{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001217004,0.0002217222,0.0003196405,0.0004004621,0.0001759987,0.00009389201,0.0004354367,0.0001616107,0.00001378736],"category_scores_gemma":[0.00893792,0.00022459,0.00005800452,0.0005945713,0.00004746577,0.0002688158,0.00006728656,0.0005061047,0.000003725343],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006457245,"about_ca_system_score_gemma":0.00006356905,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003500407,"about_ca_topic_score_gemma":0.000006708311,"domain_scores_codex":[0.9985351,0.0001776422,0.0002768605,0.0005309476,0.0001145004,0.0003649499],"domain_scores_gemma":[0.9904959,0.008611148,0.000041264,0.0006174088,0.0001099035,0.0001243286],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001538614,0.00002359167,0.0008154167,0.0002506051,0.00008359687,0.00000605357,0.0002238947,0.002817267,0.0002580324,0.0006112173,0.0001595464,0.9947354],"study_design_scores_gemma":[0.01564259,0.002512947,0.1073671,0.006655921,0.001056204,0.001556202,0.0008997148,0.3654872,0.03635348,0.0196642,0.4337027,0.009101804],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003505556,0.001915928,0.9913905,0.001183411,0.001145877,0.0001955124,0.000005608124,0.0006505761,0.000007024596],"genre_scores_gemma":[0.03277662,0.001748326,0.9647921,0.0002910633,0.00003506319,0.00008940395,0.000002271099,0.00002369087,0.000241419],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9856336,"threshold_uncertainty_score":0.9994102,"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."}}