{"id":"W4409621815","doi":"10.1002/nme.70034","title":"KATO: Neural‐Reparameterized Topology Optimization Using Convolutional Kolmogorov‐Arnold Network for Stress Minimization","year":2025,"lang":"en","type":"article","venue":"International Journal for Numerical Methods in Engineering","topic":"Topology Optimization in Engineering","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Minification; Convolutional neural network; Topology optimization; Computer science; Topology (electrical circuits); Stress (linguistics); Mathematical optimization; Applied mathematics; Algorithm; Mathematics; Artificial intelligence; Finite element method; Engineering; Structural engineering; Combinatorics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005762128,0.0003181758,0.0004565719,0.0006432608,0.000114633,0.0001112678,0.0004551144,0.0002653382,0.00004373635],"category_scores_gemma":[0.00113165,0.0003732906,0.0002089831,0.0004955764,0.00004399168,0.0003282074,0.00006198957,0.0003896626,3.937586e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005555874,"about_ca_system_score_gemma":0.00005597643,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004223475,"about_ca_topic_score_gemma":8.012286e-7,"domain_scores_codex":[0.9979702,0.00008661978,0.0009183792,0.0003025175,0.0001852385,0.0005370519],"domain_scores_gemma":[0.9980925,0.001177601,0.0001391037,0.0001574223,0.0003327128,0.0001006171],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008275625,0.00002734652,0.0004943747,0.0000677848,0.000231948,0.000003957723,0.0000400772,0.9916722,0.0009679142,0.003413718,0.0002680454,0.00272987],"study_design_scores_gemma":[0.001305546,0.0000344514,0.0001422504,0.0001331157,0.00004713746,0.00006719305,0.00002593015,0.9925691,0.000796226,0.001099978,0.003473907,0.0003051762],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001155277,0.0005295677,0.983194,0.0003350115,0.01396353,0.0004566248,0.00005216839,0.0002574726,0.00005635145],"genre_scores_gemma":[0.02424497,0.00008828209,0.9744879,0.0001051388,0.0006834572,0.0001689465,0.00007659,0.00008488286,0.00005985051],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02308969,"threshold_uncertainty_score":0.9998719,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02261058713039667,"score_gpt":0.3688971723528079,"score_spread":0.3462865852224113,"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."}}