{"id":"W4388948694","doi":"10.1016/j.jss.2023.111914","title":"Commit-time defect prediction using one-class classification","year":2023,"lang":"en","type":"article","venue":"Journal of Systems and Software","topic":"Software Engineering Research","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Commit; Support vector machine; Computer science; Class (philosophy); Random forest; Binary number; Machine learning; Binary classification; Overhead (engineering); Software; Data mining; Artificial intelligence; Database; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001122228,0.00008703078,0.0002077771,0.0003364818,0.0001195651,0.000223906,0.0003173952,0.00007850764,0.000001842502],"category_scores_gemma":[0.0005644178,0.00007673162,0.00007354253,0.0005367781,0.00002184556,0.0004841356,0.00008846392,0.0002093768,0.0000234878],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001092945,"about_ca_system_score_gemma":0.0000844145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001559328,"about_ca_topic_score_gemma":2.641688e-7,"domain_scores_codex":[0.9987125,0.00008835393,0.0003583219,0.0001429569,0.0005040657,0.0001938103],"domain_scores_gemma":[0.9986557,0.0005170547,0.0001928897,0.0002424974,0.0002664188,0.0001254581],"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":[0.00008002287,0.0003023316,0.7813989,0.002060088,0.0009430216,0.0005039899,0.004857124,0.06890432,0.04028672,0.004360301,0.03413953,0.06216366],"study_design_scores_gemma":[0.0008257079,0.0003683794,0.3784895,0.0009195147,0.00003976349,0.0008526044,0.0001674316,0.6129517,0.0001278544,0.0002748679,0.004708955,0.0002737594],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5522478,0.0006538954,0.4456702,0.0001383033,0.0008782453,0.0001309325,0.00000599093,0.0002600198,0.00001452195],"genre_scores_gemma":[0.9929975,0.00006182803,0.006465848,0.000007820649,0.0002848283,0.00000352106,0.000001704929,0.00001527372,0.0001616926],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5440474,"threshold_uncertainty_score":0.3129025,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05332738242996626,"score_gpt":0.2774134836601288,"score_spread":0.2240861012301625,"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."}}