{"as_of":"2026-08-14T16:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e07d50b221b30d8b50c5ccd6e78415b94ca6a0b92df8b13469f18bccbc41841c","coverage":[{"denominator":63,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":63,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-14T10:37:37.440024Z","state":"measured"},{"denominator":63,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":63,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.10589/citation-record","integrity":"/paper/2607.10589/integrity","json":"/paper/2607.10589/citation-record.json","paper":"/paper/2607.10589"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T10:37:37.440024Z","title":"SIAM, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:a0e33174f13849eb9b6ef8387880217eee6a3182f077cd1e6a65a6a3552492b3","observation_id":"258863cb-2ef7-45d8-a0d6-a020943f1f73","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"cambridge university press, 2009","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:115a8a28e8c58eee2c960ac35193561d11cd6772c47f049b92d97332c9333bec","observation_id":"5be4a19f-a833-4789-a0b4-a666e5139999","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Universal approximation bounds for superpositions of a sigmoidal function.IEEE Transactions on Information theory, 39(3):930–945, 1993","venue":null,"work_id":null,"year":1993},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:d280b6444b4877aa70a858786158d96d7c8da9608eedc50485a8e6db8d9b5d7c","observation_id":"01794a61-2881-4129-9ed7-a388a078cb03","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Nearly- tight vc-dimension and pseudodimension bounds for piecewise linear neural networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:ee0546e9dba1785ad02fea7fe92753966ec583de0bb3f67987300d0aaca205b7","observation_id":"633b5b20-fd5e-4647-a5a3-05395c997201","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Shallow and deep networks are near-optimal approximators of korobov functions","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:93fe173f88dcaefe7f03d4ef0b3384d29c435194d5e4b5b42ee2fa29289b7932","observation_id":"7c0d66f3-ba11-4dc3-a9b1-bcf5716d8050","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Optimal approximation with sparsely connected deep neural networks.SIAM Journal on Mathematics of Data Science, 1(1):8–45, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:421920c2bb31d8e47f1ec255919d1592e86c97485d75cba42af4100da15c3dc6","observation_id":"c8512a37-9c54-4d1f-b263-b8ad614b4e6a","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:bb0a3a0b3bc3e12596c24e04934e98e5fae6cf13464f205c57ce6a8d6bf18119","observation_id":"a3be89bc-1146-4db7-97a9-d7904e21e1f6","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Breaking the curse of di- mensionality in sparse polynomial approximation of parametric pdes.Journal de Math´ ematiques Pures et Appliqu´ ees, 103(2):400–428, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:98bcaad425e5d1aa4fe96bd88218772c145846a193774f05d2ac7d7e830d7ef7","observation_id":"8ea0d91f-6c6d-43df-b70b-7224d2f5b1c9","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Analytic regularity and poly- nomial approximation of parametric and stochastic elliptic pde’s.Analysis and Ap- plications, 9(01):11–47, 2011","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:b63b136f58acce2eb8c29409ee3755ce04d04ccfd0d1203c88a30d0c72a3e0f7","observation_id":"0635b7fd-e76d-470e-b657-860079872acb","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Approximation by superpositions of a sigmoidal function.Mathe- matics of control, signals and systems, 2(4):303–314, 1989","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:dbb57a1c1c517571514ae5f82bf5491023e9b86bd486d273a322470eb539d31e","observation_id":"b34a753e-757b-45db-a50a-2af98917ce55","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Neural network approximation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:486ae1de2f958b319f9bfd55350927eae6d4bc6a791f807cfe492f7911aaea24","observation_id":"802c7287-acb1-4579-8f68-955e78244094","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Exponential convergence of the deep neural network approximation for analytic functions.Science China Mathematics, 61(10):1733–1740, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:86ae1c4fbfe1644f5a8a8380abde8b48d012c978dee3add4b988f32a59e1a6b1","observation_id":"6ee53784-02ae-4948-89f0-9437dff0fee1","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Chapman and Hall/CRC, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:f8bdf0b3cdc6e4a706c54128fa9434a2246a04a8b4a4a8ac0e5235aa9e38ab6c","observation_id":"f91d18f0-8541-476b-833c-474a87a557c0","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Error bounds for approxima- tions with deep relu