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

apsfail

Benchmarks

Task NameDataset NameSOTA ResultTrend
Mislabel Detectionapsfail
AUROC0.971
17
Identifying mislabeled pointsapsfail
F1 Score48
12
Identifying mislabeled pointsapsfail
Precision (apsfail)36
12
Identifying mislabeled pointsapsfail
Recall73
12
Data Valuationapsfail
Valuation Runtime (s)0.47
5
Noisy Detectionapsfail
AUROC0.916
5
Verifiable Data Valuationapsfail
Proving Time (s)10.8
2
Showing 7 of 7 rows