{"id":"W4410771641","doi":"10.1145/3736405","title":"Improving Code Reviewer Recommendation: Accuracy, Latency, Workload, and Bystanders","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Workload; Code (set theory); Latency (audio); Operating system; Telecommunications; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1686667,0.001457875,0.002326608,0.001859211,0.001421004,0.003181978,0.002646645,0.00367666,0.005991756],"category_scores_gemma":[0.4792846,0.001104612,0.00345302,0.001712915,0.00203543,0.004657249,0.001902441,0.003397337,0.002306979],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002254135,"about_ca_system_score_gemma":0.005142894,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001500556,"about_ca_topic_score_gemma":0.002193892,"domain_scores_codex":[0.8089734,0.1382925,0.02031814,0.009471051,0.02094508,0.001999818],"domain_scores_gemma":[0.3070288,0.5809882,0.05014697,0.02934927,0.02742537,0.005061347],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.1477088,0.02483904,0.05341506,0.02537807,0.008585053,0.0001848627,0.002529474,0.008092523,0.009078204,0.002595476,0.01761445,0.699979],"study_design_scores_gemma":[0.1449692,0.5530471,0.1246972,0.007503968,0.01937063,0.0009645256,0.001828664,0.04792901,0.04182006,0.01506901,0.04154307,0.001257519],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.777763,0.02086974,0.1025967,0.01210611,0.004483835,0.05863597,0.004866925,0.00426592,0.01441174],"genre_scores_gemma":[0.8156888,0.002144194,0.1222152,0.003542241,0.001199348,0.05048587,0.001125914,0.0003524338,0.003246006],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1686667,"threshold_uncertainty_score":0.8920056,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07592995547935187,"score_gpt":0.3418730804869229,"score_spread":0.2659431250075711,"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."}}