{"id":"W3022352710","doi":"","title":"Predicting bug report fields using stack traces and categorical attributes.","year":2019,"lang":"en","type":"article","venue":"Conference of the Centre for Advanced Studies on Collaborative Research","topic":"Software Engineering Research","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Categorical variable; Stack (abstract data type); Computer science; Artificial intelligence; Natural language processing; Programming language; Machine learning","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001410544,0.0001732838,0.0003708757,0.0001437418,0.0003573669,0.000111155,0.0008221159,0.00007343436,0.000003906366],"category_scores_gemma":[0.008940339,0.0001227965,0.00005241873,0.001308237,0.0003001883,0.0003108924,0.0008310465,0.0004251334,0.000002543681],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002235884,"about_ca_system_score_gemma":0.0004991518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009696207,"about_ca_topic_score_gemma":0.00003057388,"domain_scores_codex":[0.9974233,0.0002304733,0.0003376251,0.0005709287,0.000868708,0.0005689655],"domain_scores_gemma":[0.9911736,0.004153782,0.0001562008,0.0007132426,0.003701755,0.00010147],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001825767,0.001217465,0.4710026,0.004821877,0.002408476,0.0002931531,0.06393892,0.1068541,0.06107971,0.2339734,0.01028928,0.04229523],"study_design_scores_gemma":[0.01027146,0.005973354,0.03262384,0.003903978,0.00008592948,0.0001063581,0.05573412,0.3956456,0.428587,0.04293468,0.02158413,0.002549601],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9772826,0.001437708,0.01435815,0.004062006,0.0007356189,0.001875374,0.0000417397,0.00006727195,0.0001395203],"genre_scores_gemma":[0.9945853,0.0002037177,0.004022957,0.000008727369,0.00003730492,0.00005035452,0.000001365946,0.00001268798,0.001077559],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4383788,"threshold_uncertainty_score":0.9994078,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1232029168967586,"score_gpt":0.4018137944970319,"score_spread":0.2786108776002734,"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."}}