{"id":"W4416052914","doi":"10.48550/arxiv.2504.11433","title":"Predicting Wave Dynamics using Deep Learning with Multistep Integration Inspired Attention and Physics-Based Loss Decomposition","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Mitacs; Transport Canada","keywords":"Deep learning; Autoencoder; Benchmark (surveying); Stability (learning theory); Convolutional neural network; Artificial neural network; Generalization; Nonlinear system; Representation (politics)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.0004966321,0.000976422,0.0006192839,0.0004083667,0.0002190771,0.0005686854,0.001366189,0.0009455353,0.001088059],"category_scores_gemma":[0.001388884,0.0003829072,0.0005674484,0.0003598855,0.0004515796,0.001252634,0.0009790186,0.001500165,0.000290682],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006995325,"about_ca_system_score_gemma":0.0008493339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006204031,"about_ca_topic_score_gemma":0.007232233,"domain_scores_codex":[0.9998701,0.00002159703,0.00000677302,0.00003547828,0.00004259452,0.00002354319],"domain_scores_gemma":[0.9996752,0.0001601546,0.00004315491,0.0000312487,0.00006521388,0.00002508842],"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":[0.00004888098,0.00005927412,0.000769414,0.00003040141,0.00003649736,0.00004647835,0.00002339273,0.9380189,0.005697771,0.003478005,0.0006022067,0.05118882],"study_design_scores_gemma":[8.107112e-7,0.000003778679,0.00002310097,5.710641e-7,0.000001043588,0.000001444654,4.341896e-7,0.9992932,0.0002321189,0.0004140531,0.00002861207,7.885774e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05112289,0.0004212914,0.9461839,0.000270418,0.00004855723,0.00002268607,0.00008179242,0.0009353994,0.0009130153],"genre_scores_gemma":[0.8573619,0.0003099614,0.1384536,0.0002376242,0.00006684881,0.00009490727,0.0003663867,0.0001183772,0.002990435],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006204031,"threshold_uncertainty_score":0.01233584,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02768860206882931,"score_gpt":0.279363501109779,"score_spread":0.2516748990409498,"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."}}