{"id":"W3206481103","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":"article","venue":"Florence Research (University of Florence)","topic":"Software Engineering Research","field":"Computer Science","cited_by":43,"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":"Technische Universität Clausthal","keywords":"Context (archaeology); Computer science; Software bug; Code (set theory); Source lines of code; Set (abstract data type); Software; Data science; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004083798,0.0001147417,0.0003844291,0.002488877,0.0003521666,0.00004392305,0.004308062,0.0000482729,0.0001911194],"category_scores_gemma":[0.00110248,0.0001454318,0.00006458467,0.008514912,0.0003912214,0.0006462421,0.006699719,0.0006867449,0.000002717317],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000145136,"about_ca_system_score_gemma":0.0003185288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001927814,"about_ca_topic_score_gemma":0.000714957,"domain_scores_codex":[0.9966689,0.0004386608,0.0002085395,0.0006642664,0.001470925,0.0005487577],"domain_scores_gemma":[0.9962033,0.001860436,0.00008525887,0.001409415,0.00028193,0.000159639],"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":[0.0001749643,0.0003730434,0.8746992,0.000345016,0.0007614941,0.0007642362,0.03120204,0.02903709,0.002853643,0.00444366,0.003787498,0.05155806],"study_design_scores_gemma":[0.0004997178,0.0002005051,0.2859319,0.000056765,0.00002967519,0.000004309184,0.002714665,0.709505,0.00007631092,0.0003219845,0.0004726016,0.000186631],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9452717,0.0003293414,0.05284864,0.0007210993,0.00007401298,0.0002574774,0.0002658531,0.00006268756,0.0001691946],"genre_scores_gemma":[0.9899939,0.00006109555,0.009751713,0.000003080176,0.000009227976,0.00000161715,0.00009077191,0.000005725592,0.00008283462],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6804679,"threshold_uncertainty_score":0.835072,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1084575965323194,"score_gpt":0.3262338500443421,"score_spread":0.2177762535120227,"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."}}