{"as_of":"2026-08-15T12:54:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f709a28fa9b45b99f246e163169be6e2e02f67f480bbaaf750330c9090fc21a2","coverage":[{"denominator":37,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":37,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T14:10:00.029939Z","state":"measured"},{"denominator":39,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":39,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+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":"2026-08-14T10:39:29.571077Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-24T12:39:29.035712Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.03833","snapshot_observed_at":"2026-08-14T10:39:29.571077Z","title":"Space- time error estimates for deep neural network approximations for differential equations","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"1908.10828","last_updated":"2019-08-28T16:57:17Z","snapshot_observed_at":"2026-08-15T05:18:37.792251Z","submitted_at":"2019-08-28T16:57:17Z","title":"Deep neural network approximations for Monte Carlo algorithms","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T10:39:29.571077Z"},"links":{"cited_paper":"/paper/1908.03833","citing_paper":"/paper/1908.10828"},"observation_digest":"sha256:a9a02ee9239b077d8b810882ae2c1cf40f8db0d3803a5701465e45b0148005b4","observation_id":"21c3664a-7cdf-4956-bdf0-bc9fe3e66a91","resolution":{"observed_at":"2026-08-14T10:39:29.571077Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"cited_work":{"arxiv_id":"1908.03833","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1908.03833","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Space-time error estimates for deep neural network approximations for diffe rential equations","venue":null,"work_id":"8065d10f-98ac-468f-ae83-f3138d930d41","year":1908},"citing_paper":{"arxiv_id":"2112.14523","last_updated":"2026-04-28T23:07:38Z","snapshot_observed_at":"2026-07-06T12:23:15.205001Z","submitted_at":"2021-12-29T12:29:23Z","title":"Deep neural network approximation theory for high-dimensional functions","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-24T12:37:24.021894Z"},"links":{"cited_paper":"/paper/1908.03833","citing_paper":"/paper/2112.14523"},"observation_digest":"sha256:8bad30de0b340b206f431efb06ec18b92a3f4b5c6e8687f9a19dea988d0626e0","observation_id":"e0a8488b-f832-452c-87c2-8b86076f848d","resolution":{"observed_at":"2026-05-24T12:39:29.039070Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/1908.03833/citation-record","integrity":"/paper/1908.03833/integrity","json":"/paper/1908.03833/citation-record.json","paper":"/paper/1908.03833"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1907.03452","last_updated":"2021-06-21T15:36:53Z","snapshot_observed_at":"2026-08-15T04:52:59.296591Z","submitted_at":"2019-07-08T08:30:23Z","title":"Deep splitting method for parabolic PDEs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.03452","snapshot_observed_at":"2026-08-14T14:09:59.823238Z","title":"Deep splitting method for parabolic PDEs","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.823238Z"},"links":{"cited_paper":"/paper/1907.03452","citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:0ab0f70c4d9db85449e7ba93f83b2d951033e386c19349952c8f94d089d3abbe","observation_id":"4d2e7726-f2c8-4bd4-b380-96d12127716b","resolution":{"observed_at":"2026-08-14T14:09:59.823238Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1806.00421","last_updated":"2021-07-14T15:26:22Z","snapshot_observed_at":"2026-08-15T07:25:26.798479Z","submitted_at":"2018-06-01T16:18:57Z","title":"Solving the Kolmogorov PDE by means of deep learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.00421","snapshot_observed_at":"2026-08-14T14:09:59.829545Z","title":"Solving stochastic differential equations and Kolmogorov equations by means of deep learning","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.829545Z"},"links":{"cited_paper":"/paper/1806.00421","citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:0803879ea29225506a528791f27221f679619deb92c59976cc2b645c8ec849fd","observation_id":"aa5397f1-36ce-4dd3-a889-85795953e213","resolution":{"observed_at":"2026-08-14T14:09:59.829545Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:09:59.835634Z","title":"Machine