{"as_of":"2026-08-08T02:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c689fc237972cb2411459bbeb6e5f6730894fa5ee873b8e0eb0de370d43d153f","coverage":[{"denominator":118,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T13:12:59.251659Z","state":"measured"},{"denominator":101,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":101,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+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":"2026-05-08T17:00:37.250246Z","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":"2026-05-11T17:51:09.277513Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"cited_work":{"arxiv_id":"2509.00924","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2509.00924","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"S., and Roy, D.Beyond universal approximation theorems: Algorithmic uniform approximation by neural networks trained with noisy data.arXiv preprint arXiv:2509.00924 (2025)","venue":null,"work_id":"559db760-d0e3-4c43-bc7d-39c2c5e00271","year":2025},"citing_paper":{"arxiv_id":"2605.04995","last_updated":"2026-05-06T14:53:55Z","snapshot_observed_at":"2026-07-06T23:17:43.402046Z","submitted_at":"2026-05-06T14:53:55Z","title":"Adaptivity Under Realizability Constraints: Comparing In-Context and Agentic Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-08T17:00:37.250246Z"},"links":{"cited_paper":"/paper/2509.00924","citing_paper":"/paper/2605.04995"},"observation_digest":"sha256:7df24686cc5e48c085fc7c4b2d1fc9183cbd155c44a99d31bbd2a6751a802bfd","observation_id":"7e366cca-b399-4407-baee-d38416946eec","resolution":{"observed_at":"2026-05-11T17:51:09.280151Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2509.00924/citation-record","integrity":"/paper/2509.00924/integrity","json":"/paper/2509.00924/citation-record.json","paper":"/paper/2509.00924"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2411.04108","last_updated":"2024-11-06T18:36:21Z","snapshot_observed_at":"2026-08-05T05:48:39.168261Z","submitted_at":"2024-11-06T18:36:21Z","title":"Weighted Sobolev Approximation Rates for Neural Networks on Unbounded Domains","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.04108","snapshot_observed_at":"2026-08-05T13:12:58.943544Z","title":"Weighted Sobolev Approximation Rates for Neural Networks on Unbounded Domains","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:58.943544Z"},"links":{"cited_paper":"/paper/2411.04108","citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:db3abebdf2f1fa987410678281beb088811ca2183ef4f5eecf900a4f65677ed7","observation_id":"13fe236c-a871-4062-a42c-c1e19afe1423","resolution":{"observed_at":"2026-08-05T13:12:58.943544Z","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":"2026-08-05T13:12:58.947678Z","title":"Designing universal causal deep learning models: The geometric (hyper) transformer.Mathematical Finance, 34(2):671–735, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:58.947678Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:79d3320bf9d41649b121bdf8a9d7c1cc940b2c34cc16fd7d6aaa5e9cc145f204","observation_id":"0fee83e8-6e2f-4d2b-b96f-79e4eb36515e","resolution":{"observed_at":"2026-08-05T13:12:58.947678Z","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":"2026-08-05T13:12:58.951412Z","title":"Slic superpixels compared to state-of-the-art superpixel methods.IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(11):2274–2282, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:58.951412Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:73dbea7bb207a6e04d8fab1d5da739699a48b1c9d604de12cbd0fad3f5c9ede1","observation_id":"2577e5f0-5dd0-4d64-93cd-c1ec28d35279","resolution":{"observed_at":"2026-08-05T13:12:58.951412Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.06081","last_updated":"2021-03-05T00:48:51Z","snapshot_observed_at":"2026-08-06T00:29:45.843399Z","submitted_at":"2020-12-11T02:02:14Z","title":"Deep Neural Networks Are Effective At Learning High-Dimensional Hilbert-Valued Functions From Limited Data","version":2},"cited_work":{"arxiv_id":"2012.06081","doi":null,"metadata_source":"pith","pith_arxiv_id":"2012.06081","snapshot_observed_at":"2026-08-05T13:12:59.530887Z","title":"Deep Neural Networks Are Effective At Learning High-Dimensional Hilbert-Valued Functions From