neural networks in w s, p norms.Analysis and Applications, 18(05):803–859, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:236df69be96ae2a8920dd97bbfedc5b4eba2713256304c0b7eaf18d9f2afa52b","observation_id":"fe7c2ec8-9e20-4e48-ae25-ce20796d4286","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Approximation rates for neural networks with encodable weights in smoothness spaces.Neural Networks, 134:107–130, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:45d510a71c24721ecfb62cd00d119dbe8342b4378cb1dda8f4ce11569070a60f","observation_id":"c7811a8b-0938-4fa4-bd77-03f449856047","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Decision theoretic generalizations of the pac model for neural net and other learning applications.Information and computation, 100(1):78–150, 1992","venue":null,"work_id":null,"year":1992},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:e4a3816d783f712dcad4da5cbf7a872d0bda928a55bf7383c7d15a82eae6b9e3","observation_id":"75b7f302-2959-450b-bf56-dd00debb6fb9","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Sphere packing numbers for subsets of the boolean n-cube with bounded vapnik-chervonenkis dimension.Journal of Combinatorial Theory, Series A, 69(2):217–232, 1995","venue":null,"work_id":null,"year":1995},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:a6559aa26f801a6e1f010e79efa9535762c24c04cc585bb2c7496430a60f4443","observation_id":"2e6cc8fc-1dcf-4bc1-8ef3-32850814242e","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Simultaneous neural network approximation for smooth functions.Neural Networks, 154:152–164, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:adf3ed86924d2103f20a720bb5db58dc3680263622e8ddfc301c73ca8679f1a3","observation_id":"c61eab36-8dcf-4fee-b8e2-4fd907db77cb","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Approximation capabilities of multilayer feedforward networks.Neural networks, 4(2):251–257, 1991","venue":null,"work_id":null,"year":1991},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:8423426409e098b6d4e476fd25a6d7e8e31c8ebd3c9183b229c71e5c52fbc8a6","observation_id":"6bdf51b6-91a6-49eb-8dcb-4d756e5b0a60","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"On estimation of analytic functions.Studia Sci Math Hungarica, 34:191–210, 1998","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:7e6fa7217a241a830e8a29f0e6bd65e8fcfdcec3aa07c42990ca26e5f6ac8432","observation_id":"36ee2418-ec52-41b8-96a1-c8011758baeb","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Springer Science & Business Media, 2013","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:d039abed0a60f6b78c5545c1860982bdf57d8b57da43d270a99cef483200f06f","observation_id":"719a710a-f138-4112-b324-2bf3ec3aa27f","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:1d7d56f433a9388569a9c65251aae24333ab34d51fbf32e1f7d8df0460b631dd","observation_id":"aa7c69de-cfda-45cc-b51f-d9ce8e657638","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Deep nonparametric regression on approximate manifolds: Nonasymptotic error bounds with polynomial prefactors.The Annals of Statistics, 51(2):691–716, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:6ed2d2c9bdc38dc04ee025294fed8ec350586b257de9f69da8a141f9177884ad","observation_id":"4686ef0b-98df-43c2-8d52-a2418c83bd8e","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Approximation bounds for norm con- strained neural networks with applications to regression and gans.Applied and Computational Harmonic Analysis, 65:249–278, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:75de00e71a1957106fb66f8268f221fda61604f4a41688db0b11de559553bc64","observation_id":"20d7cc41-4d7d-4b4a-99db-19ed1d42349a","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"On the rate of convergence of fully connected deep neural network regression estimates.The Annals of Statistics, 49(4):2231–2249, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:0a9f307bbd3699f0969eddfe647296e24287718d05e6481bfba3dc08b29176ea","observation_id":"c2ba5e9f-9f03-4881-9e55-7308ad76e60b","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Multilayer feedforward networks with a nonpolynomial activation function can approximate any function.Neural networks, 6(6):861–867, 1993","venue":null,"work_id":null,"year":1993},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:b7e8671ba2132242b3637fb4d496f789065b80526ee6131940e478c2dc630aa8","observation_id":"86ff9259-b42b-40d4-b3ef-6733b5393b79","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Some super-approximation rates of relu neural net- works for korobov functions.arXiv preprint