{"id":"W4400381602","doi":"10.1016/j.asoc.2024.111928","title":"Self-supervised dual-layer 2D normalizing flow method for industrial anomaly detection","year":2024,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Anomaly detection; Dual (grammatical number); Computer science; Anomaly (physics); Flow (mathematics); Dual layer; Layer (electronics); Pattern recognition (psychology); Artificial intelligence; Mathematics; Materials science; Physics; Composite material; Geometry","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009050576,0.0002508323,0.0002455467,0.0002293094,0.0005969741,0.0005405601,0.0004677877,0.0002151517,0.000006895193],"category_scores_gemma":[0.00002133628,0.0002603601,0.0001718531,0.0009521817,0.00001908852,0.000270358,0.0002912347,0.0003617826,0.00004969391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001194104,"about_ca_system_score_gemma":0.0000945502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002866119,"about_ca_topic_score_gemma":0.00000409666,"domain_scores_codex":[0.9980551,0.00004841001,0.0004582912,0.0007692642,0.0002252552,0.0004436934],"domain_scores_gemma":[0.998764,0.00048375,0.0001069212,0.000453846,0.00008253905,0.0001089738],"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":[0.000008897557,0.00004073736,0.000009709021,0.00007005603,0.0000609596,0.000003093183,0.0007048242,0.001336484,0.01765309,0.03851287,0.0006088077,0.9409904],"study_design_scores_gemma":[0.0002930915,0.00006162802,0.00001453998,0.00002296486,0.0000291946,0.00003424218,0.00004337422,0.9145221,0.04040465,0.002786928,0.04149273,0.0002946113],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003122539,0.00008127546,0.9902318,0.0002539254,0.0005459078,0.0008570533,0.000004145797,0.003366672,0.001536647],"genre_scores_gemma":[0.4708318,0.000002144777,0.5283606,0.0001627399,0.0004463774,0.0001384024,0.000004171847,0.00002567858,0.00002802179],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9406959,"threshold_uncertainty_score":0.9999849,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03082451740863196,"score_gpt":0.2875966023330008,"score_spread":0.2567720849243688,"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."}}