{"id":"W2057780988","doi":"10.1016/j.jss.2007.05.035","title":"Applying machine learning to software fault-proneness prediction","year":2007,"lang":"en","type":"article","venue":"Journal of Systems and Software","topic":"Software Engineering Research","field":"Computer Science","cited_by":225,"is_retracted":false,"has_abstract":false,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Software metric; Machine learning; Computer science; Support vector machine; Metric (unit); Software; Data mining; Artificial neural network; Artificial intelligence; Binary classification; Fault (geology); Software quality; Software fault tolerance; Reliability engineering; Software development; Engineering","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":[0.002180558,0.0001631056,0.0003160851,0.0004465076,0.0001972583,0.0002628205,0.000506736,0.0001030485,0.0000023893],"category_scores_gemma":[0.001669658,0.0001373995,0.00007079844,0.0004755844,0.00001788076,0.0005183185,0.0001940285,0.0004934507,0.000007624949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001322082,"about_ca_system_score_gemma":0.00006826596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005426441,"about_ca_topic_score_gemma":0.000002716932,"domain_scores_codex":[0.9980107,0.00005941247,0.0005684802,0.0002365047,0.0007431595,0.0003817648],"domain_scores_gemma":[0.9980488,0.0007126622,0.0002229105,0.0002475017,0.000412147,0.0003559288],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008163505,0.00008285384,0.6808113,0.0006561563,0.0001420352,0.0005389961,0.002742252,0.05134263,0.001693093,0.0003801491,0.0007654172,0.2607635],"study_design_scores_gemma":[0.005443265,0.004949303,0.6010224,0.005109234,0.0001036383,0.01056109,0.001574997,0.05652788,0.001873332,0.0004024766,0.3102111,0.002221297],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1598585,0.002144885,0.836548,0.00004049145,0.0009558763,0.0002541168,0.00000315226,0.0001887174,0.000006313451],"genre_scores_gemma":[0.9445174,0.00005039732,0.05462971,0.00003744096,0.0004740622,0.00002065176,0.000001453392,0.00003004076,0.0002388496],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7846589,"threshold_uncertainty_score":0.560299,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.016601231710283,"score_gpt":0.257734263122009,"score_spread":0.241133031411726,"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."}}