{"id":"W4391395450","doi":"10.1007/s10515-024-00413-4","title":"An extensive study of the effects of different deep learning models on code vulnerability detection in Python code","year":2024,"lang":"en","type":"article","venue":"Automated Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"National Natural Science Foundation of China","keywords":"Python (programming language); Computer science; Artificial intelligence; Deep learning; Word2vec; Machine learning; Programming language","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":[0.000450316,0.0002547677,0.0003412823,0.0004169692,0.00005842573,0.00006891423,0.0006857436,0.0001111245,8.13502e-7],"category_scores_gemma":[0.002248846,0.0002053393,0.0000807691,0.001143199,0.00002387144,0.0003367956,0.0002101325,0.000675059,0.000001482441],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000223475,"about_ca_system_score_gemma":0.00003127517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006656985,"about_ca_topic_score_gemma":0.00003829404,"domain_scores_codex":[0.9979293,0.0002230571,0.0003937063,0.0005261569,0.0005679441,0.0003597741],"domain_scores_gemma":[0.9963239,0.002643438,0.00005806463,0.0007837847,0.0001125757,0.00007821021],"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":[0.000007942675,0.0002402227,0.006195624,0.0005787951,0.00004519511,0.00003216541,0.003534738,0.9656741,0.01527392,0.00008470607,0.000001310894,0.008331285],"study_design_scores_gemma":[0.0002763803,0.0005165556,0.1524032,0.0003914277,0.000009472496,0.000005036591,0.00003975951,0.8150243,0.03113388,0.00004848566,0.000001263361,0.000150238],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.672664,0.0001287422,0.3240623,0.000003798075,0.000529993,0.0004237349,0.000001264566,0.002185601,5.070535e-7],"genre_scores_gemma":[0.9984002,0.00000666423,0.001424359,0.000002756536,0.00001920784,0.00009084219,0.0000011424,0.00005125238,0.000003605282],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3257362,"threshold_uncertainty_score":0.8373491,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01233075700953269,"score_gpt":0.2627646923285514,"score_spread":0.2504339353190187,"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."}}