.06
bv-uw
variant=uw
2026.05
0.06
bv-fast
variant=fast
2026.05
0.05
sv
2026.05
0.05
sv-mc
variant=mc
2026.05
0.05
sv-uw
variant=uw
2026.05
0.05
lava
2026.05
0.05
loo
2026.05
0.03
Feedback
Search any
task
Search any
task
