{"id":"W2918863576","doi":"","title":"Feature engineering in big data for detection of information systems misuse.","year":2018,"lang":"en","type":"article","venue":"Conference of the Centre for Advanced Studies on Collaborative Research","topic":"Network Security and Intrusion Detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"","keywords":"Big data; Computer science; Feature (linguistics); Feature engineering; Information engineering; Data mining; Data science; Information system; Artificial intelligence; Engineering; Deep learning","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":[0.001063374,0.0001009771,0.0002263982,0.0002087247,0.0002243489,0.00005449269,0.0008653192,0.00006097587,2.242065e-7],"category_scores_gemma":[0.002655181,0.00007416437,0.00002862983,0.001425096,0.0001601315,0.0006015393,0.0004239433,0.000161199,9.134505e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001204563,"about_ca_system_score_gemma":0.0001582296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005956109,"about_ca_topic_score_gemma":0.0002714019,"domain_scores_codex":[0.998771,0.0001328688,0.0002642635,0.0002311682,0.0003484956,0.0002522452],"domain_scores_gemma":[0.9946865,0.0006687714,0.000207177,0.0006136296,0.003795998,0.00002786059],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004820342,0.0004482233,0.0001516996,0.004460511,0.000586493,8.297637e-7,0.0341648,0.02841124,0.127571,0.2853579,0.01809218,0.4959347],"study_design_scores_gemma":[0.002431242,0.001928159,0.0001598236,0.001407792,0.000009836223,6.928666e-7,0.007464297,0.4559618,0.4030167,0.002252954,0.1251245,0.0002421524],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2456145,0.004399342,0.7055781,0.01116594,0.01444633,0.01671183,0.001231644,0.0001733393,0.0006789372],"genre_scores_gemma":[0.9976031,0.0002571625,0.001802478,0.000007379273,0.0001113269,0.0001097388,0.000005964812,0.000004723177,0.000098131],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7519886,"threshold_uncertainty_score":0.3178692,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.110888145767188,"score_gpt":0.3661943576110198,"score_spread":0.2553062118438318,"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."}}