{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01262401,0.00085677,0.0005776352,0.002203456,0.0005791784,0.001847676,0.001577783,0.001718705,0.003032234],"category_scores_gemma":[0.1498428,0.0002856331,0.0006630123,0.002915283,0.0007572208,0.005758723,0.0009314216,0.00239114,0.001188205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001176987,"about_ca_system_score_gemma":0.0006639501,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004045564,"about_ca_topic_score_gemma":0.002954257,"domain_scores_codex":[0.992922,0.004948644,0.0004305383,0.0006784968,0.000851566,0.0001688394],"domain_scores_gemma":[0.5946221,0.3833432,0.008109855,0.006657025,0.006420522,0.0008474345],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004864189,0.008742703,0.5272272,0.001090613,0.0009737028,0.0008973948,0.003268998,0.1155963,0.004655746,0.008639983,0.01394105,0.3101022],"study_design_scores_gemma":[0.0001544081,0.001056063,0.08454651,0.0001520812,0.000296821,0.0005363505,0.0009737974,0.8977681,0.002622737,0.009314727,0.002503626,0.00007475087],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9798582,0.0007246525,0.01513878,0.000889964,0.00007812973,0.00009651083,0.0008810761,0.0001749124,0.00215778],"genre_scores_gemma":[0.992294,0.0001983368,0.005103146,0.0001386935,0.00008455763,0.00006075972,0.001279091,0.00005104277,0.0007904144],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01262401,"threshold_uncertainty_score":0.06676292,"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."}}