{"id":"W4415397854","doi":"10.1016/j.neunet.2026.109236","title":"Mask-PINNs: Mitigating Internal Covariate Shift in Physics-Informed Neural Networks","year":2025,"lang":"en","type":"preprint","venue":"Neural Networks","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Normalization (sociology); Feature (linguistics); Embedding; Artificial neural network; Convergence (economics); Feature learning; Limiting; Consistency (knowledge bases); Key (lock)","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":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0004331032,0.001039528,0.001098412,0.0002320946,0.0003543491,0.001168183,0.004136912,0.000784713,0.00002060999],"category_scores_gemma":[0.00004528774,0.001038333,0.0005615855,0.001460033,0.0001714482,0.0007016311,0.005129274,0.00441023,0.000009801531],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002547309,"about_ca_system_score_gemma":0.0001879435,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002894951,"about_ca_topic_score_gemma":0.0003358743,"domain_scores_codex":[0.9942019,0.000309157,0.001520331,0.001823611,0.000549967,0.001595046],"domain_scores_gemma":[0.9959387,0.0007466666,0.000848445,0.001995624,0.000133697,0.0003369048],"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":[0.00002522983,0.00006869584,0.001657804,0.00006817903,0.00004816181,0.00005718859,0.0001855766,0.8956544,0.000001587834,0.007634509,0.002475511,0.09212312],"study_design_scores_gemma":[0.0006308237,0.00005348932,0.002397147,0.0006074655,0.00003489633,0.00001542032,0.00001024649,0.9851957,0.000009448405,0.009545607,0.0006319822,0.0008677492],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01197135,0.001387281,0.969449,0.004563557,0.007288569,0.001861561,0.00003609532,0.0009362093,0.002506398],"genre_scores_gemma":[0.985566,0.0003138771,0.005187975,0.004702993,0.003254334,0.0004657267,0.0001862902,0.00006201029,0.0002608544],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9735946,"threshold_uncertainty_score":0.9998687,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02511426141977303,"score_gpt":0.2824379685600887,"score_spread":0.2573237071403157,"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."}}