{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1494695,0.0006870993,0.001000297,0.007879945,0.008473276,0.01051998,0.00356394,0.004016904,0.004096168],"category_scores_gemma":[0.6571236,0.001425936,0.0007696266,0.006590031,0.01037024,0.01223787,0.008149331,0.006964841,0.0008612851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01098821,"about_ca_system_score_gemma":0.0149196,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004227138,"about_ca_topic_score_gemma":0.004957409,"domain_scores_codex":[0.7241344,0.219229,0.01345407,0.008221203,0.0306706,0.004290706],"domain_scores_gemma":[0.07422322,0.7969522,0.08051897,0.01054627,0.03187165,0.005887656],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.001026757,0.001856768,0.1673068,0.003068903,0.0001489476,0.001039492,0.7574213,0.0002923877,0.001022563,0.005054775,0.004154339,0.05760695],"study_design_scores_gemma":[0.0006288085,0.003086198,0.2403776,0.005532396,0.0002328976,0.001692323,0.683727,0.003058825,0.001835837,0.006287228,0.05318095,0.0003598779],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9782065,0.00191325,0.004123826,0.002914208,0.0001220767,0.00137554,0.0001869677,0.00005945157,0.01109819],"genre_scores_gemma":[0.9914483,0.000863589,0.003303401,0.001189446,0.00008124812,0.001657265,0.0001897603,0.00006001497,0.001207105],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8505305,"threshold_uncertainty_score":0.7904797,"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."}}