{"as_of":"2026-08-21T02:54:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:28ab0ebdff0c9cb98f0882d2dd6747692fbabc34c4ac2a70ed477d9e04c1bd28","coverage":[{"denominator":65,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":65,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-24T06:52:12.821942Z","state":"measured"},{"denominator":67,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":67,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T16:36:54.809029Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-06T22:07:02.591291Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"cited_work":{"arxiv_id":"2309.13722","doi":null,"metadata_source":"pith","pith_arxiv_id":"2309.13722","snapshot_observed_at":"2026-08-06T22:07:02.591291Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","venue":"math.NA","work_id":"8eeb3f7b-b1c3-476e-8cd4-7fba2a8a7db0","year":2023},"citing_paper":{"arxiv_id":"2506.22851","last_updated":"2025-06-28T11:25:44Z","snapshot_observed_at":"2026-08-06T21:54:50.140169Z","submitted_at":"2025-06-28T11:25:44Z","title":"Deep neural networks can provably solve Bellman equations for Markov decision processes without the curse of dimensionality","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T22:06:56.731948Z"},"links":{"cited_paper":"/paper/2309.13722","citing_paper":"/paper/2506.22851"},"observation_digest":"sha256:2e545872e8991a859251e4828fe43bddf2cfaef92b8be070eee56793ba30f30c","observation_id":"494c527a-8b8e-455d-ae06-4e8ef2b7ff1d","resolution":{"observed_at":"2026-08-06T22:07:02.700622Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.13722","snapshot_observed_at":"2026-08-11T16:36:54.809029Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.09494","last_updated":"2026-08-10T12:01:46Z","snapshot_observed_at":"2026-08-21T02:47:53.421303Z","submitted_at":"2026-08-10T12:01:46Z","title":"Walk-on-Spheres Monte Carlo and deep neural network approximations of elliptic PDEs with drift and killing","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T16:36:54.809029Z"},"links":{"cited_paper":"/paper/2309.13722","citing_paper":"/paper/2608.09494"},"observation_digest":"sha256:4bb173af09959e82896d8e1f766317bc8fa19a0e4d46660d055eb0cfd0304813","observation_id":"4642715b-5216-416b-9457-f1e01a615b01","resolution":{"observed_at":"2026-08-11T16:36:54.809029Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2309.13722/citation-record","integrity":"/paper/2309.13722/integrity","json":"/paper/2309.13722/citation-record.json","paper":"/paper/2309.13722"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Approximation properties of residual neural networks for Kolmogorov PDEs.Discrete Contin","venue":null,"work_id":"ea273523-5813-4a7b-bd25-6857d6a3ed85","year":2023},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:e3b06daf9be6c7c4cb0787a3b4942dc417cddfb29eaed4a0b9150b3d8091cdc5","observation_id":"4ec23928-f084-431d-aad7-5f0d8edee0ba","resolution":{"observed_at":"2026-05-24T06:56:03.157162Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Numerical solution of inverse problems by weak adversarial networks.Inverse Problems 36, 11 (2020), 115003, 31","venue":null,"work_id":"e320a6b1-4880-403e-bd51-26db0ab80588","year":2020},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:8d167205a5c29ded3a9826f2879ee7764524de8a13204947a3dd2cf34d122b79","observation_id":"0d16c880-ec1c-41ce-8116-6a0d21ba1bb3","resolution":{"observed_at":"2026-05-24T06:56:03.154042Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Deep splitting method for parabolic PDEs","venue":null,"work_id":"ad77532a-f08f-4eff-9da4-514e8a79ddff","year":2021},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:c1ace343f17e630a9715e2d99489a67a90dfcc2b8907534c5d09682a39a8062d","observation_id":"fae4e0e5-8949-488c-bb71-27361f035603","resolution":{"observed_at":"2026-05-24T06:56:03.156364Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Solving the Kolmogorov PDE by means of deep learning.J","venue":null,"work_id":"ae22d3da-71ff-432f-9d27-1801ad042d32","year":2021},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:3a78e94b10994a31e18caf99d186e884ebae214b9ddfce263e89a31808557b83","observation_id":"53d13773-929f-40ff-8ba3-469e39c674b8","resolution":{"observed_at":"2026-05-24T06:56:03.357265Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order back- ward stochastic differential