Learning Approximation Algorithms for High-Dimensional Fully Nonlinear Partial Differential Eq ua- tions and Second-order Backward Stochastic Differential Equatio ns","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.835634Z"},"links":{"citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:195676b9376462b981cda11d53005f012cd99b4eb6d1719eb2b67faf92542e17","observation_id":"fde555e0-4a45-4553-84fe-2b7c5e4989cc","resolution":{"observed_at":"2026-08-14T14:09:59.835634Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:09:59.841521Z","title":"Deep Optimal Stopping","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.841521Z"},"links":{"citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:accd7986db2088c28bb7dab5d54bfa7fa6932c50ed6644233a3723dfbd21e822","observation_id":"0b590230-77e0-4372-a048-47ec34ebe864","resolution":{"observed_at":"2026-08-14T14:09:59.841521Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.01602","last_updated":"2021-08-08T22:09:32Z","snapshot_observed_at":"2026-08-14T15:05:56.565562Z","submitted_at":"2019-08-05T13:11:28Z","title":"Solving high-dimensional optimal stopping problems using deep learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.01602","snapshot_observed_at":"2026-08-14T14:09:59.848604Z","title":"Solving high- dimensional optimal stopping problems using deep learning","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.848604Z"},"links":{"cited_paper":"/paper/1908.01602","citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:0860ec58146c3527e671dd23e4f5bd7a372f80585edca7ce253dbc2033e7a6de","observation_id":"e6b167d0-910c-4a88-92a0-56f2c274d66a","resolution":{"observed_at":"2026-08-14T14:09:59.848604Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:09:59.853975Z","title":"A unified deep artificial neural network ap- proach to partial differential equations in complex geometries","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.853975Z"},"links":{"citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:46d5119a8aff97b028873062941aaf7c2ef028890950d1152db35232eeac1839","observation_id":"12f664d7-5278-40e0-8888-ff3b5a114dcc","resolution":{"observed_at":"2026-08-14T14:09:59.853975Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1809.03062","last_updated":"2020-11-11T12:46:12Z","snapshot_observed_at":"2026-08-14T18:30:58.375718Z","submitted_at":"2018-09-09T23:50:37Z","title":"Analysis of the Generalization Error: Empirical Risk Minimization over Deep Artificial Neural Networks Overcomes the Curse of Dimensionality in the Numerical Approximation of Black-Scholes Partial Differential Equations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.03062","snapshot_observed_at":"2026-08-14T14:09:59.860563Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.860563Z"},"links":{"cited_paper":"/paper/1809.03062","citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:1562018ef67fca40497d7ded4742779e776b208f925539fbcb9625e0c178e812","observation_id":"7e3a4ad6-049e-4597-a8f6-77d7bb36312c","resolution":{"observed_at":"2026-08-14T14:09:59.860563Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1007/s10915-019-00908-3","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:10:00.155738Z","title":"Machine Learning for Semi Linear PDEs","venue":null,"work_id":"73f44804-ac61-4081-a044-0eb692f7068d","year":2019},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.866402Z"},"links":{"citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:585e62c6d324a61813250f38a295398fe8efedc800eb7a2cfc094a9fe0fb4b97","observation_id":"9f4e3622-17d3-4b1e-8953-7950a8d5ff0b","resolution":{"observed_at":"2026-08-14T14:10:00.162898Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:09:59.871791Z","title":"Deep Learning-Based Numerical Meth- ods for High-Dimensional Parabolic Partial Differential Equations an d Back- ward Stochastic Differential