{"id":"W4388266986","doi":"10.36227/techrxiv.24415900.v1","title":"Hybrid Physics-Informed Neural Network for the Wave Equation with Unconditionally Stable Time-Stepping","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Artificial neural network; Stability (learning theory); Limit (mathematics); Wave equation; Acceleration; Domain (mathematical analysis); Time stepping; Finite difference; Finite difference method; Computer science; Algorithm; Applied mathematics; Physics; Mathematical analysis; Finite element method; Mathematics; Artificial intelligence; Classical mechanics; Machine learning; Quantum mechanics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004073575,0.000478674,0.0004141828,0.0002382237,0.0003361051,0.0005254499,0.001086755,0.0009424858,0.002048381],"category_scores_gemma":[0.001075501,0.0002625863,0.0003738068,0.0002836959,0.0005011545,0.0007954831,0.0008422394,0.001182863,0.0004760181],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006554339,"about_ca_system_score_gemma":0.000881478,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003931592,"about_ca_topic_score_gemma":0.00473582,"domain_scores_codex":[0.9998714,0.00003961952,0.000004844174,0.00001602037,0.00005799683,0.00001005044],"domain_scores_gemma":[0.9997714,0.0001196735,0.0000230774,0.00003385717,0.00003636969,0.00001555912],"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":[0.00002880735,0.00002801551,0.0002108637,0.00004493746,0.00001794565,0.00004197997,0.00003257198,0.9490209,0.00362845,0.03229965,0.0005187452,0.01412708],"study_design_scores_gemma":[0.000001269807,0.000001993025,0.000008711613,9.327252e-7,4.366424e-7,0.000002276315,6.272624e-7,0.9981055,0.0001615741,0.001576388,0.0001391303,0.000001096561],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02160546,0.0001734548,0.9723415,0.000240894,0.00004219292,0.00003399922,0.00006936695,0.0002887512,0.005204414],"genre_scores_gemma":[0.5728679,0.0002582736,0.4181554,0.0002523347,0.00003827209,0.0002863382,0.000209031,0.0001816751,0.007750831],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003931592,"threshold_uncertainty_score":0.007817388,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06441235734881755,"score_gpt":0.2689174260710658,"score_spread":0.2045050687222482,"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."}}