equations.J","venue":null,"work_id":"ea40c907-8794-413b-b346-84550e2f42c1","year":2019},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:1f3840de732e6004946c441233231eaecc5adbfd7a718447d67a4a0cef47fea5","observation_id":"64275338-ac93-4d4d-b915-b87a178e3662","resolution":{"observed_at":"2026-05-24T06:56:03.353746Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"On existence and uniqueness properties for solutions of stochastic fixed point equations.Discrete Contin","venue":null,"work_id":"d4269efc-09e6-4929-b15d-d9b07589c509","year":2021},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:b865924f6c21363483f3dd349a3936460faf0658553cdc8034f70b9847ce402b","observation_id":"f080451d-5faa-429a-a77e-93a6b0022e05","resolution":{"observed_at":"2026-05-24T06:56:03.350207Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Overcoming the curse of dimensionality in the numerical approximation of high-dimensional semilinear elliptic partial differential equations","venue":null,"work_id":"d9b2dbee-3b5b-4100-b52d-93224e4060d3","year":2024},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:16ea0d80042de9c2ab0aa265aa44a553279051cf6a60fc88918470ab77d7ee43","observation_id":"0dce92c1-ae1a-4037-8c1f-19247f790486","resolution":{"observed_at":"2026-05-24T06:56:03.346731Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"feb6aa2b-4f03-4506-b72f-05f9f7890644","year":2020},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:886757e972047965d130ccbe6279235a2611060ad9d2a71958ead81e1e9b957b","observation_id":"bb7c49b6-7477-498a-bb5c-f520a0d229db","resolution":{"observed_at":"2026-05-24T06:56:03.342984Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"On nonlinear Feynman–Kac formulas for viscosity solutions of semilinear parabolic partial differential equations","venue":null,"work_id":"9d5cee00-ab02-451e-b708-6b68c3807493","year":2021},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:572340f70eaded91f3921f3ea32f96b12277daa9771026a76b8981b72c38f991","observation_id":"a0c91d28-73c2-4650-b4df-1dfaea47fb96","resolution":{"observed_at":"2026-05-24T06:56:03.340114Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"An overview on deep learning-based approximation methods for partial differential equations.Discrete Contin","venue":null,"work_id":"ad2af4ab-82d7-44ee-858e-318a77bad3b0","year":2023},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:98f8b8bfea66441f0d84d60dbda9752f53d967006335ab2328f37d0901088bfc","observation_id":"23fb148d-87f1-4753-a588-7d95f96c889e","resolution":{"observed_at":"2026-05-24T06:56:03.336699Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"NumericalsimulationsforfullhistoryrecursivemultilevelPicard approximations for systems of high-dimensional partial differential equations.Commun","venue":null,"work_id":"506b02d9-8170-499a-a224-b9dd88c4aedc","year":2020},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:04fc2a521112901d444f378416b6bf51d3da6f8832cf75bc7636b8495da6f0a3","observation_id":"b8e293de-cdf2-49fc-9800-cface9588b85","resolution":{"observed_at":"2026-05-24T06:56:03.333466Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Dynamic programming","venue":null,"work_id":"4d3f343e-d26b-4fc6-910d-b33bf3806e58","year":2010},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:8a16e389b03def4594e1aa850f7bbdd706deedb71d44c916a98f842b254af70a","observation_id":"643bbbb1-4b00-485e-bbd3-d3da6cde7534","resolution":{"observed_at":"2026-05-24T06:56:03.329916Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A unified deep artificial neural network approach to partial differential equations in complex geometries.Neurocomputing 317 (2018), 28– 41","venue":null,"work_id":"acc6b528-adb1-40d1-8253-2eb794cb9455","year":2018},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:40690bcb2ee26e473312a086dcb4fef47703a3ad80d4102f4ca8f2029538fd21","observation_id":"c13ceca4-f7b1-4dbd-9a0d-b97ee7abd08c","resolution":{"observed_at":"2026-05-24T06:56:03.326835Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"b0a46f45-c7da-441f-a726-62d54df830ba","year":2020},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:115a0e01ded782f2c61ca7dc6b656f2ca95eb5223bc9f947f821eec01ad946e9","observation_id":"17ec7910-51fd-4645-ac71-35250e001e3c","resolution":{"observed_at":"2026-05-24T06:56:03.299417Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"72edb744-1366-4aef-8d96-84c0f3caee27","year":2021},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:b73d84ce2fc52e882561edc2f8c43375dd14d19b03c544eea467ebdf88f5b126","observation_id":"56f193b4-d0b9-4977-868b-ea2838548a72","resolution":{"observed_at":"2026-05-24T06:56:03.238108Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Machine