{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008404767,0.001624365,0.0008455399,0.001775274,0.0005512912,0.001772732,0.001768808,0.002325118,0.002451534],"category_scores_gemma":[0.04689889,0.000557774,0.001019766,0.00159876,0.001115294,0.007149081,0.001966696,0.003198672,0.00107656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001186071,"about_ca_system_score_gemma":0.001031751,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005253713,"about_ca_topic_score_gemma":0.006200184,"domain_scores_codex":[0.9965737,0.001909358,0.0002829338,0.0006907683,0.0003608161,0.0001824249],"domain_scores_gemma":[0.9306741,0.05887055,0.002075369,0.004335708,0.003231885,0.000812379],"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":[0.009000932,0.005229869,0.1355175,0.001475894,0.001333143,0.0002695524,0.001059958,0.2608632,0.005891424,0.00718528,0.01312259,0.5590507],"study_design_scores_gemma":[0.0001994827,0.0009828545,0.01200315,0.0001310692,0.000327791,0.0001361688,0.0003040344,0.9752451,0.002017198,0.007590353,0.001009568,0.00005324865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.944412,0.001881399,0.04842262,0.0008169377,0.0001935048,0.00009981438,0.001317699,0.0008841263,0.00197195],"genre_scores_gemma":[0.9741794,0.0004349013,0.02041324,0.0001061165,0.00007630925,0.00007144082,0.00319695,0.0001409512,0.00138064],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008404767,"threshold_uncertainty_score":0.04444915,"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."}}