{"id":"W2890687291","doi":"","title":"[Journal First] Are Fix-Inducing Changes a Moving Target?: A Longitudinal Case Study of Just-in-Time Defect Prediction","year":2018,"lang":"en","type":"article","venue":"International Conference on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Code (set theory); Brier score; Interpretation (philosophy); Calibration; Artificial intelligence; Statistics; Mathematics; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007114711,0.0002667503,0.0002945565,0.0009398002,0.000125042,0.0002716868,0.001110478,0.00009601819,0.0000951392],"category_scores_gemma":[0.001949751,0.0002792436,0.00008065091,0.0005456946,0.00003078877,0.0005130905,0.0003576498,0.0005528725,0.00002483698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003220608,"about_ca_system_score_gemma":0.00008489427,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001293905,"about_ca_topic_score_gemma":0.00009741957,"domain_scores_codex":[0.997654,0.00004749173,0.0004227357,0.0005189311,0.0009350703,0.0004217523],"domain_scores_gemma":[0.9981254,0.0005597922,0.0001724985,0.0004279365,0.0005672461,0.0001470908],"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":[0.00009671,0.001004612,0.8743044,0.0001695503,0.0004923844,0.008926717,0.01360959,0.09404387,0.00111106,0.0006527724,0.0002696979,0.005318602],"study_design_scores_gemma":[0.002500064,0.002212705,0.2190228,0.001781471,0.00002883245,0.005345139,0.001287748,0.7646173,0.002103164,0.00008237434,0.0001841475,0.000834196],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7819946,0.00002730403,0.2163737,0.000078617,0.001017836,0.0002085652,0.000008996376,0.000269389,0.0000209544],"genre_scores_gemma":[0.9867768,0.000006825514,0.01268726,0.00001193131,0.000398135,0.00004551573,0.000002042981,0.00003022219,0.00004131305],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6705735,"threshold_uncertainty_score":0.999966,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05035473449789288,"score_gpt":0.2965110632208014,"score_spread":0.2461563287229085,"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."}}