{"id":"W4378421112","doi":"10.2139/ssrn.4460038","title":"The Drawback of Binary Labeling for the Evaluation of Unsupervised Intrusion Detection Algorithms","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Network Security and Intrusion Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Binary number; Intrusion detection system; Algorithm; Intrusion; Artificial intelligence; Mathematics; Arithmetic; Geology","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":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.01577337,0.0002091912,0.00026573,0.0001909126,0.0008895659,0.0001510347,0.001450967,0.0003131512,0.000003108928],"category_scores_gemma":[0.0003847566,0.0001322581,0.0003204254,0.0005294534,0.00009124749,0.0002004647,0.0006086557,0.003024554,0.000003235814],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006819154,"about_ca_system_score_gemma":0.002293926,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001285912,"about_ca_topic_score_gemma":0.0007534811,"domain_scores_codex":[0.9963762,0.0005077345,0.0007479202,0.0003441792,0.001037488,0.0009864401],"domain_scores_gemma":[0.9966039,0.0006422366,0.0009195694,0.000661172,0.001136543,0.00003658888],"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":[0.0001019898,0.00004204584,0.00000720935,0.000036813,0.0002757357,1.570693e-7,0.0004921905,0.04144426,0.003409089,0.01025401,0.00006282905,0.9438737],"study_design_scores_gemma":[0.0004435707,0.0003647099,0.0001081434,0.00009649619,0.0001166192,0.00002592223,0.0003289363,0.6697328,0.003880931,0.3244556,0.0003369915,0.0001093169],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1094256,0.0153102,0.8658187,0.002734158,0.005295764,0.00131537,0.000005308632,0.00007828519,0.00001664974],"genre_scores_gemma":[0.9693526,0.02877922,0.0009224164,0.00002596831,0.0006857602,0.0001054809,0.000005349692,0.0000317967,0.00009141811],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9437644,"threshold_uncertainty_score":0.9992755,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04054965104623198,"score_gpt":0.3056506656265871,"score_spread":0.2651010145803551,"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."}}