{"id":"W4319083508","doi":"10.1007/s10664-022-10276-6","title":"An empirical study of text-based machine learning models for vulnerability detection","year":2023,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Machine learning; Vulnerability (computing); Artificial intelligence; Context (archaeology); Empirical research; Source code; Function (biology); Construct (python library); Vulnerability assessment; Code (set theory); Data science; Computer security; Geography; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00129162,0.0003036643,0.0004158155,0.000537522,0.0001809682,0.0001012982,0.0008941409,0.0001576663,0.000005687228],"category_scores_gemma":[0.00420384,0.0003041868,0.0001473776,0.002067688,0.00002510804,0.0004761868,0.0002249824,0.0005876442,0.00001108438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001731821,"about_ca_system_score_gemma":0.00007742558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004945001,"about_ca_topic_score_gemma":0.00001132559,"domain_scores_codex":[0.9972143,0.0001432774,0.0004893462,0.0007793269,0.0007030893,0.0006707148],"domain_scores_gemma":[0.9950135,0.003606619,0.00006793022,0.0008190075,0.0002099592,0.0002829948],"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":[0.00002075827,0.0002656214,0.1554455,0.00009332769,0.00002328499,0.000008296414,0.0005768446,0.8385668,0.0004713528,0.000004666596,0.00003429801,0.00448927],"study_design_scores_gemma":[0.0007227359,0.0009546129,0.1108609,0.00001621371,0.000008365895,0.000002391889,0.00002215691,0.8852826,0.001495857,0.00009546398,0.0002564969,0.0002822244],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4642812,0.00002000263,0.5332149,0.00004359286,0.0001643452,0.0003628151,0.000003994228,0.00190859,5.398801e-7],"genre_scores_gemma":[0.9705984,9.66892e-7,0.02893595,0.00001955082,0.00008921457,0.0002584329,0.00001501721,0.00006674042,0.00001572673],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5063172,"threshold_uncertainty_score":0.9999411,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05958481781282825,"score_gpt":0.3385498813244283,"score_spread":0.2789650635116001,"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."}}