Limited Data","venue":"cs.LG","work_id":"de457a94-938b-4f3a-91a2-e2e12ba3af59","year":2020},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:58.954990Z"},"links":{"cited_paper":"/paper/2012.06081","citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:46bf3ba1e453a2a222b4d3dccc4ea19f82d53d3fc5fcd662ebdf2c1f978f7e75","observation_id":"f68249b5-e37a-4b45-9e83-a1891d057ece","resolution":{"observed_at":"2026-08-05T13:12:59.534657Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:12:58.958739Z","title":"Scale-sensitive dimensions, uniform convergence, and learnability.Journal of the ACM (JACM), 44(4):615–631, 1997","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:58.958739Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:09d9df1297a1101e9d954181ed6666c5d866df53ae757b5847570f5e4d8fbb0b","observation_id":"d676167e-5c20-4b1b-9161-f507071c05cc","resolution":{"observed_at":"2026-08-05T13:12:58.958739Z","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":"2026-08-05T13:12:58.961990Z","title":"Scale-sensitive dimensions, uniform convergence, and learnability.J","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:58.961990Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:0e7ffaa57e11e9d3fbf8f23e49a859b0740d33350c11502ef6075a5226e70d71","observation_id":"c52172c9-c3b7-401e-9263-716b5e4b7416","resolution":{"observed_at":"2026-08-05T13:12:58.961990Z","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":"2026-08-05T13:12:58.965456Z","title":"On the properties of variational approximations of gibbs posteriors","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:58.965456Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:19ebee1efc7f271b95eeec276d80dac7495eac5f3ef987ac38e7db1a4491f9d4","observation_id":"24e18548-b1e2-4c4e-badd-cb96c4912082","resolution":{"observed_at":"2026-08-05T13:12:58.965456Z","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":"2026-08-05T13:12:58.968313Z","title":"Some fine properties of sets of finite perimeter in ahlfors regular metric measure spaces","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:58.968313Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:be6ad5bb3fcda1d5d98fbbe7f453e2facc52cdd7f5cb3c22b95737643c43c57d","observation_id":"d0cce83a-f696-4d87-9ce5-2e5cdba9af80","resolution":{"observed_at":"2026-08-05T13:12:58.968313Z","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":"2026-08-05T13:12:58.971231Z","title":"On a theory of learning with similarity functions","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:58.971231Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:c60cf66286532a58878509e6c98fdd85913baef84e1e7541e3e12cddf6bc1e76","observation_id":"b6127dc7-8669-4c0e-aff4-0256f7c57fa0","resolution":{"observed_at":"2026-08-05T13:12:58.971231Z","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":"2026-08-05T13:12:58.974354Z","title":"Universal approximation bounds for superpositions of a sigmoidal function","venue":null,"work_id":null,"year":1993},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:58.974354Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:3c0d20e49c887151de4927dff09995c3d55771f5b64be3b97570f89f25402498","observation_id":"7304e325-7f9f-42aa-9ef4-f316f9e83516","resolution":{"observed_at":"2026-08-05T13:12:58.974354Z","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":"2026-08-05T13:12:58.977481Z","title":"Spectrally-normalized margin bounds for neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:58.977481Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:8181e4fc31fa8e0a46d3a8591da1e716b04123741320a8ef6a62e1fcd7a29447","observation_id":"cbc4e23a-1ca9-460a-9bc6-46ac28c57f85","resolution":{"observed_at":"2026-08-05T13:12:58.977481Z","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":"2026-08-05T13:12:58.980885Z","title":"Nearly-tight vc-dimension and pseudodimension bounds for piecewise linear neural networks.Journal of MachineLearning Research, 20(63):1– 17, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:58.980885Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:ea64cd78962da1f121cc3c92ae47b8a12be869eeb04783d2e38b718c86c74a7c","observation_id":"4e861d54-1e10-4539-9b40-8f8bc193f5c3","resolution":{"observed_at":"2026-08-05T13:12:58.980885Z","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":"2026-08-05T13:12:58.983895Z","title":"Vapnik-chervonenkis