{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003432452,0.002367212,0.0009023211,0.003408823,0.0006431183,0.001913844,0.002393419,0.002251833,0.002846769],"category_scores_gemma":[0.02201013,0.001011111,0.002411567,0.001571782,0.00113794,0.004958555,0.003794128,0.004341248,0.00210289],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001332875,"about_ca_system_score_gemma":0.002074828,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005054876,"about_ca_topic_score_gemma":0.01198817,"domain_scores_codex":[0.9965968,0.001658615,0.0001730594,0.0009257084,0.0004826781,0.0001630727],"domain_scores_gemma":[0.9851916,0.01130328,0.0008434893,0.001465416,0.0009759546,0.0002202991],"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":[0.000505737,0.0003813963,0.01650007,0.001246727,0.0004258327,0.001094018,0.0024577,0.1811848,0.02319397,0.01807875,0.03401882,0.7209122],"study_design_scores_gemma":[0.00003708712,0.0000553896,0.0009645793,0.00006226759,0.00006662579,0.0001610051,0.0002122098,0.9524358,0.005537703,0.03369621,0.006734546,0.00003664578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02974586,0.0008062677,0.9376738,0.001361872,0.00007519819,0.0001711907,0.001895925,0.02732383,0.0009460807],"genre_scores_gemma":[0.2944218,0.000492443,0.6912916,0.0009010073,0.0001285554,0.0004012322,0.008626661,0.001407039,0.002329692],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005054876,"threshold_uncertainty_score":0.01815277,"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."}}