{"as_of":"2026-08-08T13:49:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2bfed66bb07adf103e38bddcc909b803702eeca31ed3ab8df8ec985254d53834","coverage":[{"denominator":54,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":54,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T14:51:24.498177Z","state":"measured"},{"denominator":55,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":55,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-09T19:35:31.236089Z","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":"2026-05-11T15:36:08.139823Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"cited_work":{"arxiv_id":"2505.17751","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.17751","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Computational Math with Neural Networks is Hard","venue":null,"work_id":"49ecf2be-3dce-47cd-8a3a-c88508273a2c","year":2025},"citing_paper":{"arxiv_id":"2605.00308","last_updated":"2026-05-01T00:40:07Z","snapshot_observed_at":"2026-08-04T14:44:05.344744Z","submitted_at":"2026-05-01T00:40:07Z","title":"Adaptive anisotropic composite quadratures for residual minimisation in neural PDE approximations","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-09T19:35:31.236089Z"},"links":{"cited_paper":"/paper/2505.17751","citing_paper":"/paper/2605.00308"},"observation_digest":"sha256:79cae72ab47db2a350ac24319fd594d0055f80ead0049956771ce46448340ca0","observation_id":"aaf84f3c-6cc6-4dc2-8706-dcf73216b0a2","resolution":{"observed_at":"2026-05-11T15:36:08.149796Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2505.17751/citation-record","integrity":"/paper/2505.17751/integrity","json":"/paper/2505.17751/citation-record.json","paper":"/paper/2505.17751"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2309.15325","last_updated":"2024-01-04T20:38:03Z","snapshot_observed_at":"2026-08-02T00:36:56.846412Z","submitted_at":"2023-09-27T00:12:07Z","title":"Neural Operators for Accelerating Scientific Simulations and Design","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.15325","snapshot_observed_at":"2026-08-07T14:51:20.129523Z","title":"Azizzadenesheli, N","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:20.129523Z"},"links":{"cited_paper":"/paper/2309.15325","citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:169dcec54bee4465be5bf90b39bd92653628fc06992c2629c00b199d8019812d","observation_id":"69b391a1-4646-4e13-b9c2-e66c0c843cc8","resolution":{"observed_at":"2026-08-07T14:51:20.129523Z","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/bfb0090058","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:51:27.290158Z","title":"Volumes of sections of cubes and related problems","venue":null,"work_id":"ec95004d-fe0e-4041-9741-68908afb785f","year":1987},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:20.224744Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:dcc983d9deb7dee7f70189b6c5f0e3fc982ed97bf2fd187f01e4b9c19e6a82b9","observation_id":"c50a3091-b8ba-4be2-966b-fefc2f229d89","resolution":{"observed_at":"2026-08-07T14:51:27.416253Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T14:51:33.287126Z","title":"Neural networks as smooth priors for inverse problems for PDEs","venue":null,"work_id":"ff73ecf8-7be7-4f25-975b-85256ebb60ce","year":2021},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:20.307428Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:7079571a49a52174e8ab3a512e231507bb5ae05d419fde7cc8fd428739a7afab","observation_id":"9d1343d5-0777-4225-941d-874970fc2cda","resolution":{"observed_at":"2026-08-07T14:51:33.427328Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1023/a:1011497229317","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:51:27.032599Z","title":"Some remarkable properties of sinc and related integrals","venue":null,"work_id":"c519e7c3-34c1-47f3-acc4-66a8b04a0d19","year":2001},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:20.395883Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:fe399eefb1262be23681e40446cf70bcf2206ed2f8998740d6c8882fec0a5c58","observation_id":"ae75b1e7-c6e4-4845-80db-46e18b076d8a","resolution":{"observed_at":"2026-08-07T14:51:27.177124Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1007/978-3-642-11269-0_6","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:51:26.792353Z","title":"The complexity of satisfiability of small depth circuits","venue":null,"work_id":"313a4c1f-f877-4c68-bce9-a135fc86d283","year":2009},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:20.483139Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:df16ef4473cb2bf230d7867b73f3e9e1ddac0f67f213131d619e6400d9f78995","observation_id":"0c88e1ec-562f-4ae2-90b5-a012e66d00e4","resolution":{"observed_at":"2026-08-07T14:51:26.879732Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T14:51:20.562056Z","title":"Solving