{"id":"W3028200206","doi":"10.1007/s10664-020-09837-4","title":"Do code review measures explain the incidence of post-release defects?","year":2020,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Operationalization; Code (set theory); Computer science; Replication (statistics); Code review; Replicate; Variable (mathematics); Empirical research; Contrast (vision); Econometrics; Statistics; Software; Software quality; Artificial intelligence; Mathematics; Software development; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0007110306,0.0002739926,0.0004014393,0.00008233248,0.00007849156,0.00008265262,0.001897732,0.0000835216,0.00003239276],"category_scores_gemma":[0.02309965,0.0002087581,0.0001928687,0.001358588,0.0000494724,0.0003111155,0.0006128293,0.0005663909,0.00008041334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007453182,"about_ca_system_score_gemma":0.0001299364,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001172093,"about_ca_topic_score_gemma":9.106299e-7,"domain_scores_codex":[0.9975201,0.00009960772,0.000441148,0.0005055402,0.0009324139,0.0005011156],"domain_scores_gemma":[0.9957696,0.002729369,0.00007951804,0.0008147147,0.0002430942,0.0003636764],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001190493,0.0004650817,0.4375103,0.01812414,0.0006595632,0.001053008,0.01107935,0.3001052,0.01144747,0.003192065,0.1037074,0.1125374],"study_design_scores_gemma":[0.002886598,0.002184752,0.4807734,0.01270256,0.0002825493,0.0004623859,0.000115664,0.1906016,0.03027898,0.0004153284,0.2738061,0.00549013],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05263807,0.02117191,0.9197892,0.004700792,0.000211846,0.0004275347,0.00001039186,0.001042225,0.00000801839],"genre_scores_gemma":[0.9706662,0.0006550918,0.02553305,0.002837339,0.0001571289,0.00008211839,0.000003453077,0.00005374529,0.00001184328],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9180282,"threshold_uncertainty_score":0.9851292,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0425573360393303,"score_gpt":0.2947060225830564,"score_spread":0.2521486865437261,"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."}}