{"id":"W2029277954","doi":"10.1007/s11219-014-9230-x","title":"Predicting defective modules in different test phases","year":2014,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Engineering Research","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Benchmark (surveying); Reliability engineering; Computer science; Predictive modelling; Software; Data mining; Machine learning; Engineering; Programming language","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002185112,0.0002069104,0.0003063884,0.0002966179,0.0002060906,0.0003368088,0.0009748182,0.00008318647,0.00001972346],"category_scores_gemma":[0.02058557,0.0001721358,0.0001224646,0.000410061,0.00005501793,0.0005254085,0.0002701619,0.000795216,0.00001679164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002450656,"about_ca_system_score_gemma":0.00007455175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005519609,"about_ca_topic_score_gemma":0.00003182158,"domain_scores_codex":[0.9974374,0.000399332,0.0004949472,0.0003686375,0.0007339068,0.0005657681],"domain_scores_gemma":[0.9913775,0.007488403,0.0001580588,0.0005143693,0.000193303,0.0002683169],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000005858327,0.0001762461,0.955646,0.0000290076,0.0000155526,0.00002042229,0.0007374058,0.0008291244,0.0001672071,0.0005993443,0.0001559961,0.04161788],"study_design_scores_gemma":[0.0008814159,0.0002267933,0.9770135,0.0001608389,0.000003638562,0.000149792,0.00005194082,0.009707811,0.0008735133,0.01044413,0.0001980785,0.0002884975],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4762267,0.00007991007,0.5229372,0.0001727877,0.0002612684,0.00006412946,0.000002687952,0.0002283698,0.00002686639],"genre_scores_gemma":[0.9752147,0.00001120805,0.02429132,0.00007014372,0.0003423236,0.0000122598,0.000001184069,0.00001749585,0.00003936582],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.498988,"threshold_uncertainty_score":0.9876645,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02811477016643656,"score_gpt":0.3126412137085472,"score_spread":0.2845264435421107,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}