the quantum many-body problem with artificial neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:20.562056Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:166dbccd1b25728b375470eee0fed0bd3666e28f88a88d98196207fb89dcda17","observation_id":"9f519fe7-a29f-448f-86e7-74102bfb6dce","resolution":{"observed_at":"2026-08-07T14:51:20.562056Z","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":"2026-08-07T14:51:33.013203Z","title":null,"venue":null,"work_id":"d3e4097a-ef1c-430a-b2b8-f901018c5ceb","year":1984},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:20.648240Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:aa8cd337412a9b6e483d489a52c0b8dd7575fb3399c2a26356930f7b1ecc98db","observation_id":"f06426b8-ebb8-4d73-8338-6c388d0bc7d7","resolution":{"observed_at":"2026-08-07T14:51:33.136400Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T14:51:20.729038Z","title":"Approximation algorithms for training one-node ReLU neural networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:20.729038Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:f3e6e2e7ec01d50117a00ea844997fa691ae6d699f908eee79c9d403f890609e","observation_id":"7c88b814-5e69-40a2-bba8-032c684073db","resolution":{"observed_at":"2026-08-07T14:51:20.729038Z","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":"2026-08-07T14:51:32.709160Z","title":"High-dimensional integration: The quasi-Monte Carlo way","venue":null,"work_id":"05e2a296-4fac-44d8-b9e0-2b16181c5b4e","year":2013},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:20.804479Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:081c2ac4e71904d95c7650bb79ee29d8c8d779f9aa859bb4132fe90b8f927393","observation_id":"54455d0a-3a66-44d3-b060-d3c984658103","resolution":{"observed_at":"2026-08-07T14:51:32.858327Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T14:51:32.487339Z","title":"Expression of Fractals Through Neural Network Functions","venue":null,"work_id":"a9ef6439-8822-4010-ac62-6ab42ae0ff67","year":2020},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:20.884902Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:d792f54ba5882e479437353f3d906acd0f4306371205faa5725b0b1f9f593090","observation_id":"82dc33c1-b458-44e3-bfa4-bbe71a2975db","resolution":{"observed_at":"2026-08-07T14:51:32.576739Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T14:51:32.243315Z","title":"Algorithms for solving high dimensional PDEs: from nonlinear Monte Carlo to machine learning","venue":null,"work_id":"0a8da5b7-9eb4-4e45-8461-8430daa51675","year":2022},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:20.986950Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:d42d9c60c35d7d48bb466224955646a31d2d277690445bfe2aa1c5eb5b9f307f","observation_id":"0cfba83c-1fe8-406e-af44-9bbaaa6bd9fe","resolution":{"observed_at":"2026-08-07T14:51:32.343175Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T14:51:21.054908Z","title":"The Deep Ritz Method: A Deep Learning-Based Numerical Algorithm for Solving Variational Problems","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:21.054908Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:5d3aec73f0c592d0bdb9b54bcf0d9766c0add2351932148c11481861027025e4","observation_id":"5dfd182e-2090-48f8-aa13-56240e4ccfa6","resolution":{"observed_at":"2026-08-07T14:51:21.054908Z","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":"2026-08-07T14:51:31.978022Z","title":"The deep Ritz method: a deep learning-based numerical algorithm for solving variational problems","venue":null,"work_id":"1d2bc8d4-d03c-4d90-b35a-0d464f890b80","year":2018},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:21.133424Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:7ab4e8115768f9788e71952f861d8bf931152570f9fe7f51bb2118ddaea98c6b","observation_id":"8e2a0f69-d819-4870-a359-e46108422383","resolution":{"observed_at":"2026-08-07T14:51:32.116424Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T14:51:31.712525Z","title":"Feischl, A","venue":null,"work_id":"8f053695-c61a-4512-8d9b-0579ddcc5789","year":null},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:21.211052Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:e56e4f10092cd89acf4dde3d71da72b926f03f4fa3e6f638d064e241f07f1a0a","observation_id":"9c081924-db4b-4489-9d75-410ad89deb60","resolution":{"observed_at":"2026-08-07T14:51:31.849699Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T14:51:31.424899Z","title":"Deep Neural Networks and Adaptive Quadrature for Solving Variational