{"id":"W4308643083","doi":"10.1145/3540250.3558952","title":"Leveraging test plan quality to improve code review efficacy","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Code review; Leverage (statistics); Documentation; Code coverage; Test case; Source code; Natural language; Transformer; Test (biology); Software engineering; Software quality; Artificial intelligence; Data science; Information retrieval; Natural language processing; Machine learning; Programming language; Software; Software development; Engineering","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","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002518982,0.000488933,0.0006021413,0.0003939801,0.0004519894,0.0002287757,0.003736594,0.00004594097,0.00002331403],"category_scores_gemma":[0.02618017,0.0003982529,0.0002291504,0.001335765,0.00007912646,0.0003691946,0.003281934,0.0009243518,0.00001246919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000184417,"about_ca_system_score_gemma":0.0001155662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001377799,"about_ca_topic_score_gemma":1.721991e-7,"domain_scores_codex":[0.9966007,0.00005996388,0.0009449482,0.000737372,0.001037161,0.0006198834],"domain_scores_gemma":[0.993951,0.003433764,0.0004100094,0.001426782,0.0005279639,0.0002504442],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0001631936,0.001746591,0.08668102,0.02451716,0.001416457,0.00004179507,0.01911496,0.3798068,0.3681652,0.07911306,0.01552831,0.02370543],"study_design_scores_gemma":[0.006115834,0.004555349,0.6869663,0.03324091,0.0007153902,0.0007004577,0.001000687,0.0671,0.1236059,0.001090722,0.06510384,0.009804649],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6300486,0.001437841,0.350787,0.008788733,0.002080319,0.003626456,0.0002667622,0.002774289,0.0001899491],"genre_scores_gemma":[0.9597223,0.0001869657,0.03923455,0.0003061479,0.00009797969,0.0001845447,0.000008526305,0.000115852,0.000143091],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6002853,"threshold_uncertainty_score":0.9998469,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04372462117162971,"score_gpt":0.2599137776609984,"score_spread":0.2161891564893687,"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."}}