{"id":"W4415291118","doi":"10.1016/j.matcom.2025.10.019","title":"Polytopal mesh agglomeration via geometrical deep learning for three-dimensional heterogeneous domains","year":2025,"lang":"en","type":"article","venue":"Mathematics and Computers in Simulation","topic":"Computer Graphics and Visualization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institutes of Health; European Research Council; Politecnico di Milano; European Commission","keywords":"Graph partition; Polygon mesh; Graph; Discretization; Partition (number theory); Domain (mathematical analysis); Exploit; Generalization; Cluster analysis","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005567133,0.0009435847,0.0009930601,0.001218183,0.0005817068,0.001159729,0.001935854,0.001432492,0.001794763],"category_scores_gemma":[0.001975376,0.0007163672,0.001191089,0.0008306314,0.001076147,0.001316509,0.002024885,0.001514667,0.0005148236],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001648915,"about_ca_system_score_gemma":0.001042662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01211381,"about_ca_topic_score_gemma":0.01535075,"domain_scores_codex":[0.9996734,0.00005732718,0.00001917834,0.00008576138,0.0001181111,0.00004622131],"domain_scores_gemma":[0.9992974,0.0002793667,0.0001102221,0.0001358812,0.0001196373,0.0000575055],"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":[0.00005743383,0.00002575929,0.0008533475,0.00005293591,0.00004055819,0.00006380967,0.00006485175,0.9355626,0.002280923,0.005939636,0.001043031,0.05401519],"study_design_scores_gemma":[0.000001599135,0.00000375988,0.00003815825,0.000002103658,0.000001733371,0.000006236529,0.000004813695,0.9974871,0.0003076375,0.001968601,0.0001765716,0.000001865797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02057858,0.0001799517,0.9765173,0.0001692397,0.00002258165,0.00003053721,0.00006699986,0.001342152,0.001092537],"genre_scores_gemma":[0.5226793,0.0002897649,0.4712794,0.0003422853,0.00004561676,0.0001679667,0.0007803919,0.0004867519,0.003928483],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01211381,"threshold_uncertainty_score":0.02408659,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01623395809501786,"score_gpt":0.2952596576995908,"score_spread":0.279025699604573,"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."}}