Problems","venue":null,"work_id":"e5b6880c-d0a0-4746-bc95-51ff940b819e","year":2022},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:21.319103Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:a64a42672ef1752b3deb5d49eaee7f408a88652cbe681c0c977ede260a33d2eb","observation_id":"863b5661-cfac-47e5-b7b5-e318fdcad6fa","resolution":{"observed_at":"2026-08-07T14:51:31.559458Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.4169/amer.math.monthly.119.10.868","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:51:26.516916Z","title":"Hyperplane sections of the n-dimensional cube","venue":null,"work_id":"aec62f51-cc15-4aa3-ab77-d4f4d64c6f23","year":2012},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:21.417645Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:0f6858276283a72e196174e528fb0cb8219fb2fca129ae5354fdc6b38f66ffe9","observation_id":"16c6368a-bc1d-474b-872e-7e7b968c979c","resolution":{"observed_at":"2026-08-07T14:51:26.719376Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.17045","last_updated":"2024-01-18T12:10:03Z","snapshot_observed_at":"2026-08-05T21:02:53.757400Z","submitted_at":"2023-03-29T22:16:52Z","title":"Training Neural Networks is NP-Hard in Fixed Dimension","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.17045","snapshot_observed_at":"2026-08-07T14:51:21.496167Z","title":"Froese and C","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:21.496167Z"},"links":{"cited_paper":"/paper/2303.17045","citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:13c72549a65d7b653affefdf0e63b7d345d3d1ba8b2488d72eefced873635e32","observation_id":"33885e21-5e72-4a4e-8a46-ed6931ec7dde","resolution":{"observed_at":"2026-08-07T14:51:21.496167Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.09438","last_updated":"2022-10-11T12:07:14Z","snapshot_observed_at":"2026-07-06T13:11:32.691554Z","submitted_at":"2022-05-19T09:54:41Z","title":"Gold-standard solutions to the Schr\\\"odinger equation using deep learning: How much physics do we need?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.09438","snapshot_observed_at":"2026-08-07T14:51:21.571889Z","title":"Gold-standard solutions to the Schr¨ odinger equation using deep learning: How much physics do we need?","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:21.571889Z"},"links":{"cited_paper":"/paper/2205.09438","citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:d1a39e59f66f8f69dfa668fc6c91ac19c20b52b320d520301881c688e0c2e215","observation_id":"41775334-c6a2-4926-8f96-5bf98e390e67","resolution":{"observed_at":"2026-08-07T14:51:21.571889Z","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":"2026-08-07T14:51:31.085674Z","title":"Gilbarg and N","venue":null,"work_id":"26dd6280-6f08-4e62-b3a1-24d7496c7700","year":1998},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:21.694659Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:a5d7309fda23b11264edcab90f4b865014a93c23d4e57a6f6300b214f7cfbcc8","observation_id":"452b2b57-0fc0-4f2b-9fe1-394388d566b2","resolution":{"observed_at":"2026-08-07T14:51:31.243302Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T14:51:30.822420Z","title":"Analysis of preintegration followed by quasi–Monte Carlo integration for distribution functions and densities","venue":null,"work_id":"cb4854bb-348c-486d-a66c-f723f6df8313","year":2023},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:21.789653Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:da3272932f5ab816708f65f8a79bd2fb6303efb222a3484b14bff7258e14a210","observation_id":"ba7b9896-4936-4718-abbb-78565bddd49e","resolution":{"observed_at":"2026-08-07T14:51:30.962126Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T14:51:30.613970Z","title":"Tight hardness results for training depth-2 ReLU networks","venue":null,"work_id":"ce17cc3d-8a7e-477a-860b-81e583343aab","year":2021},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:22.006675Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:a32492fc5ad6e56a536a401235fc79ebbf71a2a177c25995ead92f1ff3d414c7","observation_id":"3fec6d3b-ebed-4cdc-99df-d0b8aacb908e","resolution":{"observed_at":"2026-08-07T14:51:30.718641Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T14:51:22.079096Z","title":"Hierarchical singular value decomposition of tensors","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:22.079096Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:c241b0496e213d7ee002cd1ab95d61708201f149bf3a875ab1eb643b547b6f78","observation_id":"f9ff6de6-19d9-4c07-a6e9-c2a3c11ba366","resolution":{"observed_at":"2026-08-07T14:51:22.079096Z","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":"2026-08-07T14:51:30.363156Z","title":"A proof that artificial neural networks overcome the curse