{"id":"W4409262152","doi":"10.1109/wacv61041.2025.00915","title":"FUN-AD: Fully Unsupervised Learning for Anomaly Detection with Noisy Training Data","year":2025,"lang":"en","type":"article","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Information and Communications Technology Council; National Research Foundation of Korea","keywords":"Anomaly detection; Computer science; Unsupervised learning; Artificial intelligence; Training (meteorology); Training set; Machine learning; Pattern recognition (psychology)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002635808,0.0001136309,0.0001215155,0.000139095,0.0003929942,0.0001683149,0.0008477139,0.00005892338,0.00001155927],"category_scores_gemma":[0.00002732273,0.00009763561,0.00003510482,0.000634435,0.00002730709,0.0004610845,0.000226165,0.000129099,0.000006593998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000292813,"about_ca_system_score_gemma":0.00008717726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004116589,"about_ca_topic_score_gemma":0.0001042926,"domain_scores_codex":[0.9989775,0.00002206248,0.000177822,0.000515467,0.0001018928,0.0002052348],"domain_scores_gemma":[0.9989116,0.00008266814,0.00005952483,0.0008067171,0.0000948029,0.00004464382],"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":[0.0000297812,0.00004481698,0.0001939246,0.00002708707,0.00003897041,8.652183e-7,0.0002186232,0.0002141262,0.01927318,0.02150508,0.0005245504,0.957929],"study_design_scores_gemma":[0.0006859179,0.0004377902,0.002008188,0.00003356204,0.00003130659,0.00001787844,0.0004289752,0.769898,0.03890903,0.002442592,0.1847643,0.0003425035],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005660094,0.00002764536,0.9881532,0.0007326382,0.0000524067,0.0003875436,0.000002509425,0.0008226313,0.004161284],"genre_scores_gemma":[0.8131616,0.000005921884,0.1836533,0.0002784318,0.00002314237,0.000166624,0.00001089128,0.000008160901,0.00269201],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9575865,"threshold_uncertainty_score":0.3981465,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04135908940490878,"score_gpt":0.2839425167875609,"score_spread":0.2425834273826521,"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."}}