{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005973537,0.0001596627,0.0002882905,0.0003958688,0.0002725731,0.0008474871,0.0001944415,0.0001085896,0.000001459561],"category_scores_gemma":[0.001885586,0.0001424112,0.00005293572,0.0004034805,0.00001985232,0.001382107,0.000144769,0.0002339072,3.215942e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001729358,"about_ca_system_score_gemma":0.0001970979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002301544,"about_ca_topic_score_gemma":0.00001080637,"domain_scores_codex":[0.9982926,0.00007858048,0.0007245035,0.0002073659,0.0004851282,0.0002117792],"domain_scores_gemma":[0.9984559,0.0002269969,0.0003316554,0.0002739924,0.000526268,0.0001852107],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001886579,0.00005540888,0.5344535,0.0008131749,0.000588308,0.0003874679,0.01231019,0.2972345,0.0342024,0.0004589219,0.008710082,0.1105974],"study_design_scores_gemma":[0.0036176,0.0007822089,0.1945138,0.002712763,0.0002163638,0.002924039,0.001238113,0.7835993,0.002968185,0.000603565,0.005402343,0.001421766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5149387,0.0009614656,0.4822251,0.00006544199,0.001626743,0.0001307884,0.000006399757,0.00004494437,4.519782e-7],"genre_scores_gemma":[0.9114678,0.00002029415,0.08806023,0.00008590905,0.0003022431,0.00000309834,0.00000696014,0.000009089676,0.00004439086],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4863648,"threshold_uncertainty_score":0.8172338,"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."}}