{"id":"W2597809331","doi":"10.1109/msr.2017.65","title":"Extracting Build Changes with BUILDDIFF","year":2017,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Code refactoring; Computer science; Java; Software evolution; Software; Precision and recall; Software maintenance; Software engineering; Software system; Data mining; Machine learning; Software construction; Programming language","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":[0.0002059776,0.00007603098,0.00007112556,0.00005618887,0.0002669187,0.0005478183,0.001399546,0.00002672158,0.0000227828],"category_scores_gemma":[0.0004276535,0.00005613922,0.00001217222,0.00005955478,0.00003435169,0.0004559561,0.0003595038,0.0001277541,0.0000548022],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001795037,"about_ca_system_score_gemma":0.00002609337,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000811166,"about_ca_topic_score_gemma":0.00003842069,"domain_scores_codex":[0.9991876,0.000007172913,0.00003710869,0.0002382716,0.0002636655,0.0002661452],"domain_scores_gemma":[0.9984837,0.0002376047,0.00003698653,0.00111114,0.00004930052,0.00008133028],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00001614294,0.0001205716,0.3110337,0.00008506535,0.00008566325,0.0004865835,0.0008647219,0.0003332062,0.008598167,0.05988524,0.006177227,0.6123137],"study_design_scores_gemma":[0.00108755,0.0004318366,0.8612962,0.0001549897,0.000006389203,0.000234313,0.00004486475,0.04216465,0.05243434,0.0005938128,0.04063505,0.0009160133],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1567348,0.00004646485,0.8289761,0.005771252,0.0002581833,0.0001166962,3.061969e-7,0.0006489954,0.007447223],"genre_scores_gemma":[0.8933028,0.000003528066,0.1044981,0.00004764006,0.00008243732,0.00001080774,8.645381e-8,0.000008567898,0.002045999],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.736568,"threshold_uncertainty_score":0.5282624,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02941656900788611,"score_gpt":0.2943552129454998,"score_spread":0.2649386439376137,"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."}}