Equations","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.871791Z"},"links":{"citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:1193c0128131bed2e8bc9c673575156b7d28cb9bd9a286d2a6c872410b26dfc5","observation_id":"b7695792-b12d-44f7-a586-7d222c0ffaaa","resolution":{"observed_at":"2026-08-14T14:09:59.871791Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.00211","last_updated":"2017-09-30T15:06:14Z","snapshot_observed_at":"2026-08-14T20:28:05.435732Z","submitted_at":"2017-09-30T15:06:14Z","title":"The Deep Ritz method: A deep learning-based numerical algorithm for solving variational problems","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.00211","snapshot_observed_at":"2026-08-14T14:09:59.877416Z","title":"The deep Ritz method: A deep learning-based numer- ical algorithm for solving variational problems","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.877416Z"},"links":{"cited_paper":"/paper/1710.00211","citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:df72d096777a808ae7c968f52ad1dfbee79e939b3bdd12d74c68fd58961b7166","observation_id":"fd70ed99-5f3c-4518-9af5-e7b6c3b8a1b1","resolution":{"observed_at":"2026-08-14T14:09:59.877416Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1809.07669","last_updated":"2020-11-03T14:24:52Z","snapshot_observed_at":"2026-08-14T18:25:48.310420Z","submitted_at":"2018-09-20T15:17:27Z","title":"DNN Expression Rate Analysis of High-dimensional PDEs: Application to Option Pricing","version":3},"cited_work":{"arxiv_id":"1809.07669","doi":null,"metadata_source":"pith","pith_arxiv_id":"1809.07669","snapshot_observed_at":"2026-08-14T14:10:00.754060Z","title":"DNN Expression Rate Analysis of High-dimensional PDEs: Application to Option Pricing","venue":"math.FA","work_id":"cddd0644-ea88-49f6-aa8b-819fff707f9c","year":2018},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.882615Z"},"links":{"cited_paper":"/paper/1809.07669","citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:79b203f386b8b54c75358169ae1ff4ac1fbcfcbbc1730df670fe5f8626fe1b39","observation_id":"beeafcd8-48f3-41b3-805c-5b7083ac30d2","resolution":{"observed_at":"2026-08-14T14:10:00.759971Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2017.79634","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:10:00.725107Z","title":null,"venue":null,"work_id":"3feba7e8-1535-4481-bb5c-220bd8ce65a5","year":2017},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.888285Z"},"links":{"citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:7ab4b12055d9d393d59229c04ee674d9c390c604c0d9e025fd5e06fd61fc67eb","observation_id":"cb99c212-3e76-4980-a154-a408b8b289ad","resolution":{"observed_at":"2026-08-14T14:10:00.735112Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1007/s10690-019-09271-7","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:10:00.114643Z","title":"Asymptotic Expansion as Prior Knowledge in Deep Learning Method for High dimensional BSDE s","venue":null,"work_id":"19a3d435-f42b-48ba-8f1a-3ebc7f567d9c","year":2019},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.893469Z"},"links":{"citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:a45325b952e7fd7a060c3a735bf4bc9cb77acfd86eab248e4914d1b41eaeeaff","observation_id":"25165fdd-16d1-48c7-81b5-ecf775ddecf7","resolution":{"observed_at":"2026-08-14T14:10:00.123894Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:09:59.898831Z","title":"Deep Learning","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.898831Z"},"links":{"citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:a98c92e8d5df14eaa6c948ea14722947109ffbeebc97e5969ac7fbccda85432a","observation_id":"f7204106-cc32-491d-82ad-25e3ed531493","resolution":{"observed_at":"2026-08-14T14:09:59.898831Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.11275","last_updated":"2019-12-02T21:51:11Z","snapshot_observed_at":"2026-08-14T16:56:10.724749Z","submitted_at":"2019-03-27T07:33:35Z","title":"Variance Reduction Applied to Machine Learning for Pricing Bermudan/American Options in High Dimension","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.11275","snapshot_observed_at":"2026-08-14T14:09:59.904352Z","title":"Machine Learning for Pricing American Options in High