raw/table2.csv

source,dataset,methods,best_method,care_wins,status,reason
claims.C1_C2_C3_tables.table2_civilcomments_pku_better.datasets,CivilComments,"[{'method': 'MV', 'reproduced_acc_mean': 0.6921825050857308, 'reproduced_acc_std': 0.0035258938420466247, 'n_seeds': 5, 'paper_acc': 0.691, 'abs_diff': 0.0011825050857308117}, {'method': 'AVG', 'reproduced_acc_mean': 0.690671316477768, 'reproduced_acc_std': 0.0029321704750082983, 'n_seeds': 5, 'paper_acc': 0.69, 'abs_diff': 0.0006713164777680802}, {'method': 'WS', 'reproduced_acc_mean': 0.7387968613775066, 'reproduced_acc_std': 0.0027980482189854067, 'n_seeds': 5, 'paper_acc': 0.739, 'abs_diff': 0.00020313862249343728}, {'method': 'UWS', 'reproduced_acc_mean': 0.7132810229584423, 'reproduced_acc_std': 0.003317321284539603, 'n_seeds': 5, 'paper_acc': 0.713, 'abs_diff': 0.00028102295844234515}, {'method': 'Dawid-Skene', 'reproduced_acc_mean': 0.735490244504816, 'reproduced_acc_std': 0.0, 'n_seeds': 5, 'paper_acc': 0.735, 'abs_diff': 0.0004902445048160509}, {'method': 'GLAD', 'reproduced_acc_mean': 0.7030377871079279, 'reproduced_acc_std': 0.003534412214373545, 'n_seeds': 5, 'paper_acc': 0.695, 'abs_diff': 0.008037787107927907}, {'method': 'MACE', 'reproduced_acc_mean': 0.732279575203754, 'reproduced_acc_std': 0.0, 'n_seeds': 5, 'paper_acc': 0.732, 'abs_diff': 0.00027957520375399003}, {'method': 'CARE-SVD', 'reproduced_acc_mean': 0.7797733217088056, 'reproduced_acc_std': 0.0030299125879635963, 'n_seeds': 5, 'paper_acc': 0.778, 'abs_diff': 0.0017733217088056197}, {'method': 'CARE-Tensor', 'reproduced_acc_mean': 0.7548387096774194, 'reproduced_acc_std': 0.007679560186298186, 'n_seeds': 5, 'paper_acc': 0.749, 'abs_diff': 0.005838709677419396}]",CARE-SVD,True,,
claims.C1_C2_C3_tables.table2_civilcomments_pku_better.datasets,PKU-BETTER,[],,,BLOCKED,released labels cannot support an accuracy; see label_audit