{"id":"W2012114007","doi":"10.1007/s10207-012-0178-1","title":"Evaluation in the absence of absolute ground truth: toward reliable evaluation methodology for scan detectors","year":2012,"lang":"en","type":"article","venue":"International Journal of Information Security","topic":"Network Security and Intrusion Detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"","keywords":"Ground truth; Computer science; Detector; Intrusion detection system; Data mining; Artificial intelligence; Intrusion; Common ground; Machine learning; Telecommunications","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":[0.01981306,0.0001032634,0.0001798233,0.0004760491,0.00006360431,0.0001178783,0.0009340544,0.00009584439,0.00004945262],"category_scores_gemma":[0.002312922,0.00008038746,0.0001328459,0.0003729532,0.00004096819,0.004888661,0.00007214852,0.0002287676,0.000005764693],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003155268,"about_ca_system_score_gemma":0.0002364071,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007494709,"about_ca_topic_score_gemma":0.00002230371,"domain_scores_codex":[0.9962898,0.0005776449,0.001015243,0.00008126469,0.001847607,0.0001883802],"domain_scores_gemma":[0.9948103,0.000721288,0.001188603,0.0001832707,0.003046988,0.00004951423],"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":[0.0007074769,0.0005399211,0.001502749,0.0001023616,0.0003399374,0.000001379555,0.08476801,0.01527179,0.0008477797,0.23866,0.003037351,0.6542212],"study_design_scores_gemma":[0.004129479,0.0006004903,0.06824093,0.0001830786,0.0001105823,0.0003453579,0.002418743,0.7068066,0.006351615,0.1955405,0.01492899,0.0003436429],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5391954,0.0004559424,0.4510855,0.001280496,0.006287549,0.0006438562,0.00001003213,0.00001435455,0.001026887],"genre_scores_gemma":[0.9890027,0.00006990483,0.01030405,0.0002451714,0.0003334885,0.00003080962,0.00001041974,0.000002766774,6.941729e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6915348,"threshold_uncertainty_score":0.686685,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0960749425709773,"score_gpt":0.3628560966939349,"score_spread":0.2667811541229576,"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."}}