Dimension","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.904352Z"},"links":{"cited_paper":"/paper/1903.11275","citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:e07b655642c1740cae70c02c28ff736c54b8f6e6df39bd4c1a8ebe1cf518f27a","observation_id":"22cf2e73-b51e-410a-b343-41ff2b915788","resolution":{"observed_at":"2026-08-14T14:09:59.904352Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1809.02362","last_updated":"2023-01-26T04:45:04Z","snapshot_observed_at":"2026-08-14T18:31:46.067147Z","submitted_at":"2018-09-07T09:03:55Z","title":"A proof that artificial neural networks overcome the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.02362","snapshot_observed_at":"2026-08-14T14:09:59.910253Z","title":"A proof that artificial neural networks overcome the curse of dim ensionality in the numerical approximation of Black-Scholes partial differential e quations","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.910253Z"},"links":{"cited_paper":"/paper/1809.02362","citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:1c662950077243827bff12044cc24bd5e5ae7a7cf9eaf58a6137d25c10e3d0c2","observation_id":"a271a83e-d74a-468d-9aa4-a1c388a39348","resolution":{"observed_at":"2026-08-14T14:09:59.910253Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1901.02220","last_updated":"2021-03-12T13:59:26Z","snapshot_observed_at":"2026-08-14T17:33:51.975771Z","submitted_at":"2019-01-08T09:41:27Z","title":"Deep Neural Network Approximation Theory","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1901.02220","snapshot_observed_at":"2026-08-14T14:09:59.916447Z","title":"Deep Neural Network Approximation Theory","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.916447Z"},"links":{"cited_paper":"/paper/1901.02220","citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:c4a24f9f10e0c06bd43f5aed4385761143c74e9e31a206862c3a43256e9a6cb4","observation_id":"b16a480f-bc18-4651-b627-d42ba730c92b","resolution":{"observed_at":"2026-08-14T14:09:59.916447Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:09:59.921766Z","title":"Solving high-dimensional partial differ- ential equations using deep learning","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.921766Z"},"links":{"citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:a465b792f582354aaf071e65bf2931cad5ea45c9c2780a4124f50f273cf50dd0","observation_id":"31c60b9c-1ad4-450f-805b-824e218738aa","resolution":{"observed_at":"2026-08-14T14:09:59.921766Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1811.01165","last_updated":"2022-03-08T22:12:04Z","snapshot_observed_at":"2026-08-14T18:04:51.274748Z","submitted_at":"2018-11-03T06:08:23Z","title":"Convergence of the Deep BSDE Method for Coupled FBSDEs","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.01165","snapshot_observed_at":"2026-08-14T14:09:59.926595Z","title":"Convergence of the deep BSDE method for coupled FBSDEs","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.926595Z"},"links":{"cited_paper":"/paper/1811.01165","citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:9a24817d008c3a20c785de13a29aae0def8aa9c399872d18dbc920f5382683f5","observation_id":"d578caad-4fb0-43ad-93fc-625d9e727f51","resolution":{"observed_at":"2026-08-14T14:09:59.926595Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:10:00.878627Z","title":"Deep Primal-Dual Algorithm for BSDEs: Appli- cations of Machine Learning to CV A and IM","venue":null,"work_id":"f52d219b-c6b1-44b0-b875-3b98073db7b7","year":2017},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.931845Z"},"links":{"citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:7584f7824aa25d029d6a20c49656bdb390853c65dc421bd092a89ec34e221abf","observation_id":"4482d8b5-fa44-4cca-a737-6b0c052d0c9b","resolution":{"observed_at":"2026-08-14T14:10:00.884036Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:09:59.937359Z","title":"Some machine learning schemes for high-dimensional nonlinear