arXiv:2507.10345, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:4c6221025ab67ea08dfab653f4736f250452d2a66f9e4cb319ed65407062b26f","observation_id":"dbca4d9f-8b68-410b-a070-b8e4c395f9f8","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:07641a67a77808eb5071d4894c8923cfcae361bfa2f83f5878064a1e1ac0a094","observation_id":"38ad5f0d-f7be-4d24-8313-2b3e6ea196a2","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Deep network approxi- mation for smooth functions.SIAM Journal on Mathematical Analysis, 53(5):5465– 5506, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:f8370eb83ea507680061ff07edff6737a6b07c1d6da815b88a795dd4bf96314c","observation_id":"7ddd09f6-9cc9-4e40-a479-025db91565d8","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"The ex- pressive power of neural networks: A view from the width.Advances in neural information processing systems, 30, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:287a261b104eaa11dadbce943e63585f4ea2115e0a55506aad06e76403a1fa46","observation_id":"011a80a1-6625-4bd2-a43a-73ce898f9b53","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Rates of approximation by relu shallow neural networks.Journal of Complexity, 79:101784, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:9633be566a4e8b0de2b57a4ab4f8f9c40341e571eacaa54e3e1e07047d2b8d30","observation_id":"029ed312-971d-4f7c-9415-81932fae4b0f","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Neural networks for optimal approximation of smooth and analytic functions.Neural computation, 8(1):164–177, 1996","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:95d0152e50a0062dfff140d7ef1a6f4fe297c9bfcc7e0ae8acc5f396224b8465","observation_id":"d0ede980-870a-4469-b242-090d32e9be2c","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Approximation properties of a multilayered feedforward artificial neural network.Advances in Computational Mathematics, 1(1):61–80, 1993","venue":null,"work_id":null,"year":1993},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:a1a33bc3f60107def0c301e43c11489aeb2931ae6a49a4dac6fbf2a07435908e","observation_id":"663a7b1e-e1d9-4491-ada7-fd3337e20e41","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"New error bounds for deep relu networks using sparse grids.SIAM Journal on Mathematics of Data Science, 1(1):78–92, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:5094111ef2b6aec188f3dc821d0c159249c6847f35efe23b3ab7c39903e2f5b5","observation_id":"eb77bd1b-1b7d-4ddf-aa23-a6d763e52bf3","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Adaptive approximation and generalization of deep neural network with intrinsic dimensionality.Journal of Machine Learning Research, 21(174):1–38, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:be959480f4157bc197f5b2aec2e2de69132456abf094795a2eb6c2f364e1038b","observation_id":"43af3ecd-1df9-4ef6-9361-cd14ec16fe9d","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Deep relu networks and high-order finite element methods.Analysis and Applications, 18(05):715–770, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:aece9c76851d20de36a2eb16b92bbb92c03fc3a83a13488467f324a66589d8cb","observation_id":"d696d207-1b98-4810-a669-f2a99f1e4ded","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Exponential relu dnn expression of holomorphic maps in high dimension.Constructive Approximation, 55(1):537–582, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:2ad9b13121b801f215c8bd2fcb9a09b5d3b823cc8dcee618ef456cbd56c81245","observation_id":"b51a86d3-db20-45b9-b0f1-2ed66c0c2757","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Optimal approximation of piecewise smooth functions using deep relu neural networks.Neural Networks, 108:296–330, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:c64f6377d6672e85d9092429518be89ce59964aeeadf85d71fdfdb463f4f5786","observation_id":"0565e343-cbe6-4b41-ad3a-795d689f3a86","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Approximation theory of the mlp model in neural networks.Acta numerica, 8:143–195, 1999","venue":null,"work_id":null,"year":1999},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:d71113639572c0104cea5f3b2c442b596ce2916a04e85aeb160a43ff1f721a15","observation_id":"f11cc75b-d8bd-4bd7-a266-0cc5497e7b2d","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"On the expressive power of deep neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:3c71e2e832c2e7a8586a587eeab4a034ffc38f9cbe94ff62b6f52e9494df8df2","observation_id":"a827fb2b-6ae6-40cb-a7ff-446d5efb6654","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Nonparametric regression using deep neural networks with relu activation function.The Annals of Statistics, 48(4):1875, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:f3509108cc4c6a3b0f4938f920b454dfcd4b699db9623a0a14d06ab88b8c8675","observation_id":"70c8fb9f-7c6d-4232-b4cf-ab5aa42b60fb","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Bounding and counting linear regions of deep neural networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:a0535f880b0419b0341b2a1fb4ff5773c46c76bfb8b3d5a46555ff6f64a49cdf","observation_id":"6cc8c463-9000-4cc3-9034-2886edf5a46f","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.03544","last_updated":"2023-05-16T08:52:01Z","snapshot_observed_at":"2026-08-14T10:53:55.530141Z","submitted_at":"2023-03-06T23:01:53Z","title":"Expressivity of Shallow and Deep Neural Networks for Polynomial Approximation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.03544","snapshot_observed_at":"2026-07-14T10:37:37.440024Z","title":"Expressivity of shallow and deep neural networks for polynomial ap- proximation.arXiv preprint arXiv:2303.03544, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"cited_paper":"/paper/2303.03544","citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:2edb4fbae2f6c7bf1e1f30316dc3859d7a7ce9f1f8eb4edc5664f90838ebbce9","observation_id":"b6d15226-d4a2-4f9a-aa43-cfc9e49e7b4a","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Deep network approximation characterized by number of neurons.Communications in Computational Physics, 28(5):1768–1811, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:cc4be3af517638f4af43bba67db4fac686626e1b16498827d2f08413eb1dc048","observation_id":"7e101718-793d-46f0-834a-2fbde41a6d72","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Optimal approximation rate of relu networks in terms of width and depth.Journal de Math´ ematiques Pures et Appliqu´ ees, 157:101–135, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:589e657891c85e32e93c1dba55405505151967354ca4116360fbd1bf0f361caf","observation_id":"e95cb639-8eb6-435c-b7d6-286a1d797650","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Optimal approximation rates for deep relu neural networks on sobolev and besov spaces.Journal of Machine Learning Research, 24(357):1–52, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:30e8f1ae72f90b503063d9b88129cd55e09cfc831a3115958e436c17b88ba49c","observation_id":"1ada28dc-1f8e-465f-8c26-f555d8ffa193","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Approximation rates for neural networks with general activation functions.Neural Networks, 128:313–321, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:161f204058800880a62c5b648e119da0f530b7787dc05e135a037a10cfe494e1","observation_id":"34718a30-251e-4a09-a114-a5a840a171d9","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"High-order approximation rates for shallow neu- ral networks with cosine and reluk activation functions.Applied and Computational Harmonic Analysis, 58:1–26, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:213a542cecb0d7a8c5e979e641657a7608f258f87241b730105f876a0c4bfa1c","observation_id":"c3e24c14-0a0b-4f84-bc6f-d45d9e7420c3","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Optimal global rates of convergence for nonparametric regression","venue":null,"work_id":null,"year":1982},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:404fe55b96795f843a99ffcde28726915cdbf0b18a800b391266a3af862bb53d","observation_id":"a9985717-524c-4227-8bdc-a746a7583ee7","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Adaptivity of deep relu network for learning in besov and mixed smooth besov spaces: optimal rate and curse of dimensionality","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:bcc4327f58025df4eae3befc114266a3737654a5e12b2395fea9789c4491a8cc","observation_id":"845786cd-4857-467b-8ade-288a14d57291","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Deep learning is adaptive to intrinsic dimensional- ity of model smoothness in anisotropic besov space.Advances in Neural Information Processing Systems, 34:3609–3621, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:6ce392594d46223c3755171ee2378533d27f915acafeb908cb6ebc8ec903061d","observation_id":"23f02c1c-0176-4323-912f-200a7372757d","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1509.08101","last_updated":"2015-09-29T13:44:37Z","snapshot_observed_at":"2026-08-03T18:23:00.117102Z","submitted_at":"2015-09-27T15:26:58Z","title":"Representation Benefits of Deep Feedforward Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1509.08101","snapshot_observed_at":"2026-07-14T10:37:37.440024Z","title":"Representation benefits of deep feedforward networks.arXiv preprint arXiv:1509.08101, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"cited_paper":"/paper/1509.08101","citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:c977c136087da058120d06e4091d7ba1a305b143e5796232f91026c987095c71","observation_id":"60dc5fc2-39ff-4e12-bd76-292730487ad4","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Springer series in statistics","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:7f92a3fdf91369f84295b3dd87f65a1b0e2ae58fb90dc18a8a1cda827fc95bd6","observation_id":"2b5ab01b-ee7f-4f18-96e3-200dbf60d6d4","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Cambridge