{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.001481249,0.0004675984,0.001072719,0.001919387,0.00007154344,0.0001755015,0.003552387,0.0002654509,0.0000469281],"category_scores_gemma":[0.006420252,0.0005358075,0.0001892714,0.003792435,0.00003895858,0.0002816796,0.01319303,0.001771364,0.000001441692],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002841948,"about_ca_system_score_gemma":0.0001785826,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001901103,"about_ca_topic_score_gemma":0.00004278309,"domain_scores_codex":[0.9961899,0.0001177774,0.0007787016,0.001356172,0.0008853067,0.0006721644],"domain_scores_gemma":[0.9927702,0.00405251,0.0001645514,0.002698781,0.00008698328,0.0002269792],"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":[0.000004175589,0.00003851414,0.5387885,0.00032271,0.0004217483,0.0001024282,0.0007860013,0.4583993,0.00001412939,0.00001812622,0.0002434434,0.0008609879],"study_design_scores_gemma":[0.0002259767,0.00002734392,0.3619174,0.0001521511,0.0001134442,0.000004878833,0.00001025064,0.635909,0.00002061838,0.00005139994,0.001089106,0.0004783697],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4371667,0.001503671,0.559519,0.0002000209,0.0003940406,0.0002806127,0.0002857053,0.0006455846,0.000004708373],"genre_scores_gemma":[0.9005946,0.00004473923,0.09835825,0.00003887497,0.00008441571,0.0001002147,0.0006705888,0.00007854923,0.00002975645],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4634279,"threshold_uncertainty_score":0.9997094,"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."}}