{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003033686,0.001801364,0.0009251006,0.01327649,0.0007627233,0.002098382,0.001550812,0.001351217,0.00176701],"category_scores_gemma":[0.02887591,0.001240018,0.001332441,0.006579358,0.0005459483,0.003685846,0.002975842,0.001748879,0.001977188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007391094,"about_ca_system_score_gemma":0.001344419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003126927,"about_ca_topic_score_gemma":0.005377264,"domain_scores_codex":[0.9937266,0.0006833909,0.001037685,0.001701795,0.002620267,0.0002301491],"domain_scores_gemma":[0.968888,0.01139649,0.005240418,0.007988376,0.006056265,0.0004305525],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004336693,0.0002645401,0.1468684,0.002270695,0.0004050848,0.00140114,0.003526751,0.009527278,0.0302245,0.003759214,0.04849072,0.752828],"study_design_scores_gemma":[0.000180931,0.0007150897,0.273706,0.0006718909,0.0007431022,0.004162203,0.001956111,0.2267417,0.1320671,0.01476127,0.3437483,0.0005462554],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2364218,0.003230868,0.5542723,0.0006505476,0.0005918535,0.001269698,0.04963889,0.1450614,0.008862657],"genre_scores_gemma":[0.285938,0.001039233,0.5944442,0.0002823016,0.0001821585,0.00126662,0.1023104,0.009578642,0.004958447],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01327649,"threshold_uncertainty_score":0.01604384,"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."}}