{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001279782,0.0003951868,0.0004444294,0.0003102987,0.0007854323,0.0009237587,0.001632074,0.0002257279,0.001639201],"category_scores_gemma":[0.0001275088,0.0004216984,0.0002191351,0.001408709,0.0001916309,0.0003593633,0.001148074,0.0005010813,0.0001388512],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001917182,"about_ca_system_score_gemma":0.0005623879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002994059,"about_ca_topic_score_gemma":0.0000462061,"domain_scores_codex":[0.9964031,0.0002497708,0.0009919341,0.001150704,0.000481993,0.000722496],"domain_scores_gemma":[0.997394,0.000476458,0.0002768255,0.001243545,0.0004343094,0.0001749037],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001210531,0.0002128847,0.001160236,0.0001047832,0.0001093426,0.000008359089,0.001805637,0.00009062185,0.0000608412,0.8903789,0.02104358,0.08501272],"study_design_scores_gemma":[0.001013864,0.0001150744,0.002583565,0.0003352707,0.00004491373,0.000006746141,0.0003673266,0.7217578,0.00220523,0.01744985,0.2535826,0.0005377153],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004193093,0.000970803,0.7240697,0.008408286,0.005919262,0.0004720548,0.000003668829,0.0002382004,0.255725],"genre_scores_gemma":[0.9822018,0.0001551488,0.008362824,0.005789194,0.0004030605,0.00002223002,0.000005581117,0.000008755185,0.00305137],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9780087,"threshold_uncertainty_score":0.9998235,"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."}}