{"id":"W3130519220","doi":"10.1109/trustcom50675.2020.00067","title":"Evaluating the Soundness of Security Metrics from Vulnerability Scoring Frameworks","year":2020,"lang":"en","type":"article","venue":"","topic":"Software Reliability and Analysis Research","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Soundness; Computer science; Software security assurance; Vulnerability (computing); Secure coding; Context (archaeology); Vulnerability assessment; Computer security; Vulnerability management; Software; Security information and event management; Information security; Risk analysis (engineering); Security service; Cloud computing security; Business","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002228481,0.0001018191,0.0002436878,0.00004852864,0.0001796598,0.0001836879,0.00156672,0.0001200747,0.0001331957],"category_scores_gemma":[0.007077342,0.00006596508,0.0001562741,0.002121414,0.0001157954,0.0002734904,0.0007812519,0.0007514451,0.00002068254],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003475013,"about_ca_system_score_gemma":0.000117921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005862297,"about_ca_topic_score_gemma":0.00001350839,"domain_scores_codex":[0.9975107,0.0004904002,0.0003552792,0.0004813909,0.0009356845,0.0002265912],"domain_scores_gemma":[0.995028,0.003531193,0.00009748284,0.0008909615,0.0003275351,0.0001248492],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008510341,0.0006596968,0.2615072,0.0003258651,0.0004460372,0.000008621971,0.03003822,0.02277126,0.003874553,0.04894098,0.000429805,0.6309127],"study_design_scores_gemma":[0.0001193638,0.00009124436,0.002884265,0.00001124418,0.00001373885,1.887045e-7,0.0002482776,0.9399284,0.003411911,0.0531311,0.00006064116,0.00009965251],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.425389,0.0001598934,0.5710055,0.003031871,0.00005784696,0.00009664866,0.000002058682,0.0000747097,0.0001824099],"genre_scores_gemma":[0.9647722,0.00001175199,0.03465842,0.000457606,0.00008190057,0.000007823875,0.000001202033,0.000003790675,0.000005317498],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9171571,"threshold_uncertainty_score":0.8472751,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1286683248139874,"score_gpt":0.3999609885309979,"score_spread":0.2712926637170105,"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."}}