learning for semi linear PDEs","venue":null,"work_id":"75c6123b-0703-4c66-84c2-6d3b65e0598b","year":2019},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:d926755c70c8a938dd004f36cacd6d27c90fa6a9fc408412f626a2317e648064","observation_id":"06398c33-7cef-4ecb-bd07-a7e93ab9ac18","resolution":{"observed_at":"2026-05-24T06:56:03.305557Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.14372","last_updated":"2022-12-29T17:02:59Z","snapshot_observed_at":"2026-08-16T16:05:25.149561Z","submitted_at":"2022-12-29T17:02:59Z","title":"Deep Runge-Kutta schemes for BSDEs","version":1},"cited_work":{"arxiv_id":"2212.14372","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2212.14372","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Deep Runge–Kutta schemes for BSDEs","venue":null,"work_id":"9ce33ec9-ae00-4afd-9dde-69bb22383508","year":2022},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"cited_paper":"/paper/2212.14372","citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:571f553dbeffa20eb25262db276d3c21bd97d4b39f33f5d29464d53dc6638754","observation_id":"68bb84b0-2d0b-4c2c-b3e5-9785b1e0ae85","resolution":{"observed_at":"2026-05-24T06:54:03.220774Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.14398","last_updated":"2022-05-28T11:03:35Z","snapshot_observed_at":"2026-08-17T22:54:22.020413Z","submitted_at":"2022-05-28T11:03:35Z","title":"Deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear partial differential equations","version":1},"cited_work":{"arxiv_id":"2205.14398","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2205.14398","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A., Hutzenthaler, M., and Werner, P","venue":null,"work_id":"64229ce6-4225-42e2-a5a1-356121508e4d","year":2022},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"cited_paper":"/paper/2205.14398","citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:b43f4df8c3a8213c594fb981e60e66da32a3d6fdcb68cf23233a480d5531f5f6","observation_id":"9e38a357-c355-4849-b86c-3cf1f1cecfc0","resolution":{"observed_at":"2026-05-24T06:54:03.215918Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Deep learning-based numerical methods for high- dimensional parabolic partial differential equations and backward stochastic differential equations","venue":null,"work_id":"7a456cd1-4a98-467c-933f-b5e0c32e6b3b","year":2017},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:12854906c3fb2077ab69b935744fbe2314bc4be0e296398793eb2865d7b4641c","observation_id":"895d6e78-8aff-42c1-9f2f-8c19375c9e11","resolution":{"observed_at":"2026-05-24T06:56:03.296223Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Algorithms for solving high dimensional PDEs: from nonlinear Monte Carlo to machine learning.Nonlinearity 35, 1 (2022), 278–310","venue":null,"work_id":"985a25d2-2876-45d5-96f0-54f91c38e028","year":2022},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:fffe42f72b414a9c86424f1e45ba210a8185e17600f5bf27deec41e93f78e334","observation_id":"ed9d5f52-c992-493f-bd19-6329cb228827","resolution":{"observed_at":"2026-05-24T06:56:03.293028Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"7cdf9e0f-5951-4a48-9b78-4b53e7a26f0c","year":2019},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:78758b9c52d7a7362f6c7ea3e273925024b7fd25c89e5dbe179c3042130e90ab","observation_id":"14863f1b-a438-4231-a438-3fc205ca30b8","resolution":{"observed_at":"2026-05-24T06:56:03.289425Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Multilevel Picard itera- tions for solving smooth semilinear parabolic heat equations.Partial Differ","venue":null,"work_id":"d297ea2e-5645-47d5-8000-6e81dc2474a7","year":2021},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:6f650d0fa3082232e42a22d9b2612904d81022d4bef5df6091991c54d179025e","observation_id":"56fc0120-ec91-4a26-b09f-2e8f6aecf089","resolution":{"observed_at":"2026-05-24T06:56:03.286531Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"The deep Ritz method: A deep learning-based numerical algorithm for solving variational