{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008098936,0.0001424626,0.0002010439,0.0001241055,0.0004489837,0.00007430957,0.0009454832,0.00006669177,0.000007965285],"category_scores_gemma":[0.0002864692,0.00008428935,0.0001524922,0.0008653443,0.00005241059,0.0004693322,0.00009810945,0.001099503,0.00003781564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005048107,"about_ca_system_score_gemma":0.00120267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000332837,"about_ca_topic_score_gemma":0.00007379634,"domain_scores_codex":[0.9968564,0.0005666527,0.0003968383,0.0003383161,0.0005944332,0.001247348],"domain_scores_gemma":[0.9984444,0.0003183897,0.0001557215,0.00083854,0.0001694652,0.00007348762],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006543309,0.0007268412,0.9804343,0.0000196658,0.0001252248,0.000004494233,0.004158804,0.0005042294,0.000100861,0.003328888,0.0002650169,0.01026622],"study_design_scores_gemma":[0.001743089,0.01368269,0.8012946,0.00006515831,0.00006396597,0.000232805,0.02689264,0.01181765,0.001192369,0.1422261,0.0003265719,0.0004623872],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9448805,0.00007600505,0.0536627,0.0004011437,0.000331631,0.0003733726,0.000001950743,0.0002357026,0.00003695929],"genre_scores_gemma":[0.9996555,0.0000663076,0.00006061079,0.00003391464,0.0001138762,0.00002830941,0.000001210623,0.000009649433,0.00003060604],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1791397,"threshold_uncertainty_score":0.4776856,"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."}}