{"id":"W4402034738","doi":"10.32920/26871409","title":"Transformer Models for Automated Bug Triaging and Duplicate Bug Detection","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Software Testing and Debugging Techniques","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; Transformer; Engineering","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":[0.0005802638,0.0003027749,0.0003211878,0.0002934473,0.0001270691,0.00055649,0.0005420287,0.0002683601,0.000001056243],"category_scores_gemma":[0.00006197382,0.000264605,0.0001470717,0.0002168509,0.00003305801,0.00016279,0.0004929311,0.0004075641,0.000005623419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006544673,"about_ca_system_score_gemma":0.00009526544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002654327,"about_ca_topic_score_gemma":0.00001020497,"domain_scores_codex":[0.9982459,0.00002919793,0.0003456992,0.0008981117,0.0001740361,0.0003070332],"domain_scores_gemma":[0.9988405,0.0002727786,0.00008552811,0.0006055495,0.0001082925,0.00008732675],"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":[0.00005998958,0.0001162803,0.00004214444,0.002939407,0.0002911709,0.00002225474,0.002681626,0.007860924,0.002196902,0.02261503,0.03281179,0.9283625],"study_design_scores_gemma":[0.00009951598,0.00003245179,0.000009217139,0.0001463857,0.0000235622,0.00001882659,8.876783e-7,0.5980825,0.002974558,0.3982713,0.0001377116,0.0002030902],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002354269,0.0004192009,0.9163578,0.0008441983,0.0005159105,0.0007487796,0.0000101048,0.07785709,0.0008926971],"genre_scores_gemma":[0.6713043,0.00004150199,0.3277138,0.0001485505,0.00007117712,0.0004536954,0.000006484434,0.00003648177,0.0002239729],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9281594,"threshold_uncertainty_score":0.9999806,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04005328244476049,"score_gpt":0.3005505525739943,"score_spread":0.2604972701292338,"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."}}