problems.Commun","venue":null,"work_id":"150f37d7-3e64-4236-ab6b-41dc494b5b59","year":2018},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:bdbce711dcd1ef85aca7d76fbd03b732781562d637d2805f3dd2e561c49804fc","observation_id":"ae3bacc5-8fff-41d3-ae53-f8e5c89ff17d","resolution":{"observed_at":"2026-05-24T06:56:03.311538Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"DNN expression rate analysis of high-dimensional PDEs: Application to option pricing.Constr","venue":null,"work_id":"d3a2ac8c-3026-42f8-8b88-903698821b26","year":2021},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:e39dbaa521e11a9fb15f3fe0e8c6a131c413d14ee65d2aa5e1cba5cac5ada4ad","observation_id":"7312f469-fc82-454c-97f4-928a42222e44","resolution":{"observed_at":"2026-05-24T06:56:03.283067Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Fractional weak adversarial networks for the sta- tionary fractional advection dispersion equations.Z","venue":null,"work_id":"829c7685-7bb9-4bb0-89b1-2178e5942bf7","year":2024},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:8691d3fa106d067e76a2fbb81e4f86fe3e4288c9955fc2bd4d5bf97630db5553","observation_id":"c2792a1b-01df-485b-8628-a599745a940d","resolution":{"observed_at":"2026-05-24T06:56:03.278860Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Asymptotic expansion as prior knowledge in deep learning method for high dimensional BSDEs.Asia-Pacific Financial Markets (Mar 2019)","venue":null,"work_id":"280ee9be-d1d9-4536-b01e-d903a89f0d2f","year":2019},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:cd08d3a008d3abde3723dd6c38278a0f76f10178856302890ce8cbadb1c24256","observation_id":"f6511de6-f738-49b5-8ef2-0ff8e4743205","resolution":{"observed_at":"2026-05-24T06:56:03.275788Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Approximation error analysis of some deep backward schemes for nonlinear PDEs.SIAM J","venue":null,"work_id":"b3d264e9-0293-4be8-806d-80abbde29c7e","year":2022},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:190abdf14b2e407903a9cb02b12d9b63dcd7b6a4bd7f42eb56fb2dee658eede8","observation_id":"de8ff125-cd47-48fd-a4d1-1118fa37077f","resolution":{"observed_at":"2026-05-24T06:56:03.331071Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Neural Networks–Based Algorithms for Stochastic Control and PDEs in Finance","venue":null,"work_id":"cdd67cc8-484a-43b6-996c-57e8d59fd16e","year":2023},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:6d7e4abb005fec01f85e1f2a1464f745518000c9112aef304e6988067970dab0","observation_id":"cd7ade47-26fd-4ce7-8aad-3e3cbad56bab","resolution":{"observed_at":"2026-05-24T06:56:03.272092Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1911.03188","last_updated":"2019-11-08T11:18:27Z","snapshot_observed_at":"2026-08-19T21:56:09.668203Z","submitted_at":"2019-11-08T11:18:27Z","title":"Generalised multilevel Picard approximations","version":1},"cited_work":{"arxiv_id":"1911.03188","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1911.03188","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"B., Jentzen, A., and Welti, T","venue":null,"work_id":"a5568ac0-59d3-414d-bb78-75fb3bde31c2","year":1911},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"cited_paper":"/paper/1911.03188","citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:ef053d7e09045da8e327a18681690710f848c7658f5e82dc6a1cc6bd4950495c","observation_id":"9ee605ea-3269-4541-aba7-b5435b5ad0aa","resolution":{"observed_at":"2026-05-24T06:54:03.258335Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Uniform er- ror estimates for artificial neural network approximations for heat equations.IMA J","venue":null,"work_id":"1522059a-52d5-469a-8757-d1442d5d754f","year":2022},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:2e67b59a68df518146ccbe3bfaba9370d159f0013da41766f4c7059ec9adb740","observation_id":"13fb871d-9dd4-4c74-ade9-06130936f408","resolution":{"observed_at":"2026-05-24T06:56:03.268235Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Deep ReLU network expression rates for option prices in high-dimensional, exponential Lévy models.Finance Stoch","venue":null,"work_id":"66fd9cf5-190e-47ac-abff-c8b2c7870988","year":2021},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:2dcd1e96e7608a88cf74ac2fd46ef08c33e34967556c3d8cab0eb4f09a06811b","observation_id":"ff149eb5-8ab5-4ab6-ba8d-b2f0144393bc","resolution":{"observed_at":"2026-05-24T06:56:03.319900Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.05744","last_updated":"2021-03-09T22:34:13Z","snapshot_observed_at":"2026-08-16T18:40:03.337586Z","submitted_at":"2021-03-09T22:34:13Z","title":"Deep