{"id":"W4408001831","doi":"10.32604/cmc.2025.057792","title":"Amalgamation of Classical and Large Language Models for Duplicate Bug Detection: A Comparative Study","year":2025,"lang":"en","type":"article","venue":"Computers, materials & continua/Computers, materials & continua (Print)","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Linguistics; Philosophy","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":[0.0186986,0.001524354,0.001458274,0.003745341,0.001113787,0.003693476,0.002536261,0.001554078,0.001831869],"category_scores_gemma":[0.0413302,0.0006344299,0.002360801,0.002459732,0.001077572,0.008155562,0.001973366,0.002245215,0.001041026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002489392,"about_ca_system_score_gemma":0.002313542,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009304912,"about_ca_topic_score_gemma":0.007067529,"domain_scores_codex":[0.9906509,0.005840994,0.0006320685,0.00120703,0.001355851,0.0003132176],"domain_scores_gemma":[0.9081095,0.08055627,0.001538242,0.004032944,0.004843845,0.0009191902],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00838262,0.003405563,0.05493775,0.001812303,0.002265145,0.0005287797,0.002154523,0.149373,0.0045565,0.007680241,0.01156797,0.7533355],"study_design_scores_gemma":[0.0002201693,0.001165582,0.008950223,0.0001068671,0.0008464818,0.0003469958,0.001034103,0.9753523,0.002498608,0.006834972,0.002507432,0.0001362465],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7758138,0.01166218,0.1979677,0.001650024,0.0004282075,0.0003851936,0.001425711,0.005993411,0.004673796],"genre_scores_gemma":[0.915404,0.001835481,0.07774428,0.0002437494,0.0001738293,0.000215872,0.002010459,0.0005660047,0.001806378],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0186986,"threshold_uncertainty_score":0.09888887,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01555918790220971,"score_gpt":0.2876918971537875,"score_spread":0.2721327092515777,"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."}}