of dimensionality in the numerical approximation of Black-Scholes partial differen- tial equations","venue":null,"work_id":"dd116af8-5465-48e5-96c0-e18c3b415098","year":2023},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:22.173280Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:408fd207300b91f00a63def3e4c66643bdf06cb4acfb5a86ae653ddae33273cd","observation_id":"ac248f02-0650-42d2-8242-5a8672b44647","resolution":{"observed_at":"2026-08-07T14:51:30.470017Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.18219","last_updated":"2026-07-21T19:07:42Z","snapshot_observed_at":"2026-08-07T16:42:45.587616Z","submitted_at":"2025-03-23T21:45:58Z","title":"Theory-to-Practice Gap for Neural Networks and Neural Operators","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.18219","snapshot_observed_at":"2026-08-07T14:51:22.262827Z","title":"Grohs, S","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:22.262827Z"},"links":{"cited_paper":"/paper/2503.18219","citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:c165a3bdbedcf554fed92762341fd2d1bd135eeba23854800a88c681de30b6e5","observation_id":"a9ca1ec1-0446-4bf7-939f-1c1c6c9d39aa","resolution":{"observed_at":"2026-08-07T14:51:22.262827Z","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/s10208-023-09607-w","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:51:25.981893Z","title":"Proof of the theory-to-practice gap in deep learning via sampling complexity bounds for neural network approximation spaces","venue":null,"work_id":"f06f9888-ea76-45c5-9ec8-111d25c98983","year":2024},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:22.348877Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:4a924aa4e711ff3af28aeb6378ccbc63745e42e84337d3d93530958453629de7","observation_id":"fa7f7882-6c23-4d35-8216-59f0427c8de2","resolution":{"observed_at":"2026-08-07T14:51:26.110580Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T14:51:22.429773Z","title":"A new scheme for the tensor representation","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:22.429773Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:3685b49c94154516b6efcfc81cd0dedebc25548c8f9734e7605160f2e900a0d3","observation_id":"f4dce1b6-c751-419c-8b28-f4ca0bbc7e7d","resolution":{"observed_at":"2026-08-07T14:51:22.429773Z","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":"2026-08-07T14:51:30.141421Z","title":"Solving high-dimensional eigenvalue problems using deep neural networks: A diffusion Monte Carlo like approach","venue":null,"work_id":"9440461a-bcc5-4a46-bc3a-ed4f0321b9a1","year":2020},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:22.502337Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:587b9a9762bc501b39d76b44647c47499895993ea50365190dd2cbe17fdb0373","observation_id":"9213709c-dbe7-4ef1-b1fd-031a1a6aec43","resolution":{"observed_at":"2026-08-07T14:51:30.241936Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1007/s10444-024-10171-2","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:51:25.569604Z","title":"Neural and spectral operator surrogates: unified construction and expression rate bounds","venue":null,"work_id":"685a290a-da1e-40cc-a7a4-74c361eb6506","year":2024},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:22.582066Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:3fc1974eafcba44ae9ca86fcf675d8e96bd39b6616e5095fd98e3dc0ead39d39","observation_id":"6dcc9eb0-2d25-4ea8-a5e9-bca49b71e77c","resolution":{"observed_at":"2026-08-07T14:51:25.721230Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T14:51:30.004262Z","title":"On the complexity of k-SAT","venue":null,"work_id":"475110e5-66e9-4d1b-a234-824fd0559e4f","year":1999},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:22.659764Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:3d3389374269d2cc95553d215dd024f879d61e665b3796f43405ee49f53a73a4","observation_id":"b9358824-6eff-41eb-8e35-bfca58aa45c7","resolution":{"observed_at":"2026-08-07T14:51:30.084356Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T14:51:29.885345Z","title":"Which Problems Have Strongly Exponential Complex- ity?","venue":null,"work_id":"5e3f0ef7-6f19-4062-8792-e0746aa62aab","year":2001},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:22.847568Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:b2cf2f49a883f6374c8dac29127465edf946a77bf0ca59c4b2135bc9fe1b997c","observation_id":"760c55bd-665b-4d57-b6d3-6ddd4699d3c5","resolution":{"observed_at":"2026-08-07T14:51:29.942126Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1515/rjnamm.2011.017","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:51:25.231796Z","title":"QTT approximation of elliptic solution operators in higher