PDEs","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.937359Z"},"links":{"citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:411957494cd5af64426be5b1fd3e04ab895362b5d29ee0539daa16930877e27c","observation_id":"4e5d8bcd-2501-4d33-b081-4e1270b7e67c","resolution":{"observed_at":"2026-08-14T14:09:59.937359Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1901.10854","last_updated":"2019-07-14T07:01:49Z","snapshot_observed_at":"2026-08-14T17:23:38.249895Z","submitted_at":"2019-01-30T14:37:35Z","title":"A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1901.10854","snapshot_observed_at":"2026-08-14T14:09:59.942163Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.942163Z"},"links":{"cited_paper":"/paper/1901.10854","citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:cddc8b955a0c039a5a960f4ca0a00e66346843e5ab16f1062703b2304cacf783","observation_id":"1ebe2c1d-4547-40e5-999f-9801a039a1ac","resolution":{"observed_at":"2026-08-14T14:09:59.942163Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.05985","last_updated":"2019-03-14T13:31:10Z","snapshot_observed_at":"2026-08-14T17:02:19.538223Z","submitted_at":"2019-03-14T13:31:10Z","title":"Overcoming the curse of dimensionality in the approximative pricing of financial derivatives with default risks","version":1},"cited_work":{"arxiv_id":"1903.05985","doi":null,"metadata_source":"pith","pith_arxiv_id":"1903.05985","snapshot_observed_at":"2026-08-14T14:10:00.490251Z","title":"Overcoming the curse of dimensionality in the approximative pricing of financial derivatives with default risks","venue":"math.NA","work_id":"0489b886-c781-49c9-9787-3ba0f0b6f672","year":2019},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.947177Z"},"links":{"cited_paper":"/paper/1903.05985","citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:b8c60ce763d0eb2c30788d045ff36ddd8e0b4a0b1874493dd1b4dc8054abb0ad","observation_id":"0397eebb-1a8a-4abe-8ed3-8c1ce9e2ec56","resolution":{"observed_at":"2026-08-14T14:10:00.496983Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1906.02551","last_updated":"2023-01-03T15:28:21Z","snapshot_observed_at":"2026-08-14T16:19:52.835372Z","submitted_at":"2019-06-06T12:36:59Z","title":"Deep Curve-dependent PDEs for affine rough volatility","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.02551","snapshot_observed_at":"2026-08-14T14:09:59.952838Z","title":"Deep PPDEs for rough local stochastic volatility","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.952838Z"},"links":{"cited_paper":"/paper/1906.02551","citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:b420b5e7060263520cc0a44b1948394a08484c814dd54e157ffae9e0376b3ebd","observation_id":"86ef2b73-57f4-409a-8b7d-1773c3df2f8e","resolution":{"observed_at":"2026-08-14T14:09:59.952838Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1809.07321","last_updated":"2019-09-23T14:25:33Z","snapshot_observed_at":"2026-08-14T18:26:13.210187Z","submitted_at":"2018-09-19T17:56:40Z","title":"A proof that deep artificial neural networks overcome the curse of dimensionality in the numerical approximation of Kolmogorov partial differential equations with constant diffusion and nonlinear drift coefficients","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.07321","snapshot_observed_at":"2026-08-14T14:09:59.958638Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.958638Z"},"links":{"cited_paper":"/paper/1809.07321","citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:5bfd08c633c3db8cfb11b1e18d4f6267ea56ff83fb9c1818e0143edeeded6292","observation_id":"32bf5e20-1e7c-42cd-9e2e-784c96337a12","resolution":{"observed_at":"2026-08-14T14:09:59.958638Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1904.00377","last_updated":"2020-05-14T12:34:55Z","snapshot_observed_at":"2026-08-14T16:54:09.340261Z","submitted_at":"2019-03-31T10:51:16Z","title":"A Theoretical Analysis of Deep Neural Networks and Parametric PDEs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.00377","snapshot_observed_at":"2026-08-14T14:09:59.963773Z","title":"A theoretical analysis of deep neural networks and parametric PD Es","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.963773Z"},"links":{"cited_paper":"/paper/1904.00377","citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:c27d40cee7ed7e35f0579f71cb85806d629c5b8c5aa939b1e33e9ee5f97e869c","observation_id":"6700ef96-9487-4d65-a60c-c777af57e341","resolution":{"observed_at":"2026-08-14T14:09:59.963773Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.05858","last_updated":"2019-11-03T00:26:43Z","snapshot_observed_at":"2026-08-14T17:02:28.427714Z","submitted_at":"2019-03-14T08:45:13Z","title":"Better