university press, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:37683ade185e7475b20ae1547736fa847d819f67140a648603bd459e94acb82b","observation_id":"3909b7e6-352a-4284-a8dd-1e7765a1599b","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Deep neural networks with general activations: Super- convergence in sobolev norms.arXiv preprint arXiv:2508.05141, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:0184e9612e9adf728c5d7dd3685fe82084228a3287a3385d08635b9e49b5e297","observation_id":"85c53e66-56fd-4ac5-b853-4a99e847a44a","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Near-optimal deep neural network approximation for korobov functions with respect to lp and h1 norms.Neural Networks, 180:106702, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:a40aa53614c6f75f96ec6eea8945e36d3e9e6fcd61b9b7ab575a5515ff569cb3","observation_id":"3f9063ae-25ed-43f8-bde7-0a3b499045b0","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Nearly optimal vc-dimension and pseudo-dimension bounds for deep neural network derivatives.Advances in Neural Information Processing Systems, 36:21721–21756, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:4037bd037b887875b6f1c854748dafc2d01ddef59f66e61e810984ab9cbabb71","observation_id":"8231fe03-6fb4-458c-a195-d291bc1e6ed3","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"On the optimal approximation of sobolev and besov functions using deep relu neural networks.Applied and Computational Harmonic Analysis, page 101797, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:fe99e9fdb543ac30b18d30348b80dcc097f6dccc7fc30c99c0e63eb34b720a50","observation_id":"1ded229f-23dc-4eab-9483-fd6363bbd1a5","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2605.31152","last_updated":"2026-07-24T07:14:45Z","snapshot_observed_at":"2026-08-13T14:50:25.593125Z","submitted_at":"2026-05-29T11:04:06Z","title":"Approximation and learning of anisotropic and mixed smooth functions by deep ReLU neural networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.31152","snapshot_observed_at":"2026-07-14T10:37:37.440024Z","title":"Approximation and learning of anisotropic and mixed smooth functions by deep relu neural networks.arXiv preprint arXiv:2605.31152, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"cited_paper":"/paper/2605.31152","citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:24dcc796ae13dd8f02986554813709a56d7c08a5256d5f620e2855dcf6620876","observation_id":"95a5af10-4358-49d6-a072-8eae804afdfe","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Optimal rates of approximation by shallow relu k neural networks and applications to nonparametric regression.Constructive Approximation, 62(2):329–360, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:d97a1c3927ef62dedf67d7471d2218a2c02fd43f693a3b0851ac7d948e72ad88","observation_id":"1eff7212-adc0-494b-9f29-ecff5e18cdbd","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Error bounds for approximations with deep relu networks.Neural networks, 94:103–114, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:3f3f85607fd32df11f867c41dd9d59d41485a5441e078ecd203959b01a7b1b5d","observation_id":"33d91b89-1643-4130-9eb8-1a04a6a7f018","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Optimal approximation of continuous functions by very deep relu networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:b70281f2f6688ce273e64c6cced1cbf6d44d8d0dca72724b3f47cd5b90a34163","observation_id":"593a81d2-14bf-4b8b-8af6-96ef24dc1fff","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","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":"2026-07-14T10:37:37.440024Z","title":"Deep network approximation: Be- yond relu to diverse activation functions.Journal of Machine Learning Research, 25(35):1–39, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-07-14T10:37:37.440024Z"},"links":{"citing_paper":"/paper/2607.10589"},"observation_digest":"sha256:25d340c34eee6316178c787913d3f97b4655329d78f3a40e740e6fbbb438ea34","observation_id":"281b6637-8c8f-4cbb-bbdd-278a2bb17bc9","resolution":{"observed_at":"2026-07-14T10:37:37.440024Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.10589","last_updated":"2026-07-12T05:59:12Z","latest_version":1,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-02T20:25:47.505767Z","submitted_at":"2026-07-12T05:59:12Z","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width"},"reference_resolution":{"displayed":63,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":63,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":63},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 63 of 63 outbound references and 0 inbound Pith citation observations for arXiv:2607.10589."}