{"id":"W4416961717","doi":"10.1109/pst65910.2025.11268879","title":"Houdini: Benchmarking Container Security Confinement","year":2025,"lang":"","type":"article","venue":"","topic":"Security and Verification in Computing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Container (type theory); Benchmarking; Benchmark (surveying); Suite; Cloud computing","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":[0.003867578,0.001558205,0.0005885342,0.00140851,0.0007189165,0.001492505,0.003123542,0.0009582142,0.002608188],"category_scores_gemma":[0.01074576,0.0006874478,0.0008202431,0.001420981,0.002105081,0.002873016,0.002174105,0.002108203,0.001283959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001950427,"about_ca_system_score_gemma":0.001666225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008829672,"about_ca_topic_score_gemma":0.006837211,"domain_scores_codex":[0.9951671,0.001147547,0.0004371975,0.0005933933,0.001844612,0.0008101602],"domain_scores_gemma":[0.9916367,0.002445969,0.0006702908,0.002644988,0.001955188,0.0006468015],"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":[0.005240184,0.004047274,0.06419896,0.003073558,0.0008331687,0.001808207,0.001923976,0.404666,0.1191309,0.03173214,0.1621778,0.2011678],"study_design_scores_gemma":[0.0003577974,0.002195634,0.0194499,0.0001450093,0.00008411372,0.0004129315,0.0005629461,0.8070476,0.1283888,0.004956351,0.03621851,0.0001803904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8137208,0.001388172,0.07028535,0.0007717863,0.0007201493,0.0008949753,0.005290751,0.07938153,0.02754652],"genre_scores_gemma":[0.904885,0.0005075097,0.06962863,0.0004420056,0.00003580007,0.0003575992,0.0139182,0.004787849,0.005437424],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008829672,"threshold_uncertainty_score":0.02045399,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01461938887470646,"score_gpt":0.2802329559385558,"score_spread":0.2656135670638494,"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."}}