dimensions","venue":null,"work_id":"e48ec59c-8176-4171-a627-2a4a2fa4d81b","year":2011},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:22.926441Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:675f9ce9a9fc59ab9f59071b16bbccdae917f537a07976281fd5667015d85280","observation_id":"5745fecf-3a01-4627-ae1a-bcac443d7417","resolution":{"observed_at":"2026-08-07T14:51:25.355110Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.15715","last_updated":"2024-02-24T04:40:27Z","snapshot_observed_at":"2026-07-06T17:34:53.153463Z","submitted_at":"2024-02-24T04:40:27Z","title":"Operator Learning: Algorithms and Analysis","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.15715","snapshot_observed_at":"2026-08-07T14:51:22.985705Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:22.985705Z"},"links":{"cited_paper":"/paper/2402.15715","citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:873c76eabbcc9a626f7507e92c577c0037e3b1b788da238e650fd902be2236a1","observation_id":"11d7ed3a-7676-4627-adb5-1042b62ca973","resolution":{"observed_at":"2026-08-07T14:51:22.985705Z","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":"10.1002/malq.19670130104","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:51:24.854188Z","title":"The Decision Problem for a Class of First-Order Formulas in Which all Disjunctions are Binary","venue":null,"work_id":"8af1515d-6a6a-424e-9243-5dfe6d60ef72","year":1967},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:23.064971Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:b9d6b3d53b67964b4225f1e89314c1a1ce4025e885e797c6d2aef8cb20f0ba9d","observation_id":"2b0f50f5-89d0-4089-88ec-df60a3ddfc94","resolution":{"observed_at":"2026-08-07T14:51:24.970549Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T14:51:23.119649Z","title":"Error estimates for DeepONets: a deep learning framework in infinite dimensions","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:23.119649Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:58bea22af08273321f46a25bd194e63b65a8bbe784055800aad595833cd36f19","observation_id":"a48c3d4f-80a9-4529-9fed-8e7b0dfdd69d","resolution":{"observed_at":"2026-08-07T14:51:23.119649Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.14394","last_updated":"2024-03-19T05:39:32Z","snapshot_observed_at":"2026-07-06T16:36:47.091524Z","submitted_at":"2023-10-22T19:58:33Z","title":"Neural Networks are Integrable","version":2},"cited_work":{"arxiv_id":"2310.14394","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.14394","snapshot_observed_at":"2026-08-07T14:51:27.614565Z","title":"Neural Networks are Integrable","venue":"math.NA","work_id":"ac4d1693-ecec-497a-84ea-3c94f4888422","year":2023},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:23.175873Z"},"links":{"cited_paper":"/paper/2310.14394","citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:4fe8b66db66540a0f811c86de50a8718706354748d64ce13afebd3b479c6e2fa","observation_id":"5082aef0-c3b7-41e2-9700-b20562466c04","resolution":{"observed_at":"2026-08-07T14:51:27.681119Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T14:51:29.757746Z","title":"Exponential ReLU neural network approximation rates for point and edge singularities","venue":null,"work_id":"ee966228-3aca-46a8-819d-4103f0bfccd3","year":2023},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:23.240785Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:0a9d4e56976d9476ebdb065aaaea754f77c695b49e232ba612770b9bb49c1e1d","observation_id":"16c992a7-f03c-4364-97d0-caa2f2c08a32","resolution":{"observed_at":"2026-08-07T14:51:29.828033Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T14:51:23.476015Z","title":"Marcati and C","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:23.476015Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:41813106f60d360a3db2dd4bc0441579d4ffa3e02833eb3a770dd44490872ed7","observation_id":"b45db3c4-7ad2-4baa-a168-8f799e7bf872","resolution":{"observed_at":"2026-08-07T14:51:23.476015Z","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":"2026-08-07T14:51:29.657310Z","title":"Deep learning in high dimension: ReLU neural network expression for Bayesian PDE inversion","venue":null,"work_id":"a8cf028b-3338-4f5c-988b-cc49bb2d9964","year":2022},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:23.551063Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:1e0833e59e89aba75c3092bbebc935676bba69b67ab8be37d0b778c59027f3b3","observation_id":"34e3e47a-250a-4d61-9ba0-8d33959db929","resolution":{"observed_at":"2026-08-07T14:51:29.699650Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T14:51:23.640204Z","title":"Approximation of 2 d × 2d matrices using tensor