| split,task,model,n,macro_f1,fail_precision,fail_recall,false_positive_rate,joint_accuracy,unknown_prediction_rate,invalid_or_missing,defect_n,defects_flagged,benign_n,false_alarms | |
| development_test,requirement_check,Base,1127,0.3131561888836168,0.9230769230769231,0.21314387211367672,0.01773049645390071,0.5306122448979592,0.1730257320319432,0,563,120,564,10 | |
| development_test,regression_search,Base,787,0.20545926331366943,0.9508196721311475,0.1475826972010178,0.007614213197969543,0.5336721728081322,0.0,0,393,58,394,3 | |
| development_test,keyboard_access,Base,27,0.8911064425770308,1.0,0.7777777777777778,0.0,0.8888888888888888,0.2962962962962963,0,9,7,9,0 | |
| development_test,requirement_check,UI-TestJev,1127,0.7301582607619586,0.8321167883211679,0.8099467140319716,0.16312056737588654,0.8234250221827861,0.0,0,563,456,564,92 | |
| development_test,regression_search,UI-TestJev,787,0.4053060518040957,0.9259259259259259,0.3816793893129771,0.030456852791878174,0.6315120711562897,0.0,0,393,150,394,12 | |
| development_test,keyboard_access,UI-TestJev,27,1.0,1.0,1.0,0.0,1.0,0.3333333333333333,0,9,9,9,0 | |
| development_test,requirement_check,Luna,1127,0.7118288899617797,0.8490196078431372,0.7690941385435168,0.13652482269503546,0.7985803016858918,0.02839396628216504,0,563,433,564,77 | |
| development_test,regression_search,Luna,787,0.5080121476615636,0.9590163934426229,0.5954198473282443,0.025380710659898477,0.7001270648030495,0.0038119440914866584,0,393,234,394,10 | |
| development_test,keyboard_access,Luna,27,0.9628482972136223,1.0,0.8888888888888888,0.0,0.9629629629629629,0.37037037037037035,0,9,8,9,0 | |