{"id":"W131327581","doi":"","title":"Security benchmarking using partial verification","year":2008,"lang":"en","type":"article","venue":"USENIX Security Symposium","topic":"Security and Verification in Computing","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Benchmarking; Computer science; Computer security; Order (exchange); Threat model; Partial order reduction; Model checking; Theoretical computer science; Business","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":[0.009396859,0.0009441116,0.001152124,0.002271828,0.001261101,0.003059167,0.00212271,0.001401795,0.007287145],"category_scores_gemma":[0.05951023,0.0006505561,0.001114433,0.002061999,0.002185771,0.00566248,0.003474077,0.001688866,0.0009793306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00187014,"about_ca_system_score_gemma":0.003536367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003177424,"about_ca_topic_score_gemma":0.004379479,"domain_scores_codex":[0.9843121,0.007371783,0.0009092877,0.001249151,0.005086513,0.00107111],"domain_scores_gemma":[0.942789,0.02652598,0.002221685,0.01998212,0.00766926,0.0008119713],"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":[0.00088473,0.0002907918,0.01922151,0.000765077,0.0002847598,0.0002854884,0.0005057721,0.6538424,0.01023676,0.1455478,0.006795689,0.1613392],"study_design_scores_gemma":[0.00004475591,0.0002646939,0.001559094,0.00006212114,0.00004316046,0.00009481463,0.00009402707,0.9314069,0.008287731,0.05496858,0.003142099,0.00003207609],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4296603,0.00126159,0.5190265,0.00152172,0.0002694712,0.0003248718,0.001743585,0.01145534,0.03473666],"genre_scores_gemma":[0.926348,0.0001220085,0.07100588,0.00007692256,0.0000189927,0.0001306031,0.0009336507,0.0003440576,0.001019892],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009396859,"threshold_uncertainty_score":0.04969597,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0338729842272198,"score_gpt":0.2591525270121877,"score_spread":0.2252795427849679,"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."}}