neural network approximation for high-dimensional parabolic Hamilton-Jacobi-Bellman equations","version":1},"cited_work":{"arxiv_id":"2103.05744","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.05744","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Deep neural network approximation for high- dimensional parabolic Hamilton–Jacobi–Bellman equations.arXiv:2103.05744 (2021), 23 pages","venue":null,"work_id":"ad42789d-8da5-48b5-bb10-db43e84b896c","year":2021},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"cited_paper":"/paper/2103.05744","citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:1c29eafb7b21dd4a2b4a4e7379fb1270c3b926093f41fa7e747fca01429a12be","observation_id":"732bee12-2590-4455-8720-96586c9a40c6","resolution":{"observed_at":"2026-05-24T06:54:03.226439Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Deep neural network approximation for high- dimensional elliptic PDEs with boundary conditions.IMA J","venue":null,"work_id":"89c72458-5ce0-4b5a-a7e9-daae7dcbb581","year":2022},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:2acb4dfc0912eb4a03907f9591e1fc5fcc0e3918cdf528ff6c0dd9e2a3141987","observation_id":"5e22a2d8-b963-4987-bbfe-40b4ebbeedc8","resolution":{"observed_at":"2026-05-24T06:56:03.306809Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A proof that artificial neural networks overcome the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations.Mem","venue":null,"work_id":"e25c5bac-559a-47b6-a8fb-3be16fc90c64","year":2023},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:4c21df5c2f5b50eadd4a65a0bd4b50c0545e262c07adfa573315ba3b1ebbc480","observation_id":"a3f9914b-10bf-4807-918d-d248afc8a240","resolution":{"observed_at":"2026-05-24T06:56:03.310291Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Space-time er- ror estimates for deep neural network approximations for differential equations.Adv","venue":null,"work_id":"d8228e90-94c2-4ae4-86c3-e9dd2af9112c","year":2023},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:71f11b5d072a1c2cdbb343b8842cd67aa2450b357f71081991d916a6972af67a","observation_id":"bddd26ba-7528-4098-b910-a73b81a15770","resolution":{"observed_at":"2026-05-24T06:56:03.254277Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Deep neural network approximations for solutions of PDEs based on Monte Carlo algorithms.Partial Differ","venue":null,"work_id":"f63311e4-ff2e-403a-816e-6b3a9ca619d0","year":2022},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:d0f0eb84cc2f28671c68d13e17f60332004e7e3a06a279068a8fd7e3a760e36b","observation_id":"af590aa6-ebc0-41b5-8c64-178d452ef232","resolution":{"observed_at":"2026-05-24T06:56:03.250570Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Solving high-dimensional partial differential equa- tions using deep learning.Proc","venue":null,"work_id":"e8d96f00-ac4e-41bd-ad97-9d283d2c7f54","year":2018},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:6568de7d48cbde88d97ab132dfae6e46f07397d84a8878f078bc3ef2fb9deb1f","observation_id":"02315c04-9bdc-4a7d-a590-c0d2800c724a","resolution":{"observed_at":"2026-05-24T06:56:03.302461Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Convergence of the deep BSDE method for coupled FBSDEs","venue":null,"work_id":"27440464-7f97-44b4-a8a9-287cf6d6f1d3","year":2020},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:04a28dc1745edc06012513906f9a9a3d0bdd09dd2e95d631d0980902e26dffe7","observation_id":"82ed7122-a60d-45f4-8393-98402835fd2a","resolution":{"observed_at":"2026-05-24T06:56:03.314852Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Deep Primal-Dual Algorithm for BSDEs: Applications of Machine Learning to CVA and IM","venue":null,"work_id":"2f36b225-ba98-433a-b6af-9a91893f55a0","year":2017},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:f9fc0ac811217c88d5c22cd9248e5868148930a33e6741f66be32199fea0a4a6","observation_id":"5eedc035-eab1-419b-8a85-afb1afc61bbb","resolution":{"observed_at":"2026-05-24T06:56:03.247342Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A., and Johnson, C","venue":null,"work_id":"62ced1d6-2274-4676-91fb-39473b659d28","year":1985},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:26859a055c746cda7930b3ad8ca12b9431c39fb81244326ffd14d314bf254e7d","observation_id":"685dec29-1b67-4fef-8efc-d844fbff6c46","resolution":{"observed_at":"2026-05-24T06:56:03.243806Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.02199","last_updated":"2024-06-03T15:54:30Z","snapshot_observed_at":"2026-08-11T20:37:28.796256Z","submitted_at":"2020-06-03T12:14:56Z","title":"Space-time