{"id":"W4413371374","doi":"10.1109/tii.2025.3582372","title":"TKDA: A Tensor-Based Knowledge Distillation Approach of Anomaly Detection for Industrial Cyber-Physical Intelligence","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Informatics","topic":"Computational Physics and Python Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"National Natural Science Foundation of China","keywords":"Cyber-physical system; Anomaly detection; Computer science; Tensor (intrinsic definition); Distillation; Artificial intelligence; Chemistry; Mathematics; Chromatography","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":[0.000260544,0.0001967857,0.0002787178,0.0004332991,0.0002771007,0.0001114565,0.0004399031,0.0002041113,0.000002180836],"category_scores_gemma":[0.00003354954,0.000196822,0.0002121206,0.001643625,0.00008508422,0.0003677969,0.000006401736,0.0003672853,0.00001036778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001303767,"about_ca_system_score_gemma":0.000432871,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002787003,"about_ca_topic_score_gemma":0.000005547345,"domain_scores_codex":[0.9986039,0.00005145354,0.000697613,0.0002048215,0.0002391308,0.0002030475],"domain_scores_gemma":[0.9981695,0.0007314428,0.0002790127,0.0004196005,0.0003273003,0.00007317775],"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":[0.0001425595,0.000794502,0.000009428475,0.00006234037,0.00008526501,4.571057e-8,0.0007572356,0.4043641,0.0002107357,0.04326485,0.0002924874,0.5500165],"study_design_scores_gemma":[0.0009636512,0.000221287,0.00002337755,0.00004773056,0.00005451448,7.577588e-7,0.00009757117,0.9611925,0.03157092,0.003884719,0.001757654,0.0001853061],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01313788,0.000002627107,0.9834682,0.0001372379,0.0007396568,0.0009259164,0.00008061407,0.0001060887,0.001401763],"genre_scores_gemma":[0.9855211,0.000001041333,0.01394245,0.00004386058,0.0001529002,0.0002271841,0.00001811096,0.000008741555,0.000084605],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9723832,"threshold_uncertainty_score":0.8026167,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06476290144687455,"score_gpt":0.2999850653799274,"score_spread":0.2352221639330528,"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."}}