decomposition","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:23.640204Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:39f33e85aff8ebc7abcc6d96d355c7c5e255332547e95e90550e6415bc01ec7f","observation_id":"9b49969a-a903-452a-a8e3-455fa77cb572","resolution":{"observed_at":"2026-08-07T14:51:23.640204Z","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":"2026-08-07T14:51:23.700826Z","title":"Topological properties of the set of functions generated by neural networks of fixed size","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:23.700826Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:bac2032173bf44178a81efdfd097fa245b4af2b3b81af88a1dda67ace3be4358","observation_id":"beef8bfb-c5c3-4c79-bfec-72a8dbc9e8a7","resolution":{"observed_at":"2026-08-07T14:51:23.700826Z","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":"2026-08-07T14:51:29.484046Z","title":"On the difference between Turing machine time and random-access machine time","venue":null,"work_id":"1978ad42-5cee-432e-a1dd-c9a50e39cd6b","year":1993},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:23.766401Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:27b51084e99c1e253b9fca2ca93d4b0cd3d0375d34037809daa8e97804d60a07","observation_id":"c1a26a04-2c60-4872-a536-4803270ce023","resolution":{"observed_at":"2026-08-07T14:51:29.587670Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T14:51:29.349166Z","title":"On quadrature rules for solving Partial Differential Equations using Neural Networks","venue":null,"work_id":"a3fff770-53a6-42ce-b2ef-d8a7419903ab","year":2022},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:23.858128Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:b162c9d46a6d15a804bf8da09c39571a1a2c31ea010f52dc5aae5ab2c605ca13","observation_id":"fdf6c7c0-e497-4dc0-a5c1-0415489b82b3","resolution":{"observed_at":"2026-08-07T14:51:29.419545Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T14:51:29.141693Z","title":"A probabilistic algorithm for k-SAT and constraint satisfaction problems","venue":null,"work_id":"1f8d474e-3d51-47ca-9415-56801be6d337","year":1999},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:23.917139Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:c637b1b910f0e5cb5d45688cc65500ac14f374e0f3d46b8745a2f679a9f9d036","observation_id":"09b69af4-296f-4816-9fc0-5a8248bc495a","resolution":{"observed_at":"2026-08-07T14:51:29.232881Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T14:51:23.996311Z","title":"Deep solution operators for variational inequalities via proximal neural networks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:23.996311Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:4f2c9abc67d7445b2746bffd8dc38062e073798e1894b761428647d4975d5c26","observation_id":"ae8ef4f0-bf41-4174-8d78-ac725cde14a1","resolution":{"observed_at":"2026-08-07T14:51:23.996311Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09835","last_updated":"2023-07-19T08:46:47Z","snapshot_observed_at":"2026-08-05T09:45:55.830911Z","submitted_at":"2023-07-19T08:46:47Z","title":"Deep Operator Network Approximation Rates for Lipschitz Operators","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09835","snapshot_observed_at":"2026-08-07T14:51:24.049918Z","title":"Schwab, A","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:24.049918Z"},"links":{"cited_paper":"/paper/2307.09835","citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:22998ce46205e9838ac6cb6560dbfc09908203576a2fdab8b8d75b5f233de038","observation_id":"9eee41d8-9f11-4bb1-a071-8ff478b1c456","resolution":{"observed_at":"2026-08-07T14:51:24.049918Z","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":"2026-08-07T14:51:24.153165Z","title":"Deep learning in high dimension: neural network expression rates for analytic functions in L2(Rd, γd)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:24.153165Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:a816a79fa36c6474305ceb05b35d8cb91053776b8db9ea8df74a00b8a63020e4","observation_id":"59b5dc6d-e1ce-4269-a2b9-ce68913105be","resolution":{"observed_at":"2026-08-07T14:51:24.153165Z","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":"2026-08-07T14:51:28.989635Z","title":null,"venue":null,"work_id":"811e5cf4-ef93-406d-be8a-769b2b7c8f51","year":2013},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:24.233054Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:4506ac22e50c56c063dcf4057d386e0525c31a2124a448be565c55234a426634","observation_id":"06a01ec9-4026-4c92-8fe2-7aec67498b94","resolution":{"observed_at":"2026-08-07T14:51:29.081447Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T14:51:28.787003Z","title":"Le probl` eme de Dirichlet pour les ´ equations elliptiques