{"id":"W2894722607","doi":"10.1145/3239235.3239525","title":"An empirical study of design discussions in code review","year":2018,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Japan Society for the Promotion of Science","keywords":"Computer science; Code (set theory); Software engineering; Focus (optics); Empirical research; Software quality; Software design; Software; Code review; Programming language; Software development; Epistemology","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":[0.0007557474,0.00005239321,0.000131618,0.00008625413,0.00002060962,0.00001553636,0.0007418685,0.00001702159,0.00004348177],"category_scores_gemma":[0.0004866498,0.00003334778,0.00001266203,0.0006757403,0.0000237733,0.0001613522,0.0001576146,0.00007957403,0.00003097454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001809061,"about_ca_system_score_gemma":0.00004583444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000347345,"about_ca_topic_score_gemma":0.00004656757,"domain_scores_codex":[0.9990456,0.0001702726,0.0001695906,0.000204686,0.0002620622,0.0001478292],"domain_scores_gemma":[0.9989144,0.0003122289,0.00001529476,0.0006198582,0.00006278945,0.00007544225],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002975885,0.008769533,0.7318679,0.000502248,0.00005413882,0.0001242584,0.01287607,0.001218597,0.001402059,0.001987372,0.06326367,0.1779044],"study_design_scores_gemma":[0.0009481977,0.006161587,0.8794178,0.0007252861,0.000007904316,0.000009344369,0.0001959832,0.1090933,0.001473818,0.0004707942,0.001118195,0.000377737],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1066718,0.0001821307,0.8919253,0.0005440688,0.0000581754,0.0004065773,1.997012e-7,0.000123938,0.00008775396],"genre_scores_gemma":[0.9572043,0.00002706356,0.04257879,0.00008761527,0.0000143956,0.00002070783,1.06808e-7,0.000004270188,0.00006272335],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8505325,"threshold_uncertainty_score":0.1378589,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1024041161298065,"score_gpt":0.4161624724902682,"score_spread":0.3137583563604617,"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."}}