{"id":"W3209001851","doi":"10.1016/j.infsof.2021.106756","title":"Early Prediction for Merged vs Abandoned Code Changes in Modern Code Reviews","year":2019,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Software Engineering Research","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Code review; Code (set theory); Machine learning; Source code; Artificial intelligence; Classifier (UML); Suite; Software; Source lines of code; Empirical research; Software inspection; Process (computing); 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":[],"consensus_categories":[],"category_scores_codex":[0.0004556519,0.000130138,0.0002193928,0.0002550391,0.00005066717,0.00003864863,0.000726037,0.00008083861,0.00001166184],"category_scores_gemma":[0.0001408222,0.0001433804,0.00006926359,0.0006793106,0.00002141534,0.0004274192,0.000163291,0.0001551704,0.00008296584],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001320546,"about_ca_system_score_gemma":0.00003626868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004226275,"about_ca_topic_score_gemma":0.0001185745,"domain_scores_codex":[0.9988477,0.00006728488,0.0001233893,0.0005360331,0.00008608463,0.0003395064],"domain_scores_gemma":[0.9989281,0.0002620979,0.00005573618,0.0005870959,0.00007355396,0.00009337615],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006643818,0.0004058477,0.6997093,0.0007821485,0.0001459985,0.0001598802,0.003491226,0.2225668,0.009110617,0.04781212,0.002953503,0.01219816],"study_design_scores_gemma":[0.001615163,0.0002395286,0.05732301,0.0001001147,0.000009744636,0.000001794907,0.00001231754,0.9351141,0.0006165984,0.001533678,0.003194302,0.0002395743],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5951705,0.00009530543,0.4037037,0.00007163641,0.0002106213,0.0005256318,0.00001049062,0.0001514603,0.00006063726],"genre_scores_gemma":[0.996617,0.0002329617,0.001239731,0.0000362098,0.00002885194,0.000006413597,0.000004497929,0.00001360641,0.001820745],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7125474,"threshold_uncertainty_score":0.5846883,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07216682349375034,"score_gpt":0.2064888295048538,"score_spread":0.1343220060111034,"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."}}