{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01172784,0.001794627,0.001679805,0.005515385,0.0004809652,0.001085621,0.0008189986,0.001139627,0.0005209742],"category_scores_gemma":[0.07028923,0.0004380504,0.001199151,0.002592206,0.0004270076,0.001590651,0.0006507514,0.001236417,0.0005249613],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004151203,"about_ca_system_score_gemma":0.0005510225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003187781,"about_ca_topic_score_gemma":0.002842793,"domain_scores_codex":[0.9931452,0.002803965,0.0005810107,0.001080777,0.002098273,0.0002907195],"domain_scores_gemma":[0.8688802,0.09730582,0.006726163,0.01204016,0.01373073,0.00131694],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002432037,0.0006051718,0.5991499,0.0004146441,0.00217717,0.0004031459,0.0004300126,0.1461459,0.0287709,0.0003035667,0.002482236,0.2166854],"study_design_scores_gemma":[0.00003712189,0.001470565,0.1564193,0.0000401468,0.0004045834,0.0004784984,0.0000944445,0.8259324,0.01380845,0.0006248729,0.0006317499,0.00005781188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.934215,0.001053378,0.061097,0.0001894819,0.00005989612,0.00007012725,0.001162532,0.001347729,0.0008048695],"genre_scores_gemma":[0.9888119,0.0001179894,0.009317461,0.00002107845,0.00003293866,0.00002698676,0.001433799,0.00009374576,0.0001441382],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01172784,"threshold_uncertainty_score":0.06202346,"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."}}