{"id":"W4398795735","doi":"10.1145/3664646.3665664","title":"AI-Assisted Assessment of Coding Practices in Modern Code Review","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Google (Canada)","funders":"DeepMind","keywords":"Computer science; Java; Best practice; Software engineering; Python (programming language); Workflow; Coding (social sciences); Programming language; Software deployment; Code review; Static program analysis; Software development; Software; Database","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":[],"consensus_categories":[],"category_scores_codex":[0.001832175,0.0002104201,0.0004903391,0.0003869352,0.00001326937,0.0002113341,0.001634622,0.000139482,0.00003168751],"category_scores_gemma":[0.00103618,0.000188131,0.0001159842,0.0006363381,0.00002093132,0.0001639179,0.004409143,0.001421223,0.00001457741],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000261856,"about_ca_system_score_gemma":0.0006406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001737983,"about_ca_topic_score_gemma":0.00004188304,"domain_scores_codex":[0.9975758,0.0001430361,0.0005257063,0.0007224834,0.0007593218,0.0002736677],"domain_scores_gemma":[0.9973234,0.0009291391,0.0002835417,0.001218194,0.0001730383,0.00007267584],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001141346,0.001183056,0.02232963,0.2212549,0.00101841,0.001247825,0.001538755,0.0396,0.002572196,0.1631323,0.06012163,0.48599],"study_design_scores_gemma":[0.0001180412,0.00003196186,0.01218339,0.01620591,0.00003228626,0.00001924711,0.000005329956,0.9627546,0.0002011299,0.007129261,0.0009522708,0.0003665712],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002045513,0.02564129,0.9545301,0.01023017,0.001069402,0.001056756,0.00001299309,0.0006776529,0.004736164],"genre_scores_gemma":[0.7787283,0.008107846,0.2115471,0.0004967399,0.00005773878,0.0002474571,0.00001567541,0.00004505881,0.0007540903],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9231546,"threshold_uncertainty_score":0.7671761,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1117525305005444,"score_gpt":0.4417333888704112,"score_spread":0.3299808583698668,"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."}}