{"id":"W4394906543","doi":"10.1145/3660806","title":"An Empirical Study on Code Review Activity Prediction and Its Impact in Practice","year":2024,"lang":"en","type":"preprint","venue":"Proceedings of the ACM on software engineering.","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ubisoft (Canada); Queen's University","funders":"Mitacs","keywords":"Code (set theory); Computer science; Programming language","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008386633,0.0003569017,0.000578652,0.000566588,0.00006792581,0.0005250692,0.003126606,0.0001305828,0.000008647277],"category_scores_gemma":[0.07241864,0.0002235533,0.0001635796,0.001247492,0.00002742095,0.0003188261,0.005830531,0.001162008,0.00002494287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001804393,"about_ca_system_score_gemma":0.00006955301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002082268,"about_ca_topic_score_gemma":0.000001847248,"domain_scores_codex":[0.9956682,0.0000649366,0.0006871852,0.001380949,0.001932357,0.0002663115],"domain_scores_gemma":[0.9959208,0.001297949,0.0004604891,0.001772693,0.0004209727,0.0001271051],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.001317635,0.008665771,0.2650301,0.01197746,0.001278891,0.00006284791,0.01133781,0.08790443,0.0007404943,0.0005933176,0.4851822,0.1259091],"study_design_scores_gemma":[0.0009428244,0.002281287,0.8507248,0.01664965,0.0007191857,0.00003874425,0.0009088219,0.1099831,0.0005482754,0.004038928,0.01196654,0.001197839],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9933117,0.00118127,0.00009601632,0.002050617,0.001470029,0.001367701,0.0001707597,0.0002369019,0.0001150202],"genre_scores_gemma":[0.9982786,0.0001563743,0.001089056,0.0001596303,0.0001149899,0.00006636334,0.000003439919,0.0000321726,0.00009934509],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5856947,"threshold_uncertainty_score":0.9353948,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1013324913904522,"score_gpt":0.4411874478183851,"score_spread":0.339854956427933,"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."}}