{"id":"W4389952571","doi":"10.2139/ssrn.4668704","title":"Self-Supervised Dual-Layer 2d Normalized Flow Method for Industrial Anomaly Detection","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Download; Computer science; Anomaly detection; Dual (grammatical number); Dual layer; Anomaly (physics); Layer (electronics); Flow (mathematics); Data mining; World Wide Web; Mathematics; Physics","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","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004166816,0.0004729418,0.0005479944,0.0005376959,0.0007217322,0.0005377244,0.001460817,0.0007708998,0.00001092748],"category_scores_gemma":[0.00009792885,0.0004696674,0.0006572893,0.0006943279,0.00002416017,0.0003685201,0.0007122608,0.004775329,0.00004649812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001594831,"about_ca_system_score_gemma":0.003448973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000180936,"about_ca_topic_score_gemma":0.0004231753,"domain_scores_codex":[0.9951954,0.0002998287,0.0008455736,0.0009148462,0.0004723226,0.002272053],"domain_scores_gemma":[0.9976953,0.0001964536,0.0006627244,0.0008863593,0.0003743352,0.0001847872],"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":[0.0002355207,0.0003449753,0.00007295852,0.000115661,0.001490962,0.00001164299,0.0005631454,0.002597989,0.004765168,0.1046154,0.001662018,0.8835246],"study_design_scores_gemma":[0.001770486,0.0007005848,0.00003329877,0.00004652757,0.0002061114,0.0005860494,0.0001317945,0.5640939,0.009181738,0.4036041,0.01882356,0.000821793],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002150402,0.0002691451,0.9918671,0.001544383,0.001349848,0.001309324,0.00002174741,0.001360955,0.0001270521],"genre_scores_gemma":[0.1669042,0.003434594,0.8197114,0.0002655137,0.004209359,0.001930945,0.00005182014,0.0002181068,0.003274039],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8827028,"threshold_uncertainty_score":0.9997755,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0398110202005813,"score_gpt":0.3049174129147265,"score_spread":0.2651063927141452,"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."}}