{"id":"W4407424530","doi":"10.1016/j.automatica.2025.112193","title":"Physics-informed neural network Lyapunov functions: PDE characterization, learning, and verification","year":2025,"lang":"en","type":"article","venue":"Automatica","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Lyapunov function; Artificial neural network; Characterization (materials science); Applied mathematics; Physics; Computer science; Artificial intelligence; Mathematics; Quantum mechanics; Optics; Nonlinear system","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":[],"consensus_categories":[],"category_scores_codex":[0.00005547012,0.0001179129,0.0001335823,0.00003053503,0.0002783063,0.00008407996,0.00005588335,0.00003365768,0.0003029616],"category_scores_gemma":[0.000007657542,0.000112248,0.00004359083,0.0002595953,0.00004508952,0.0001873112,0.00003185385,0.0001444846,0.00004536508],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001268341,"about_ca_system_score_gemma":0.00003969296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005646088,"about_ca_topic_score_gemma":3.030177e-7,"domain_scores_codex":[0.9993179,0.00003963476,0.0002152515,0.0001721139,0.00007397338,0.0001811669],"domain_scores_gemma":[0.9996237,0.00005333416,0.0000978928,0.0001334274,0.00004497472,0.00004668258],"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":[0.00004957657,0.0001774943,0.08650099,0.00009903807,0.0002340072,4.300726e-7,0.0005107931,0.009735738,0.002334065,0.1448302,0.02133635,0.7341913],"study_design_scores_gemma":[0.0006020637,0.00004225083,0.05601387,0.00008661215,0.00007967055,0.000001236223,0.0001746015,0.8251039,0.0003494925,0.00583056,0.1114238,0.0002918583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6788489,0.0001033076,0.2704128,0.002403669,0.001508058,0.0007642498,0.00001306774,0.0006125356,0.0453334],"genre_scores_gemma":[0.9908614,0.00001468285,0.0003244079,0.0001579275,0.0004089221,0.00005627811,0.0002105057,0.00001026104,0.007955601],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8153682,"threshold_uncertainty_score":0.4577339,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007685554052186502,"score_gpt":0.2516909722706216,"score_spread":0.2440054182184351,"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."}}