{"id":"W2067490448","doi":"","title":"The Impact of Mislabelling on the Performance and Interpretation of Defect Prediction Models","year":2018,"lang":"en","type":"article","venue":"Institutional Repositories DataBase (IRDB)","topic":"Software Engineering Research","field":"Computer Science","cited_by":89,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Noise (video); Reliability (semiconductor); Interpretation (philosophy); Artificial intelligence; Predictive modelling; Machine learning; Rank (graph theory); Training set; Data modeling; Recall; Data mining; Database; Mathematics; Cognitive psychology","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":[0.000545467,0.00008662631,0.00008019233,0.0000594018,0.0003756297,0.00007412103,0.000397641,0.00002750697,8.567355e-7],"category_scores_gemma":[0.0006921683,0.00004944461,0.00004825854,0.0002757639,0.0003992194,0.0006811576,0.0001620982,0.0001261432,0.000001745906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008241283,"about_ca_system_score_gemma":0.0001979385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001296364,"about_ca_topic_score_gemma":0.00000340558,"domain_scores_codex":[0.9990011,0.00004738442,0.0002140699,0.0001792389,0.0004251687,0.0001330232],"domain_scores_gemma":[0.9980981,0.0009825609,0.00008766595,0.000488151,0.0003084968,0.00003501828],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008256173,0.0002785807,0.05788846,0.0002903461,0.0006157952,0.00001403696,0.005532845,0.2993905,0.03859958,0.5692425,0.002346264,0.02497546],"study_design_scores_gemma":[0.0001293573,0.000376451,0.01430631,0.0002399597,0.000006883648,0.00003719868,0.00001291388,0.9562398,0.02797448,0.0004771556,0.0001307043,0.00006876013],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7504795,0.0001473225,0.24842,0.0000368022,0.0004456765,0.000119293,0.00003549235,0.00003497518,0.0002809458],"genre_scores_gemma":[0.9982514,0.00005905659,0.001515267,0.000004117102,0.0001299193,0.00001412023,0.00000863716,0.000003835326,0.00001358561],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6568493,"threshold_uncertainty_score":0.2889078,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01975086518738715,"score_gpt":0.2721726546332785,"score_spread":0.2524217894458913,"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."}}