{"id":"W4402034432","doi":"10.32920/26871409.v1","title":"Transformer Models for Automated Bug Triaging and Duplicate Bug Detection","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; University of Manitoba; Systems, Applications & Products in Data Processing (Canada)","funders":"","keywords":"Computer science; Workflow; Software; Mean reciprocal rank; Software bug; Rank (graph theory); Data mining; 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":[0.004264507,0.001264277,0.001402289,0.002563155,0.0005439765,0.002155841,0.002232419,0.001429717,0.002429276],"category_scores_gemma":[0.01615834,0.0005763488,0.001691062,0.002242619,0.001110913,0.003400881,0.001941405,0.002500379,0.001713807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001688035,"about_ca_system_score_gemma":0.001949688,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009209722,"about_ca_topic_score_gemma":0.009038489,"domain_scores_codex":[0.998235,0.000629153,0.00013253,0.0004993685,0.0003584028,0.0001455157],"domain_scores_gemma":[0.992918,0.003624888,0.0007461086,0.001039399,0.001433039,0.0002385832],"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":[0.0005253269,0.0003856182,0.006884149,0.0002541173,0.0002149283,0.0001738085,0.0002807969,0.6131445,0.003910812,0.0272854,0.0132328,0.3337079],"study_design_scores_gemma":[0.00001104077,0.00004227027,0.0002352225,0.000004944495,0.00001279176,0.00002628318,0.00001263869,0.9883024,0.0004800662,0.01043517,0.0004288065,0.000008312088],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05412723,0.001318969,0.9363739,0.0008227561,0.0001229391,0.0001399868,0.0006003595,0.004216938,0.00227688],"genre_scores_gemma":[0.7901255,0.00109551,0.1978156,0.0005492825,0.0001993317,0.0002502584,0.002857981,0.0004011233,0.006705522],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009209722,"threshold_uncertainty_score":0.02255315,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03379990107120691,"score_gpt":0.3007839726597976,"score_spread":0.2669840715885907,"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."}}