Approximations of High Dimensional Smooth Functions by Deep Neural Networks with Rectified Power Units","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.05858","snapshot_observed_at":"2026-08-14T14:09:59.969053Z","title":"Better Approximations of High Di- mensional Smooth Functions by Deep Neural Networks with Rectifie d Power Units","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.969053Z"},"links":{"cited_paper":"/paper/1903.05858","citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:d6db7668edf96d9297abbd251cc67c2e273f2df9bf4b065e441e0fe02d3c6905","observation_id":"4669c1f1-3330-49d9-90c2-4fc8cc3b38f3","resolution":{"observed_at":"2026-08-14T14:09:59.969053Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.09668","last_updated":"2018-01-01T07:22:36Z","snapshot_observed_at":"2026-08-14T20:20:02.981085Z","submitted_at":"2017-10-26T12:50:45Z","title":"PDE-Net: Learning PDEs from Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.09668","snapshot_observed_at":"2026-08-14T14:09:59.974502Z","title":"PDE-Net: Learning PDEs from Data","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.974502Z"},"links":{"cited_paper":"/paper/1710.09668","citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:1753650c76e6c4833f8e47e2cd7cd8a80d9eb1f5974f3df27d6389d2b718f8d9","observation_id":"95c60763-9630-49a5-a9e9-38de4e7fe3ce","resolution":{"observed_at":"2026-08-14T14:09:59.974502Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.03040","last_updated":"2019-12-16T09:31:28Z","snapshot_observed_at":"2026-08-14T17:05:47.705561Z","submitted_at":"2019-03-07T16:57:52Z","title":"Deep learning observables in computational fluid dynamics","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.03040","snapshot_observed_at":"2026-08-14T14:09:59.980469Z","title":"O., Mishra, S., and Ray, D","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.980469Z"},"links":{"cited_paper":"/paper/1903.03040","citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:858bc4ab4df0d470a38669a91379bd9cfd253181528721e4adfd1b3f02c4056f","observation_id":"2c192648-04f5-49c6-bb1d-1cb2296b23de","resolution":{"observed_at":"2026-08-14T14:09:59.980469Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:10:00.860498Z","title":"Neural Networks Trained to Solve Differential Equations Learn General Representations","venue":null,"work_id":"6bea6b9f-11f1-478d-a001-b2de7508040a","year":2018},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.985816Z"},"links":{"citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:ff654da22f92f355721d2faed3392607cdae9b924ab96a5e84e249cf3dabb6ee","observation_id":"1bd0c10a-66f5-4341-ae21-9ba4f343654d","resolution":{"observed_at":"2026-08-14T14:10:00.865808Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1806.08459","last_updated":"2020-01-23T18:12:05Z","snapshot_observed_at":"2026-08-14T19:00:44.530726Z","submitted_at":"2018-06-22T00:30:51Z","title":"Topological properties of the set of functions generated by neural networks of fixed size","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.08459","snapshot_observed_at":"2026-08-14T14:09:59.990514Z","title":"Topological prop- erties of the set of functions generated by neural networks of fi xed size","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.990514Z"},"links":{"cited_paper":"/paper/1806.08459","citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:01b5a492225ba892d7e243dc6f16abc5d4a2bebebcc3fac1ac1b30cb2c440cda","observation_id":"b27f6a0f-bf3a-4d6d-8b56-a1f1540142f7","resolution":{"observed_at":"2026-08-14T14:09:59.990514Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1709.05289","last_updated":"2018-05-22T11:24:29Z","snapshot_observed_at":"2026-08-14T20:32:45.758427Z","submitted_at":"2017-09-15T16:14:39Z","title":"Optimal approximation of piecewise smooth functions using deep ReLU neural networks","version":4},"cited_work":{"arxiv_id":"1709.05289","doi":null,"metadata_source":"pith","pith_arxiv_id":"1709.05289","snapshot_observed_at":"2026-08-14T14:10:00.343821Z","title":"Optimal approximation