deep neural network approximations for high-dimensional partial differential equations","version":2},"cited_work":{"arxiv_id":"2006.02199","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2006.02199","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Space-time deep neu- ral network approximations for high-dimensional partial different ial equations","venue":null,"work_id":"a59fed08-c891-4830-ba8e-ed3ef0eff3d2","year":2006},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"cited_paper":"/paper/2006.02199","citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:1a1cd10c5c04c0a4a2e5be782250fc0a748f58d92b3b5985ae9a400b4867ca39","observation_id":"d26b59ab-4d13-4ceb-8771-96d4b418567e","resolution":{"observed_at":"2026-05-24T06:54:03.251931Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"00eb9abd-729c-4298-b3e6-d4fcb8ceff58","year":2024},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:bae942f022a97818a98233d3ec18ad59493d9ee8a93c9c2fb3d1545f34bdbe31","observation_id":"728722fa-5d33-4db4-9d91-468b19d94889","resolution":{"observed_at":"2026-05-24T06:56:03.240650Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Deep backward schemes for high-dimensional nonlinear PDEs","venue":null,"work_id":"34f95623-a526-4a60-bc0f-2e7c6bcf4181","year":2020},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:fedec2e2fbe5828ab1e605156090eee49881de8fa004791d8534506128dc1f87","observation_id":"f9248e8a-a7c6-4a62-9af7-fa96a2def5e3","resolution":{"observed_at":"2026-05-24T06:56:03.317922Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Overcoming the curse of dimen- sionality in the numerical approximation of parabolic partial differential equations with gradient-dependent nonlinearities.Found","venue":null,"work_id":"f856e8d5-ae5c-4353-b2ec-1f3c6c930307","year":2022},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:5c30f250f0a7215c2bfdafc0cff44a57a483cb2c66b8c18e91e3be1921cfc3db","observation_id":"13ed7b02-9ba8-4f5d-ace5-77b9b7691ac1","resolution":{"observed_at":"2026-05-24T06:56:03.313564Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2009.02484","last_updated":"2020-10-09T07:05:53Z","snapshot_observed_at":"2026-08-13T18:34:33.526597Z","submitted_at":"2020-09-05T07:37:37Z","title":"Multilevel Picard approximations for high-dimensional semilinear second-order PDEs with Lipschitz nonlinearities","version":4},"cited_work":{"arxiv_id":"2009.02484","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2009.02484","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Hutzenthaler, A","venue":null,"work_id":"a1b74422-6ad6-4120-9795-2c13efdcc6a8","year":2009},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"cited_paper":"/paper/2009.02484","citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:1e4755ab8936efc24df194e9792bcf08f8a9d5ca66fdd0cf56364d69755f69d0","observation_id":"20d56fa5-a80d-4b4e-80dd-cc387cf41bd4","resolution":{"observed_at":"2026-05-24T06:54:03.243985Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"3987995d-cd2d-426f-9378-614bda22decd","year":2020},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:d87a773e99f671fddd09fde7bcf9605ab59e912a101eba5aa49c9cf9edc3985d","observation_id":"6356b0a5-21bb-4b4b-8c6e-079467afbd04","resolution":{"observed_at":"2026-05-24T06:56:03.316738Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A., and von Wurstemberger, P","venue":null,"work_id":"297a70ce-99e8-4edd-adad-8c030242e9c9","year":2020},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:f170f7d66b42c120b28f8304090d0b644fa1033f718de77aa8e7ce9bfbceb579","observation_id":"aa98b937-d5bb-4e67-8fd1-1f93d936e477","resolution":{"observed_at":"2026-05-24T06:56:03.323802Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.08297","last_updated":"2021-10-15T18:07:51Z","snapshot_observed_at":"2026-08-20T01:41:07.647954Z","submitted_at":"2021-10-15T18:07:51Z","title":"Strong $L^p$-error analysis of nonlinear Monte Carlo approximations for high-dimensional semilinear partial differential