{"id":"W4319864592","doi":"10.2139/ssrn.4328070","title":"An Empirical Study on the Stability of Explainable Software Defect Prediction","year":2023,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Stability (learning theory); Computer science; Software; Software bug; Machine learning; 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":[0.01128197,0.000289836,0.0003940488,0.001993938,0.0005965553,0.001523472,0.0009892762,0.0008643784,0.002949542],"category_scores_gemma":[0.1563009,0.000223039,0.0005688678,0.001570945,0.001101625,0.002222163,0.000919827,0.001502471,0.0003194422],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006216603,"about_ca_system_score_gemma":0.0004999907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004753828,"about_ca_topic_score_gemma":0.003000355,"domain_scores_codex":[0.9964213,0.002142198,0.0002644089,0.0005607425,0.0004573547,0.0001540802],"domain_scores_gemma":[0.5725964,0.3867875,0.01986822,0.01177921,0.007283999,0.00168462],"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":[0.0005059002,0.0001983479,0.9788269,0.00003598932,0.0002960221,0.0001746652,0.0008850467,0.005955439,0.0006579166,0.001951184,0.000298694,0.01021382],"study_design_scores_gemma":[0.00006276356,0.0006209177,0.8853118,0.00003586875,0.0002182527,0.0004038917,0.001975711,0.10188,0.001004642,0.007704697,0.0007475158,0.00003399115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9974754,0.0001432658,0.001683417,0.0001292203,0.000005073182,0.000006358962,0.00009666525,0.00001022217,0.0004503071],"genre_scores_gemma":[0.9995,0.00002500606,0.0002000007,0.00001026553,0.000008306158,0.000002667265,0.0001690059,0.000004972615,0.00007971162],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01128197,"threshold_uncertainty_score":0.05966544,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02377250379194801,"score_gpt":0.2884570077219796,"score_spread":0.2646845039300316,"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."}}