{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001552227,0.0009021647,0.0005345527,0.0007822523,0.000447343,0.0005041836,0.0007946445,0.000777821,0.0008027079],"category_scores_gemma":[0.01580907,0.0002540471,0.0005652813,0.000715752,0.0006535305,0.001632803,0.0007865229,0.001403622,0.0002106521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000847949,"about_ca_system_score_gemma":0.00115196,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0103053,"about_ca_topic_score_gemma":0.01250421,"domain_scores_codex":[0.9988477,0.0003154883,0.00006801059,0.0002630634,0.0003261073,0.0001795201],"domain_scores_gemma":[0.984554,0.0112304,0.0009483765,0.001451157,0.001508322,0.0003078261],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002216878,0.001520043,0.065497,0.0009281121,0.0004949615,0.0005280684,0.0004509055,0.5590948,0.03589426,0.00278461,0.0116739,0.3189164],"study_design_scores_gemma":[0.00002679885,0.0003524541,0.01047586,0.00004058955,0.0000845883,0.00009264514,0.0001021944,0.9688262,0.01738152,0.001757024,0.0008364712,0.00002359793],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9795869,0.0009224293,0.01638645,0.000299787,0.00006391457,0.00002514957,0.0003650038,0.001100591,0.001249697],"genre_scores_gemma":[0.988005,0.0002412908,0.01007155,0.00008373069,0.00001744812,0.00001481498,0.00064944,0.00009165767,0.0008250257],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0103053,"threshold_uncertainty_score":0.02049059,"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."}}