{"id":"W4390640589","doi":"10.1016/j.jss.2024.111961","title":"An empirical assessment of different word embedding and deep learning models for bug assignment","year":2024,"lang":"en","type":"article","venue":"Journal of Systems and Software","topic":"Software Engineering Research","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Artificial intelligence; Deep learning; Word embedding; Word2vec; Benchmark (surveying); Natural language processing; Machine learning; Word (group theory); Embedding","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":[],"consensus_categories":[],"category_scores_codex":[0.0008517615,0.0001168652,0.0003136964,0.0002066102,0.00007265726,0.0003633401,0.000225937,0.00006037065,9.65187e-7],"category_scores_gemma":[0.0001232417,0.00008426914,0.00006645967,0.0001135128,0.00002050169,0.0004584457,0.00008795022,0.0002689828,7.932386e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009319248,"about_ca_system_score_gemma":0.00006789379,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004522264,"about_ca_topic_score_gemma":3.859782e-7,"domain_scores_codex":[0.9986914,0.00007603812,0.0003969868,0.0001945906,0.0004492922,0.0001916536],"domain_scores_gemma":[0.9985032,0.0009184435,0.0001175362,0.0001372625,0.0001493451,0.000174233],"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":[0.00004854676,0.0003064764,0.2425009,0.005284871,0.0006394167,0.0002593423,0.009391502,0.4749905,0.001908618,0.007386759,0.0005215258,0.2567615],"study_design_scores_gemma":[0.0002529415,0.0005325389,0.01443776,0.000645058,0.00001597454,0.0001441951,0.0002000191,0.9828226,0.00002515902,0.0005205805,0.000299018,0.0001041516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2379809,0.003610722,0.7578723,0.00005122604,0.0003307757,0.000109309,0.000001355344,0.00004176516,0.000001718197],"genre_scores_gemma":[0.9620925,0.0001367237,0.03758943,0.000004097466,0.0001234811,0.00001038064,4.654418e-7,0.00001384463,0.00002912242],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7241116,"threshold_uncertainty_score":0.3503697,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04004862236986989,"score_gpt":0.3478501262090294,"score_spread":0.3078015038391595,"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."}}