{"id":"W3206397610","doi":"10.1007/s10664-021-10083-5","title":"A fine-grained data set and analysis of tangling in bug fixing commits","year":2022,"lang":"en","type":"preprint","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Trent University; University of Saskatchewan; University of British Columbia, Okanagan Campus; Kelowna General Hospital; University of British Columbia; University of Ottawa","funders":"Horizon 2020 Framework Programme; Technische Universität Clausthal; Deutsche Forschungsgemeinschaft","keywords":"Context (archaeology); Computer science; Software bug; Set (abstract data type); Code (set theory); Software; Source lines of code; Data mining; Programming language; Biology","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":[0.01804132,0.0004666252,0.0006545017,0.01178225,0.00111258,0.001573871,0.0009788362,0.001488984,0.001429146],"category_scores_gemma":[0.1332253,0.0003810367,0.0004849198,0.008459627,0.001358744,0.00192759,0.002455498,0.001298032,0.0007967242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001087916,"about_ca_system_score_gemma":0.001080382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006461294,"about_ca_topic_score_gemma":0.007807063,"domain_scores_codex":[0.979675,0.0075764,0.002795614,0.004085901,0.005221998,0.0006451155],"domain_scores_gemma":[0.6868892,0.1961561,0.0455457,0.03565111,0.03193932,0.003818525],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00048056,0.0004144321,0.9098739,0.000916429,0.0002586482,0.0007150537,0.007142597,0.006412904,0.003979556,0.001798537,0.01152095,0.05648641],"study_design_scores_gemma":[0.00003952751,0.0002128293,0.9642885,0.0002780645,0.000067518,0.0004629639,0.00234949,0.0158444,0.002502996,0.002293041,0.01157617,0.00008461453],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9700894,0.0005256187,0.01107327,0.0003616708,0.00004833124,0.0002364,0.01546146,0.0003703817,0.001833417],"genre_scores_gemma":[0.9615985,0.00009102571,0.01365597,0.00009147257,0.00003788872,0.0003743364,0.02352239,0.000114258,0.0005141945],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01804132,"threshold_uncertainty_score":0.09541273,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07673165410839632,"score_gpt":0.3435880299778528,"score_spread":0.2668563758694564,"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."}}