{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006940857,0.000378583,0.000434845,0.0005576296,0.0001350692,0.000239845,0.0008902221,0.0002244511,0.00001063587],"category_scores_gemma":[0.004029626,0.0003775264,0.0001178695,0.001422945,0.00003443267,0.000347384,0.0004344474,0.0005986484,0.0001108314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001477494,"about_ca_system_score_gemma":0.00009431694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000104321,"about_ca_topic_score_gemma":4.985867e-7,"domain_scores_codex":[0.9973046,0.00005226497,0.000390774,0.0006855703,0.0007603163,0.0008064425],"domain_scores_gemma":[0.9941942,0.004470777,0.00004326601,0.0008368078,0.00007072308,0.0003842042],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005973866,0.00003354053,0.07411813,0.0002893913,0.0000529148,0.00005803616,0.0004299364,0.8894247,0.0000476826,0.00005483059,0.0046731,0.03081177],"study_design_scores_gemma":[0.0002746191,0.000122679,0.2042272,0.0001459496,0.0000066815,0.000002478215,9.992957e-7,0.793617,0.0001404231,0.0002317938,0.0008876477,0.0003425053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2118092,0.0000966363,0.7795288,0.002548229,0.0002309906,0.0002747081,0.00001406236,0.005485618,0.00001177088],"genre_scores_gemma":[0.8188981,0.00001868507,0.1797994,0.0002963569,0.0003423572,0.0001132418,0.00003567402,0.0001190601,0.0003771494],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6070889,"threshold_uncertainty_score":0.9998677,"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."}}