{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002008996,0.001062757,0.002435229,0.0008132199,0.0004544905,0.001371779,0.00200397,0.0004113071,0.00004178853],"category_scores_gemma":[0.0001222806,0.00109496,0.0002676309,0.0007041714,0.0002826267,0.001642714,0.002321361,0.0002807798,0.00002658617],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002172445,"about_ca_system_score_gemma":0.0001224708,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001535034,"about_ca_topic_score_gemma":0.00007067314,"domain_scores_codex":[0.992977,0.0008778512,0.002427124,0.002045847,0.0005592909,0.001112835],"domain_scores_gemma":[0.9948727,0.0007734853,0.001460478,0.001813418,0.0008494682,0.0002304298],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001023455,0.001099851,0.00009581833,0.0007592867,0.0006153016,0.00004780493,0.006795489,0.0001249254,0.9295844,0.02663741,0.003005574,0.03021068],"study_design_scores_gemma":[0.005878803,0.001260723,0.003166636,0.000675243,0.0001841391,0.000057079,0.0005731729,0.01571382,0.9586888,0.007828005,0.004608517,0.001365054],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4288867,0.0001057903,0.5638012,0.0002169891,0.002810679,0.003000167,0.0001332732,0.0009658704,0.00007924345],"genre_scores_gemma":[0.9237801,0.00002771668,0.07421014,0.0003427582,0.0004639213,0.0008032363,0.00005933006,0.00007553388,0.0002372318],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4948934,"threshold_uncertainty_score":0.9996649,"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."}}