{"id":"W4391444574","doi":"10.1145/3641543","title":"Beyond Fidelity: Explaining Vulnerability Localization of Learning-Based Detectors","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Fidelity; Vulnerability (computing); Detector; Computer security; Telecommunications","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":[0.001392252,0.0001663165,0.0002571427,0.0003211662,0.0001352457,0.00003953488,0.0002824423,0.0001428998,0.00001859361],"category_scores_gemma":[0.002978635,0.0001686905,0.00008223204,0.0005099438,0.0000542918,0.0001895516,0.00002111834,0.0005862278,0.000001980535],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004418781,"about_ca_system_score_gemma":0.00005769949,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002834359,"about_ca_topic_score_gemma":0.000002676348,"domain_scores_codex":[0.9985184,0.0004380636,0.0002717494,0.0004168696,0.0001453277,0.0002095887],"domain_scores_gemma":[0.9945953,0.004845299,0.00004411206,0.0003921128,0.00005443988,0.00006865957],"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":[0.000009156186,0.00001024133,0.0001782346,0.0001226415,0.00002719132,0.00000462126,0.0005268434,0.8857512,0.000317385,0.0008904562,0.000001276942,0.1121608],"study_design_scores_gemma":[0.0001766605,0.0001631013,0.0001952921,0.00007770793,0.00002992088,0.00001578882,0.00003834206,0.9920622,0.005093803,0.001076473,0.000896433,0.0001742868],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007770755,0.0002549925,0.9901531,0.000106289,0.0008634648,0.00007764719,0.00000230349,0.0007666308,0.000004778278],"genre_scores_gemma":[0.5044384,0.000009033744,0.495467,0.00002403657,0.00002021374,0.00001233472,0.000001758012,0.00001439261,0.00001279392],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4966677,"threshold_uncertainty_score":0.6878999,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04447907595058553,"score_gpt":0.3148810260823837,"score_spread":0.2704019501317981,"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."}}