{"id":"W4391882875","doi":"10.3390/computers13020052","title":"Interpretable Software Defect Prediction from Project Effort and Static Code Metrics","year":2024,"lang":"en","type":"article","venue":"Computers","topic":"Software Engineering Research","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; Fanshawe College","funders":"","keywords":"Interpretability; Computer science; Predictive modelling; Machine learning; Software quality; Reliability (semiconductor); Software; Random forest; Software bug; Artificial intelligence; Data mining; Software metric; Support vector machine; Code (set theory); Source code; Quality (philosophy); Reliability engineering; Software development; Set (abstract data type); 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":[0.0002987867,0.0001532232,0.0001591593,0.0004355694,0.0000613079,0.0006127733,0.0005292978,0.0000564973,0.000004407939],"category_scores_gemma":[0.0002579499,0.0001431032,0.00006567502,0.0009734822,0.00003642993,0.0005054934,0.0004525184,0.0002421527,0.00002435337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001250863,"about_ca_system_score_gemma":0.0001123868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007855,"about_ca_topic_score_gemma":0.000002273897,"domain_scores_codex":[0.9986163,0.00003616662,0.0001740346,0.0005373247,0.0003400962,0.0002960599],"domain_scores_gemma":[0.9978517,0.001583635,0.00001811948,0.00040963,0.00003888901,0.00009803625],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002504211,0.0001175371,0.08646741,0.001012255,0.0008134298,0.000568399,0.008202625,0.01037937,0.0003077806,0.002279881,0.1100131,0.7798132],"study_design_scores_gemma":[0.0001702278,0.0001366241,0.009029706,0.0002365365,0.00001716872,0.00003017467,0.000008037186,0.9812185,0.0001596015,0.0006592284,0.008153281,0.0001809363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06993261,0.001539329,0.9252222,0.00007265367,0.001569174,0.000226786,0.00003226692,0.001384628,0.00002034961],"genre_scores_gemma":[0.7386892,0.00006697716,0.2608452,0.00008949349,0.0001237037,0.00003840761,0.00002403209,0.00003137495,0.00009160359],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9708391,"threshold_uncertainty_score":0.5908988,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01890795632843099,"score_gpt":0.2708190553122697,"score_spread":0.2519110989838387,"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."}}