{"id":"W3044427914","doi":"","title":"{UBCIS}: Ultimate Benchmark for Container Image Scanning","year":2020,"lang":"en","type":"article","venue":"USENIX Security Symposium","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Container (type theory); Benchmark (surveying); Computer science; Image (mathematics); Computer vision; Artificial intelligence; Materials science; Geology; Composite material","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":[0.000175769,0.0001824819,0.0003328445,0.00004158487,0.0001201724,0.00004481737,0.0001602513,0.00009852138,0.0001976269],"category_scores_gemma":[0.0002057664,0.0001609669,0.0001655242,0.0001773365,0.000108933,0.00009835397,0.00007752032,0.0002542007,0.00005245253],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004109149,"about_ca_system_score_gemma":0.00006784354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000045227,"about_ca_topic_score_gemma":0.000001416639,"domain_scores_codex":[0.9987093,0.00001913989,0.0003129996,0.000386704,0.000233638,0.0003381683],"domain_scores_gemma":[0.9989095,0.00009619108,0.00008433792,0.0003067529,0.0001645743,0.0004386555],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003041912,0.0002998962,0.001963771,0.000736522,0.0001027264,0.0000769219,0.003682393,0.000001959254,0.5469125,0.008949707,0.4362749,0.0006945584],"study_design_scores_gemma":[0.003890614,0.0006615311,0.000390618,0.000205003,0.0003764958,0.0001167802,0.0003233584,0.08452193,0.1152286,0.002249557,0.7914215,0.0006140834],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.3487733,0.0001740306,0.07263449,0.5438638,0.0003279314,0.006160904,0.0003505536,0.002319301,0.02539561],"genre_scores_gemma":[0.9317542,0.0000392246,0.056123,0.01045614,0.0006431169,0.000300097,0.0002440477,0.00005316049,0.0003869666],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5829809,"threshold_uncertainty_score":0.6564038,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02076700369625764,"score_gpt":0.3083486786194348,"score_spread":0.2875816749231772,"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."}}