{"id":"W4414608058","doi":"10.1016/j.jss.2025.112636","title":"BugMentor: Generating answers to follow-up questions from software bug reports using structured information retrieval and neural text generation","year":2025,"lang":"en","type":"article","venue":"Journal of Systems and Software","topic":"Software Engineering Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Question answering; Context (archaeology); Similarity (geometry); Software; Semantics (computer science); Language model; Software bug; Face (sociological concept)","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":[0.001981899,0.002191655,0.000838169,0.002378762,0.0004205859,0.0009301375,0.001833485,0.001918187,0.006878919],"category_scores_gemma":[0.01309021,0.0004045445,0.0011534,0.0009005217,0.0005057857,0.001780511,0.001286456,0.001291618,0.002860746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000764516,"about_ca_system_score_gemma":0.001094531,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002648204,"about_ca_topic_score_gemma":0.00397313,"domain_scores_codex":[0.99779,0.0008409531,0.0001639079,0.0005261665,0.0005845318,0.00009444118],"domain_scores_gemma":[0.9940382,0.003628435,0.0005510179,0.0007155647,0.0009192915,0.0001474628],"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":[0.0004660137,0.0007741276,0.003441891,0.001545733,0.000141203,0.0006792297,0.001141235,0.0223231,0.03884212,0.003819489,0.04082285,0.8860031],"study_design_scores_gemma":[0.0005908372,0.001300533,0.004818237,0.0002272345,0.000220499,0.00117285,0.0006770553,0.849291,0.08242691,0.01486615,0.04421441,0.0001942067],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09361492,0.001993576,0.7895849,0.001434742,0.0004641083,0.001687572,0.004246856,0.09990604,0.00706717],"genre_scores_gemma":[0.288565,0.0005207176,0.688886,0.0006420761,0.0001475158,0.0009589596,0.01000984,0.00151846,0.008751542],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006878919,"threshold_uncertainty_score":0.02301228,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0174313937346621,"score_gpt":0.2649110413383188,"score_spread":0.2474796476036567,"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."}}