{"id":"W4394796613","doi":"10.21203/rs.3.rs-4243961/v1","title":"A Novel Kernel-Based Machine Learning Approach for Differential-Algebraic Equations","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Numerical methods for differential equations","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Legendre polynomials; Kernel (algebra); Support vector machine; Mathematics; Nonlinear system; Kernel method; Applied mathematics; Residual; Differential (mechanical device); Computer science; Differential algebraic equation; Differential equation; Algorithm; Artificial intelligence; Mathematical analysis; Engineering","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":[0.001291542,0.0006184505,0.001490313,0.000841058,0.0006129105,0.001382105,0.002097229,0.001445862,0.002779599],"category_scores_gemma":[0.004727591,0.0004543356,0.000956617,0.00103065,0.0008861928,0.002103665,0.002268323,0.002295227,0.001448796],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006439955,"about_ca_system_score_gemma":0.001180802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00261772,"about_ca_topic_score_gemma":0.002476278,"domain_scores_codex":[0.9991559,0.0002709971,0.00006013013,0.0001488451,0.0003023125,0.00006181445],"domain_scores_gemma":[0.9979171,0.0008748554,0.0001595497,0.000245493,0.0006869361,0.000116155],"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":[0.0002432653,0.0003121709,0.001342319,0.0003870281,0.0002057964,0.0001458489,0.0001370913,0.4971182,0.01216513,0.1370057,0.008043408,0.3428941],"study_design_scores_gemma":[0.000002633226,0.000006662041,0.00003941495,0.000002419922,0.00000342635,0.000008896577,0.000001842794,0.9940467,0.0002938832,0.005153344,0.000436839,0.0000038597],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002758406,0.0001760058,0.9962317,0.0001057327,0.00005813916,0.0000142608,0.00002455722,0.000199446,0.000431673],"genre_scores_gemma":[0.30082,0.0007293764,0.6869166,0.0002985825,0.0003587975,0.0002055434,0.0003800294,0.0003502634,0.009940802],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002779599,"threshold_uncertainty_score":0.009298682,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2497161793882159,"score_gpt":0.4723020964633409,"score_spread":0.222585917075125,"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."}}