equations","version":1},"cited_work":{"arxiv_id":"2110.08297","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.08297","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"cf4d5c92-48d4-49d9-a486-45bbad7103a8","year":2021},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"cited_paper":"/paper/2110.08297","citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:127c8fabf89b7a4741282360adc2a0d1ceed93e9a6f587d0be0f246e49af3413","observation_id":"eace4e74-ae99-4f35-982a-935508503166","resolution":{"observed_at":"2026-05-24T06:54:03.238604Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Overcoming the curse of dimensionality in the approximative pricing of financial derivatives with default risks","venue":null,"work_id":"5e6ebcec-85ce-45f8-a019-a31786db2572","year":2020},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:91c39931b8fbf0ff93c72f9a6d1ab3a22fc74dbd871ca2a6f929210353eba3c8","observation_id":"b5b95684-9925-4c12-9423-2a835778410c","resolution":{"observed_at":"2026-05-24T06:56:03.322336Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Multilevel Picard approximations of high- dimensional semilinear parabolic differential equations with gradient-dependent nonlin- earities","venue":null,"work_id":"f6831f27-170b-4a12-8c92-03fee15f487f","year":2020},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:74271693853f09115cb2aae4339e0d0e5c0d98fe577da860ba4aa739a1bd19f6","observation_id":"fd6904cc-0954-4b0e-a459-9b604b7ac7b7","resolution":{"observed_at":"2026-05-24T06:56:03.303722Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"13c35bc8-28e9-4084-9ec2-187d71b577a7","year":2022},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:0e98d1dd755ee29bbdaf8b46fd091a889170911665c3c3ba60b44fa1ef5654b4","observation_id":"e728731a-68d7-4bda-be16-64d014f0423c","resolution":{"observed_at":"2026-05-24T06:56:03.290373Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"64c9d7f1-117b-461d-a0bd-30f6242b7471","year":2022},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:170515ef08f0032f08d687f1fb4e7e25a669938192441ebf1cf5a27945531da8","observation_id":"f70498a3-7252-459b-8795-bd7ae2697ccf","resolution":{"observed_at":"2026-05-24T06:56:03.279125Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Deep curve-dependent PDEs for affine rough volatility","venue":null,"work_id":"4b73a785-fb21-4331-ab9a-2343f2b3c81b","year":2023},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:87d1e4e7f137b165e36619f429fcc5d9fa99c875445cd7f90c6d7634cb3329fc","observation_id":"434b9057-b140-4613-a134-cf55a1b607ac","resolution":{"observed_at":"2026-05-24T06:56:03.283520Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"f546b1aa-e3a5-4027-8c23-ce33e9268ee9","year":2021},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:896c56c2cb64b54644cfb38a44a0fe3e1a9385f97326f88e06a25a5f3dcdefa8","observation_id":"a1a753d4-fcf7-4266-869e-9a1c55c3b050","resolution":{"observed_at":"2026-05-24T06:56:03.286997Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A theoretical analysis of deep neural networks and parametric PDEs.Constr","venue":null,"work_id":"54f44a5f-ae67-4aaa-b30c-b1c76d562601","year":2022},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:e5f753ead5bea7e2d065872eb8a333f1c0381abdf3661dcf6eb14dc170be657d","observation_id":"cf695a88-91b7-4de9-b078-ce789e8289d6","resolution":{"observed_at":"2026-05-24T06:56:03.293593Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.09639","last_updated":"2025-03-12T06:29:26Z","snapshot_observed_at":"2026-08-16T16:59:08.779531Z","submitted_at":"2022-05-19T16:00:34Z","title":"Multilevel Picard approximation algorithm for semilinear partial integro-differential equations and its complexity analysis","version":5},"cited_work":{"arxiv_id":"2205.09639","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2205.09639","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Multilevel Picard approximation algorithm for semilin- ear partial integro-differential equations and its complexity analysis.arXiv:2205.09639 (2022), 54 pages","venue":null,"work_id":"0c4d3506-7470-44f5-9f2e-c19ed8ef2eae","year":2022},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"cited_paper":"/paper/2205.09639","citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:22196e06f61d5a3ac254c77932bbef10af102176e6bf960aa5c2a9e57c72397a","observation_id":"a355d947-47dd-4a44-98de-d73896b39ec8","resolution":{"observed_at":"2026-05-24T06:54:03.231855Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Tractability of multivariate