{"id":"W2099940443","doi":"10.1109/cisda.2009.5356528","title":"A detailed analysis of the KDD CUP 99 data set","year":2009,"lang":"en","type":"article","venue":"","topic":"Network Security and Intrusion Detection","field":"Computer Science","cited_by":4782,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; University of New Brunswick","funders":"","keywords":"Computer science; Data mining; Anomaly detection; Set (abstract data type); Data set; Signature (topology); Anomaly (physics); Knowledge extraction; Artificial intelligence; Mathematics","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":[0.002040506,0.0007837804,0.0009710014,0.007708716,0.001643196,0.002135677,0.001000074,0.000695203,0.002273865],"category_scores_gemma":[0.006602654,0.0001793965,0.0008519328,0.008623339,0.0004397916,0.001334203,0.0007479417,0.0007920258,0.002023547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001405325,"about_ca_system_score_gemma":0.002169768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01739994,"about_ca_topic_score_gemma":0.01994447,"domain_scores_codex":[0.9954991,0.000329385,0.0004371259,0.0003298997,0.003122622,0.0002818726],"domain_scores_gemma":[0.9945663,0.001124018,0.0002436997,0.0007543014,0.003103582,0.0002080711],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.000816441,0.001771719,0.07482187,0.001888488,0.0004146214,0.00126599,0.0007468329,0.02693634,0.007189075,0.01178811,0.4614237,0.4109368],"study_design_scores_gemma":[0.0001046044,0.000453284,0.3172847,0.0002837975,0.0001573832,0.002199728,0.002274158,0.1508334,0.02633228,0.008140933,0.4916162,0.0003195456],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.4455943,0.003768847,0.04403275,0.004840733,0.001933032,0.001720582,0.4487604,0.0075029,0.04184647],"genre_scores_gemma":[0.4458537,0.001911407,0.07758681,0.0004615679,0.0002240952,0.0009644905,0.4612133,0.0003165087,0.01146808],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01739994,"threshold_uncertainty_score":0.03459734,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03366468587413417,"score_gpt":0.271417510805663,"score_spread":0.2377528249315288,"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."}}