{"id":"W3200397134","doi":"10.1145/3460976","title":"Extending Isolation Forest for Anomaly Detection in Big Data via K-Means","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Cyber-Physical Systems","topic":"Network Security and Intrusion Detection","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Anomaly detection; Big data; SPARK (programming language); Intrusion detection system; Isolation (microbiology); Streaming data; Data mining; Anomaly (physics); Artificial intelligence; Real-time computing","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003279222,0.0001966217,0.0002758539,0.0001922102,0.0003715341,0.000240517,0.0007987093,0.0001343739,0.000003663492],"category_scores_gemma":[0.00006141077,0.0002038428,0.0001275792,0.001062684,0.00002685994,0.0009854016,0.00004850758,0.00030807,0.00003731168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001532517,"about_ca_system_score_gemma":0.00005254695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004432751,"about_ca_topic_score_gemma":0.00211983,"domain_scores_codex":[0.998014,0.0001803711,0.0003842211,0.0007703071,0.0003067133,0.0003444412],"domain_scores_gemma":[0.9977211,0.0004352294,0.0001157685,0.001513049,0.0001186975,0.00009611556],"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":[0.00007975743,0.0007158482,0.00007511405,0.00009278206,0.00006660601,0.00001460383,0.0005290467,0.03770147,0.02407795,0.002784589,0.00006128483,0.9338009],"study_design_scores_gemma":[0.0005867966,0.0002314063,0.0009290354,0.00009392822,0.00002395438,0.00004432695,0.00006147908,0.9796044,0.008597947,0.00349583,0.006063629,0.0002672181],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05542123,0.0000653133,0.9408469,0.0003342135,0.002620237,0.0004320955,0.00002502227,0.0001694985,0.00008543903],"genre_scores_gemma":[0.995935,0.00002388894,0.003039693,0.00005100658,0.0006408283,0.0001440815,0.00002988029,0.00002052017,0.0001151082],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.941903,"threshold_uncertainty_score":0.8312469,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04601198017966552,"score_gpt":0.2710519071490929,"score_spread":0.2250399269694274,"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."}}