{"id":"W3197188256","doi":"10.1016/j.infsof.2021.106756","title":"Early prediction for merged vs abandoned code changes in modern code reviews","year":2021,"lang":"en","type":"preprint","venue":"Information and Software Technology","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Code review; Code (set theory); Machine learning; Classifier (UML); Artificial intelligence; Source code; Suite; Software; Source lines of code; Process (computing); Empirical research; Software inspection; Software engineering; Software development; Software quality; Programming language; Statistics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006948312,0.000257227,0.0005049872,0.001129651,0.00008606272,0.0002449004,0.0008116492,0.0007149159,0.000004075764],"category_scores_gemma":[0.002309292,0.0002665539,0.00006852231,0.0005634676,0.0000645634,0.0006880573,0.001019732,0.0007356693,0.000007541021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001356586,"about_ca_system_score_gemma":0.0001395351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003019111,"about_ca_topic_score_gemma":0.0001465156,"domain_scores_codex":[0.998332,0.0000421217,0.0006077974,0.0003900664,0.0002501688,0.0003778833],"domain_scores_gemma":[0.9983855,0.0002286332,0.0002387678,0.0008021893,0.0002759395,0.00006895702],"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":[0.00005001739,0.00005935985,0.02556434,0.002217687,0.00006955799,0.000009333166,0.005842906,0.002319842,0.00007393779,0.001820089,0.001455175,0.9605178],"study_design_scores_gemma":[0.007308229,0.00109953,0.09384291,0.003940111,0.00007974333,0.0001875606,0.0003691948,0.7329873,0.00392464,0.02891108,0.1245873,0.002762361],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08140249,0.002149711,0.9114838,0.001575434,0.0005580251,0.00127895,0.00008699967,0.001456034,0.000008543647],"genre_scores_gemma":[0.6322998,0.009891513,0.3507401,0.0006887019,0.0001218641,0.005313387,0.0007383072,0.00006324881,0.0001430888],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9577554,"threshold_uncertainty_score":0.9999787,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02435593368266787,"score_gpt":0.27361690913263,"score_spread":0.2492609754499622,"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."}}