{"id":"W4405268506","doi":"10.36227/techrxiv.173396130.09213575/v1","title":"Data Cleaning for Unsupervised Anomaly Detection","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Anomaly detection; Computer science; Data mining; Anomaly (physics); Benchmark (surveying); Data pre-processing; Artificial intelligence; Pattern recognition (psychology); Data set; Generalization; Similarity (geometry); Preprocessor; Contamination; Mathematics; Geography","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":[0.003627413,0.001391391,0.001245783,0.002396703,0.001008582,0.001588027,0.002419589,0.001156027,0.001623846],"category_scores_gemma":[0.02003605,0.0006909305,0.001557687,0.002122439,0.001229363,0.002438749,0.003045355,0.002852142,0.001915182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006860914,"about_ca_system_score_gemma":0.001832109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001990707,"about_ca_topic_score_gemma":0.002622545,"domain_scores_codex":[0.9955744,0.001004476,0.0004414677,0.00124007,0.001495518,0.000244146],"domain_scores_gemma":[0.9863026,0.003518173,0.001031807,0.006068846,0.002882494,0.0001960603],"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":[0.0006029928,0.000464926,0.027864,0.0006397978,0.0005194664,0.0003816109,0.0008757017,0.08419274,0.1006093,0.01131319,0.01545129,0.757085],"study_design_scores_gemma":[0.0000415957,0.0003356384,0.01587371,0.00009521923,0.00009892635,0.0007539587,0.0003249487,0.7432831,0.1756442,0.03302971,0.03038837,0.0001306018],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02766685,0.0001910281,0.9639839,0.0001623027,0.00006934135,0.0001427016,0.0007980845,0.006331849,0.0006539666],"genre_scores_gemma":[0.2581741,0.0002111775,0.7322955,0.0002187356,0.00006287677,0.0005084669,0.005903798,0.001289122,0.001336247],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003627413,"threshold_uncertainty_score":0.01918387,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08149931435038517,"score_gpt":0.3297805017193006,"score_spread":0.2482811873689155,"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."}}