hackathon-ENGIN/archive/legacy_experiments/robustness_summary.csv

765 B

1scenarioseedsmacro_f1_meanmacro_f1_stdmacro_f1_minmacro_f1_maxseverity_meanseverity_stdseverity_minseverity_maxraw_score_meanraw_score_stdraw_score_minraw_score_maxml_points_meanml_points_min
2clean50.95835475596529530.0051339269429745350.95183896297057440.96590653931885230.65263157894736850.0313834102105233560.6315789473684210.70175438596491220.88192396171081340.0090828083154674710.8717739590700360.895393000656158616.3847923421626914.354791814007184
3masked_5pct50.9541504510229830.0051669268276099760.94653402548139380.95993920555324060.6315789473684210.030386856273138260.61403508771929830.68421052631578950.87350757510934240.0107504009885524420.86340929104086990.891007035743877914.7015150218684812.68185820817398