of piecewise smooth functions using deep ReLU neural networks","venue":"math.FA","work_id":"a5eac859-dcfc-4821-8ecd-8c6a85a68c6e","year":2017},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-14T14:09:59.996153Z"},"links":{"cited_paper":"/paper/1709.05289","citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:23cd917352acb6d0c1a798c1c960ffb0295612d647de97e6839e76aa8607a5d4","observation_id":"02a6a453-3f17-4410-8907-6b57f631684c","resolution":{"observed_at":"2026-08-14T14:10:00.349717Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:10:00.001705Z","title":"Neural networks-based backward scheme for fully nonlinear PDEs","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:00.001705Z"},"links":{"citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:1106f2d3452c18f15ddd888a294034ad4275a8440a4986aad7a5d586818197c7","observation_id":"a7b0f207-d5c7-49f7-bfab-6c4993bab670","resolution":{"observed_at":"2026-08-14T14:10:00.001705Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1801.06637","last_updated":"2018-01-20T08:02:09Z","snapshot_observed_at":"2026-08-14T19:53:36.356147Z","submitted_at":"2018-01-20T08:02:09Z","title":"Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1801.06637","snapshot_observed_at":"2026-08-14T14:10:00.009474Z","title":"Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:00.009474Z"},"links":{"cited_paper":"/paper/1801.06637","citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:0ff6af158cdd384529a740afd0b1c604b58afec0b59ae47e9cf73ff8540ecc54","observation_id":"defd40a7-bd4d-4338-afef-65c171a3af1e","resolution":{"observed_at":"2026-08-14T14:10:00.009474Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.06652","last_updated":"2020-05-13T11:06:33Z","snapshot_observed_at":"2026-08-14T17:01:37.894482Z","submitted_at":"2019-03-15T16:42:52Z","title":"Rectified deep neural networks overcome the curse of dimensionality for nonsmooth value functions in zero-sum games of nonlinear stiff systems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.06652","snapshot_observed_at":"2026-08-14T14:10:00.015724Z","title":"Rectified deep neural networks overcome the curse of dimensionality for nonsmooth value functions in zero-s um games of nonlinear stiff systems","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:00.015724Z"},"links":{"cited_paper":"/paper/1903.06652","citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:f85f66a2d0295d54ca8ca56a60a3947ff87c25a6adb2c54b8fba0d7af8f0c0cc","observation_id":"64c46afe-3e9c-44ac-8824-ea715c91c775","resolution":{"observed_at":"2026-08-14T14:10:00.015724Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:10:00.022951Z","title":"DGM: A deep learning algorithm for solving partial differential equations","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:00.022951Z"},"links":{"citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:46570284ce9f88d9602d6deac167a0e1705ad529240ad203d1f88977350fb356","observation_id":"86ea9583-7005-47f9-bdf8-9bd9082bf7e5","resolution":{"observed_at":"2026-08-14T14:10:00.022951Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:10:00.029939Z","title":"Error bounds for approximations with deep ReLU networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:00.029939Z"},"links":{"citing_paper":"/paper/1908.03833"},"observation_digest":"sha256:e44757a6114a3d2c4270d537cd49def8764825cffa638092c850f6c15e2779de","observation_id":"0e7c5bfd-1a0b-4d02-b608-a57217f26a22","resolution":{"observed_at":"2026-08-14T14:10:00.029939Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"1908.03833","last_updated":"2019-08-11T00:40:43Z","latest_version":1,"primary_category":"math.NA","snapshot_observed_at":"2026-08-15T03:21:22.751656Z","submitted_at":"2019-08-11T00:40:43Z","title":"Space-time error estimates for deep neural network approximations for differential equations"},"reference_resolution":{"displayed":37,"state_counts":{"malformed_identifier":1,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":28,"verified_exact":5,"verified_fuzzy":2},"total_outbound_references":37},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 2 inbound Pith citation observations for arXiv:1908.03833."}