du second ordre ` a coefficients discontinus","venue":null,"work_id":"b96985e4-0697-40ea-8fa7-ba1c832e9241","year":1965},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:24.295937Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:ec38af2f5fc1d6ba033e3db5273e354384c998c87518a1beb5ffd87533a5cb20","observation_id":"5b4ba884-1b98-4092-96e1-8f1d7b52371e","resolution":{"observed_at":"2026-08-07T14:51:28.898628Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T14:51:28.596545Z","title":"On the Complexity of Derivation in Propositional Calculus","venue":null,"work_id":"cd110859-ba4c-4502-87a4-dc9ba6a4ab61","year":1967},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:24.401193Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:3cfb70c44152757b4c24391ebe5b0f6cbf09a81577d798b393bdf2eca9c2e2bf","observation_id":"26fb6330-e874-4d6e-88c5-c615d8d29e58","resolution":{"observed_at":"2026-08-07T14:51:28.686884Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T14:51:28.366510Z","title":"Weak adversarial networks for high-dimensional partial differ- ential equations","venue":null,"work_id":"4b103f26-4496-47c9-916e-59759731e46f","year":2020},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:24.498177Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:162363a3a55d978083a838780471435f5e654666366fb2b08e98920617b03360","observation_id":"e594795c-c614-448e-a8a0-1ca4fd39b920","resolution":{"observed_at":"2026-08-07T14:51:28.504547Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1137/21m146658x","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:51:26.293938Z","title":null,"venue":null,"work_id":"493ebf20-84b5-40f3-803a-59f24871b5fc","year":null},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":166,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:21.908547Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:dddca9c75e1a501a068c54333f02d1f9f682e2f8500258ee098fdb3a47c102ad","observation_id":"3e47c877-116b-47a4-9515-d71ead372d29","resolution":{"observed_at":"2026-08-07T14:51:26.404584Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T14:51:22.787521Z","title":null,"venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":375,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:22.787521Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:76834c2eae518ce84bc28bbb6306fd67dd8c70d04e5c928b7c86987ccff62e67","observation_id":"20bdce06-52d2-418a-ad45-be5589899974","resolution":{"observed_at":"2026-08-07T14:51:22.787521Z","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/s10208-022-09565-9","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:51:24.584214Z","title":null,"venue":null,"work_id":"5a39cb9c-50d2-4bf8-a515-5306f1981f75","year":null},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":1127,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:23.380150Z"},"links":{"citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:8727c4207fe6cdd4bb34489b0b6aa68a778bafe1759558214b1505477cb43916","observation_id":"a2c5de12-c005-4bb2-af13-daa62d50f989","resolution":{"observed_at":"2026-08-07T14:51:24.672116Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.02242","last_updated":"2024-10-30T10:50:26Z","snapshot_observed_at":"2026-07-06T18:40:18.655063Z","submitted_at":"2024-07-02T13:03:46Z","title":"Towards optimal hierarchical training of neural networks","version":2},"cited_work":{"arxiv_id":"2407.02242","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.02242","snapshot_observed_at":"2026-08-07T14:51:27.960538Z","title":"Towards optimal hierarchical training of neural networks","venue":"math.NA","work_id":"2a87df2f-5744-4838-92fc-65e9afbe8ba5","year":2024},"citing_paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T14:51:21.260415Z"},"links":{"cited_paper":"/paper/2407.02242","citing_paper":"/paper/2505.17751"},"observation_digest":"sha256:8a866bace28c0602894615ea7301b9e231d9096218301ed2bd67d378a9de7d5b","observation_id":"2e08f9da-eabc-49bc-bc13-aa083abf23a0","resolution":{"observed_at":"2026-08-07T14:51:28.123104Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.17751","last_updated":"2025-05-23T11:21:05Z","latest_version":1,"primary_category":"math.NA","snapshot_observed_at":"2026-08-07T14:39:12.500513Z","submitted_at":"2025-05-23T11:21:05Z","title":"Computational Math with Neural Networks is Hard"},"reference_resolution":{"displayed":54,"state_counts":{"malformed_identifier":2,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":19,"verified_exact":11,"verified_fuzzy":21},"total_outbound_references":54},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 54 of 54 outbound references and 1 inbound Pith citation observation for arXiv:2505.17751."}