{"id":"W4295929872","doi":"10.11606/d.55.2022.tde-15092022-141353","title":"Detecting outliers and annotating their types with indexing structures","year":2022,"lang":"en","type":"dissertation","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Cascades (Canada)","funders":"","keywords":"Outlier; Computer science; Anomaly detection; Categorization; Data mining; Scalability; Scope (computer science); The Internet; Search engine indexing; Artificial intelligence; Information retrieval; Database; World Wide Web","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":[0.003116016,0.001236552,0.001966851,0.01214524,0.001917164,0.004890887,0.003726156,0.002113515,0.002410825],"category_scores_gemma":[0.02355166,0.0005592388,0.001711914,0.01305154,0.001487783,0.005601167,0.00328234,0.002293725,0.0045217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001523992,"about_ca_system_score_gemma":0.00227954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007900131,"about_ca_topic_score_gemma":0.01110667,"domain_scores_codex":[0.991856,0.0005632208,0.001457783,0.001750035,0.003530162,0.0008428861],"domain_scores_gemma":[0.9815088,0.003351445,0.003642463,0.004932752,0.005891206,0.0006733928],"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":[0.001623191,0.0006128091,0.2110327,0.00150401,0.0002148149,0.001992185,0.003468221,0.01430113,0.04287183,0.03285671,0.0867288,0.6027935],"study_design_scores_gemma":[0.0001700982,0.0006688809,0.1090751,0.0009727864,0.0004146897,0.004195668,0.009084595,0.3029673,0.08040569,0.1480805,0.3433533,0.0006114244],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2386893,0.004403939,0.6278946,0.002594953,0.001268975,0.001302538,0.08464739,0.02594622,0.01325208],"genre_scores_gemma":[0.4051655,0.001912564,0.4670968,0.0006812813,0.0004197328,0.001007831,0.1147815,0.001986805,0.006948032],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01214524,"threshold_uncertainty_score":0.01647925,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007325911939838359,"score_gpt":0.2434786647761562,"score_spread":0.2361527528363178,"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."}}