{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003328888,0.0001992302,0.0001792301,0.0001691619,0.0001562268,0.000536364,0.002416591,0.0002258842,0.00001542911],"category_scores_gemma":[0.00001962383,0.0001902511,0.0001203878,0.0002697041,0.00001978416,0.0001766287,0.006098965,0.0004060067,0.00007030038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006072771,"about_ca_system_score_gemma":0.0001084552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009642416,"about_ca_topic_score_gemma":0.00008206941,"domain_scores_codex":[0.998238,0.00001774779,0.0002984862,0.001109185,0.0001381913,0.0001984229],"domain_scores_gemma":[0.9972364,0.00005608873,0.00009081646,0.002460856,0.00009267789,0.00006313785],"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":[0.000007175161,0.00006642952,0.000007301522,0.0004298731,0.0001056815,0.00000284983,0.0001215946,0.0001390433,0.004171732,0.1745079,0.01693785,0.8035026],"study_design_scores_gemma":[0.00006138149,0.00004707795,0.00003455497,0.00004295015,0.00003228083,0.000008837596,0.00001423623,0.8021099,0.01158715,0.1060233,0.07974339,0.0002948916],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007536922,0.0001524137,0.9902017,0.001116274,0.0006000305,0.0007761448,0.0001259866,0.002205049,0.004068688],"genre_scores_gemma":[0.5835202,0.00004232739,0.4132072,0.0002466797,0.0003493519,0.000636554,0.0001171916,0.00003693363,0.001843574],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8032076,"threshold_uncertainty_score":0.7758216,"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."}}