{"id":"W4413925951","doi":"10.1109/tse.2025.3605442","title":"Towards Explainable Vulnerability Detection With Large Language Models","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Vulnerability (computing); Data science; Programming language; Software engineering; Natural language processing; Computer security","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":[0.0001956646,0.0001691687,0.0001527379,0.0002214648,0.0001733176,0.0000790078,0.0003043292,0.00007843224,0.000008435583],"category_scores_gemma":[0.00001320338,0.0001633355,0.0000648363,0.0005149167,0.000008237618,0.0005415176,0.000004490337,0.0003137785,0.000005038722],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001639524,"about_ca_system_score_gemma":0.00005991896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006781905,"about_ca_topic_score_gemma":0.00003901618,"domain_scores_codex":[0.9989266,0.00002179012,0.0001689926,0.0003840963,0.0001920103,0.0003065082],"domain_scores_gemma":[0.9992146,0.0000722773,0.00002048423,0.000574078,0.00005629451,0.00006220785],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007946941,0.00005106057,0.00000537201,0.00005439647,0.00002490379,0.000007064364,0.0004995292,0.9539096,0.0004779571,0.0009962911,0.000002987538,0.04396284],"study_design_scores_gemma":[0.0003540664,0.00004221194,0.00004480776,0.00006404697,0.00001177998,0.000007613873,0.00005555065,0.9463788,0.05251491,0.0001760555,0.0001632902,0.0001868351],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02734176,0.00005266233,0.970705,0.00003636537,0.0005595986,0.0001652523,0.000005032075,0.001027937,0.0001063361],"genre_scores_gemma":[0.8712298,0.000003364681,0.1283796,0.00005804859,0.00001674932,0.00008039846,3.706057e-7,0.00001298914,0.000218697],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.843888,"threshold_uncertainty_score":0.666063,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00918862300238798,"score_gpt":0.2233836719503931,"score_spread":0.2141950489480051,"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."}}