{"id":"W2003920582","doi":"10.1145/1414004.1414063","title":"Analysis of the reliability of a subset of change metrics for defect prediction","year":2008,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Eclipse; Computer science; Reliability (semiconductor); Precision and recall; Software metric; Software quality; Data mining; Stability (learning theory); Software; Metric (unit); Software bug; Reliability engineering; Machine learning; Artificial intelligence; Software development; Engineering; Programming language","routes":{"ca_aff":true,"ca_fund":false,"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":[],"consensus_categories":[],"category_scores_codex":[0.0006077234,0.0000397959,0.0001658757,0.0003404844,0.00001881883,0.000001954479,0.0004572206,0.0000309404,0.000004341489],"category_scores_gemma":[0.001786447,0.00002655678,0.0002199282,0.003828808,0.0000509039,0.00008562228,0.0001128517,0.00003765668,1.288871e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000242757,"about_ca_system_score_gemma":0.0000320429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001711548,"about_ca_topic_score_gemma":0.00001052737,"domain_scores_codex":[0.9992199,0.00003302282,0.0001882449,0.0001336897,0.0003339876,0.00009115366],"domain_scores_gemma":[0.998027,0.001004237,0.00006908995,0.0005995419,0.0002798236,0.00002032586],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000005154894,0.00006784685,0.9947076,0.00006834787,0.0001281002,8.191055e-8,0.0004287398,0.00290018,0.0002769507,0.0003250629,0.0001460842,0.0009458128],"study_design_scores_gemma":[0.00008317614,0.00007372753,0.7957917,0.000003508005,0.00004940494,3.467771e-7,0.000002734351,0.1934062,0.01050281,0.00003549751,0.00002958191,0.00002122812],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.619179,0.00003642903,0.3804837,0.00003005222,0.00004715958,0.0001628029,0.00002154942,0.00002253076,0.00001673264],"genre_scores_gemma":[0.9887322,0.00001261816,0.01120091,0.000003786095,0.000006083142,0.00001909366,0.000001342094,0.0000021633,0.00002177763],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3695532,"threshold_uncertainty_score":0.2138673,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08058338221403603,"score_gpt":0.2897177058425626,"score_spread":0.2091343236285265,"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."}}