{"id":"W4384039146","doi":"10.1007/s10664-023-10342-7","title":"BTLink : automatic link recovery between issues and commits based on pre-trained BERT model","year":2023,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Commit; Computer science; Traceability; Identifier; Software; Software engineering; Classifier (UML); Data mining; Machine learning; Artificial intelligence; Database; 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":[0.001788121,0.00195404,0.001116795,0.00275898,0.0007584828,0.00154984,0.003417143,0.002260683,0.009170246],"category_scores_gemma":[0.01021198,0.000771308,0.001109051,0.001406567,0.0004560624,0.004315712,0.002162385,0.003478337,0.007935707],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008777447,"about_ca_system_score_gemma":0.00240431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01293358,"about_ca_topic_score_gemma":0.02096078,"domain_scores_codex":[0.9986092,0.0001950522,0.00007984149,0.0004710401,0.0004627641,0.0001820658],"domain_scores_gemma":[0.9948651,0.002026214,0.0004149918,0.001318575,0.00101225,0.000362881],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002146098,0.001441393,0.018982,0.0005372947,0.0003299574,0.0006417838,0.0002143177,0.1291318,0.02208285,0.003925884,0.130386,0.6901808],"study_design_scores_gemma":[0.00004257039,0.00009551092,0.001169265,0.00001753483,0.00002935698,0.00005938297,0.00002996398,0.987586,0.004327265,0.003447672,0.003176482,0.00001913757],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1090268,0.001550431,0.6652384,0.001263402,0.00122098,0.0004609652,0.007782446,0.2078672,0.00558937],"genre_scores_gemma":[0.6647153,0.0004520453,0.277741,0.0007173288,0.0003929984,0.0004215566,0.02840782,0.004312511,0.02283936],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01293358,"threshold_uncertainty_score":0.0306775,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03532628315271463,"score_gpt":0.3095404327340525,"score_spread":0.2742141495813379,"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."}}