{"id":"W2385483600","doi":"10.1145/2884781.2884839","title":"Cross-project defect prediction using a connectivity-based unsupervised classifier","year":2016,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":249,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Homogeneity (statistics); Classifier (UML); Computer science; Reuse; Machine learning; Artificial intelligence; Metric (unit); Data mining; 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":[0.000559632,0.0001396042,0.0001284054,0.0002517331,0.0001160295,0.0002024641,0.0005302721,0.00008925701,0.00007372651],"category_scores_gemma":[0.0008564334,0.00009382527,0.0001065596,0.000587953,0.00006545457,0.0006310314,0.000147855,0.0001079717,0.00006364316],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001438697,"about_ca_system_score_gemma":0.0002707639,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001067135,"about_ca_topic_score_gemma":0.000006138373,"domain_scores_codex":[0.9984604,0.00009160873,0.0001591609,0.0004793516,0.0004046463,0.0004048247],"domain_scores_gemma":[0.9977922,0.001278482,0.0000257217,0.0006686564,0.0001423871,0.00009252313],"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":[0.00007049465,0.0002167809,0.8138755,0.00009677277,0.0001028169,0.00006415032,0.0002105072,0.005608651,0.1225079,0.01003233,0.001186331,0.04602776],"study_design_scores_gemma":[0.002210374,0.0002456113,0.2280674,0.0001008894,0.000007624595,0.00002913332,0.000004095295,0.7326429,0.03339237,0.0001589592,0.002737665,0.000402942],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3760774,0.00001076578,0.622578,0.00008757444,0.00023115,0.0001414104,0.000004076828,0.0006601869,0.0002094342],"genre_scores_gemma":[0.9638176,0.00000113353,0.03570585,0.00005361362,0.00007238719,0.00002603833,6.703501e-7,0.00001762777,0.000305104],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7270343,"threshold_uncertainty_score":0.3826084,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05826272584185882,"score_gpt":0.3199587132953625,"score_spread":0.2616959874535036,"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."}}