problems","venue":null,"work_id":"3141049d-d35a-4ed9-b344-81ec1d84a9e5","year":2008},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:6e3a0aaba43b0ed735179381aa86b8b60a27feca82a0c278cb0e1971f25d81c9","observation_id":"03a149fc-dd4f-4f1f-b425-6a3a001be7b2","resolution":{"observed_at":"2026-05-24T06:56:03.263274Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Solving high-dimensional Hamilton-Jacobi-Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space.Partial Differ","venue":null,"work_id":"2323a357-831e-4330-beaf-3de2665cc963","year":2021},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:5a17f44c04f659e6d40fd22de998c2af9f5699225d4fa733c38380684dfa3d8e","observation_id":"507ff436-6b58-42a4-8ebe-89fd9705ca07","resolution":{"observed_at":"2026-05-24T06:56:03.325447Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Neural networks-based backward scheme for fully nonlinear PDEs.Partial Differ","venue":null,"work_id":"aeb408b8-3e4d-4724-b1cd-0b2ca4939384","year":2021},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:2b9fcb2f36cda73312b3aa28b6ee3334f596a6ba2d21ebfdeb38f8f75820de34","observation_id":"e0be56ad-a825-4c89-beef-8aac84dbf18e","resolution":{"observed_at":"2026-05-24T06:56:03.275814Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"19ac340d-6852-4871-b4df-75bb08d8e787","year":2019},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:2b4746876da7fb46ff66ff236b11720168f42c9462b3527c60e2127c75e01173","observation_id":"b17ea97d-d7da-438f-9bdf-8a750660918c","resolution":{"observed_at":"2026-05-24T06:56:03.259701Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Rectified deep neural networks overcome the curse of dimensionality for nonsmooth value functions in zero-sum games of nonlinear stiff systems","venue":null,"work_id":"c04ae6e4-a94c-4efa-9863-f80beb780221","year":2020},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:2e7e2588eec0d63f916dbdb60d7b92774fa50fad0fef1685ae10775604d4a71b","observation_id":"f88682f1-f373-446a-b3e7-60428147c603","resolution":{"observed_at":"2026-05-24T06:56:03.247833Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"91b81c96-2540-416d-9ae5-7e7dc086e59e","year":2007},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:cd54997d5fdb186cd03b12ce656940d1678ed2a4fb2772229a015f19ea142543","observation_id":"673d7559-51fd-4e46-9669-5f463e01535b","resolution":{"observed_at":"2026-05-24T06:56:03.328241Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"DGM: A deep learning algorithm for solving partial differential equations.J","venue":null,"work_id":"63d92323-9c58-48f3-ba8e-456582af0833","year":2018},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:9528034fc31a9f540b8bf3bb77d5ef02a06566877dd6644d58a61ac0f039536b","observation_id":"1f6a2ab4-af12-465d-af74-b4f5df3cc84d","resolution":{"observed_at":"2026-05-24T06:56:03.255917Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Towards fast weak adversarial trainingtosolvehighdimensionalparabolicpartialdifferentialequationsusingXNODE- WAN","venue":null,"work_id":"6d75cc87-cc58-4ec2-bce6-679ae4ca04dc","year":2022},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:c24020501c159def318c5c2b99f667df712d502740fc8c62320c8bf65012071d","observation_id":"9d5e325e-b928-413d-8b42-6ee3ad0ddb44","resolution":{"observed_at":"2026-05-24T06:56:03.271764Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Weak adversarial networks for high- dimensional partial differential equations.J","venue":null,"work_id":"4357f679-3ccd-4b38-9c0a-4a993369caee","year":2020},"citing_paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense","version":3},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-05-24T06:52:12.821942Z"},"links":{"citing_paper":"/paper/2309.13722"},"observation_digest":"sha256:5fdd153ae57d6206ec0589b4a77219e9595c3755b627aede1c3bdb4026fa2504","observation_id":"a4a17e5f-6103-4420-9316-d020d8d463b3","resolution":{"observed_at":"2026-05-24T06:56:03.300523Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2309.13722","last_updated":"2026-04-28T23:18:52Z","latest_version":3,"primary_category":"math.NA","snapshot_observed_at":"2026-08-18T00:07:50.307470Z","submitted_at":"2023-09-24T18:58:18Z","title":"Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense"},"reference_resolution":{"displayed":65,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":11,"verified_exact":8,"verified_fuzzy":46},"total_outbound_references":65},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 65 of 65 outbound references and 2 inbound Pith citation observations for arXiv:2309.13722."}