dimension of neural nets.The handbook of brain theory and neural networks, pages 1188–1192, 2003","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:58.983895Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:fe12d1cb94e24444350df35c6f34474f1eeca176672541f7f58cd1cfcd868238","observation_id":"5ff09a1f-13c1-42af-99aa-ec6bd0db3274","resolution":{"observed_at":"2026-08-05T13:12:58.983895Z","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":"2026-08-05T13:12:58.986618Z","title":"On numerical computation for the distribution of the convolution ofN independent rectified Gaussian variables.J","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:58.986618Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:f582978a5449a7e44efed72c9c7084748c123bbbc2f7eb3120b4ed831b4574a9","observation_id":"a205771d-b87e-4d4f-a9b3-3d2cee7721d5","resolution":{"observed_at":"2026-08-05T13:12:58.986618Z","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":"2026-08-05T13:12:58.989888Z","title":"Learnability and the vapnik-chervonenkis dimension.Journal of the ACM (JACM), 36(4):929–965, 1989","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:58.989888Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:95604bc42d333a683b84e74e4bb677aafde1629e6d416c7bd0a1b6fdec916232","observation_id":"0ac7064e-abdf-4064-917d-71a62f3354ac","resolution":{"observed_at":"2026-08-05T13:12:58.989888Z","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":"2026-08-05T13:12:58.992443Z","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":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:58.992443Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:847f931073ecf37964fa3076c6cbce8274ec57182f42ce36972d64c2b4470194","observation_id":"cbbe501b-5dd6-4cf5-a633-3e4a3cc179fd","resolution":{"observed_at":"2026-08-05T13:12:58.992443Z","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":"2026-08-05T13:12:58.995132Z","title":"Practical existence theorems for deep learning approximation in high dimensions","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:58.995132Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:92afb0941eb96d9cc85b08db1285430f3b35dfd3042ec4d2a3e6ae2d34578400","observation_id":"2f6b2482-f72b-449c-aee3-66d174bd9c97","resolution":{"observed_at":"2026-08-05T13:12:58.995132Z","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":"2406.01539","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T13:12:59.509970Z","title":"Physics-informed deep learning and compressive collocation for high-dimensional diffusion-reaction equations: practical existence theory and numerics","venue":null,"work_id":"42b42b0d-8a40-4d0f-a02d-662ef3719892","year":2024},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:58.998432Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:e77a264e2f780249a44b87c59bc4c7f2e3d319adb667c5124c686b30a711dfa0","observation_id":"cba87364-3241-422b-ab26-297d84e0e616","resolution":{"observed_at":"2026-08-05T13:12:59.516228Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:12:59.001778Z","title":"Physics-informed neural networks (pinns) for fluid mechanics: A review.Acta Mechanica Sinica, 37(12):1727–1738, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.001778Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:4afd132c8f9a8d99e7803a298cd7623d5599f69ece66dd797393da18d09e612d","observation_id":"72404f47-b882-4603-b8e2-d20b87283036","resolution":{"observed_at":"2026-08-05T13:12:59.001778Z","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":"2026-08-05T13:12:59.005021Z","title":"Dimension-free log-sobolev inequalities for mixture distributions","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.005021Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:312c968b2f9b86caf617c9071f24631e005a1a5f465fd4d9af394747d8bcc7b9","observation_id":"436a3680-a451-4c07-aab9-6f4983f8ed6c","resolution":{"observed_at":"2026-08-05T13:12:59.005021Z","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":"2026-08-05T13:12:59.008128Z","title":"Characterizing overfitting in kernel ridgeless regression through the eigenspectrum","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.008128Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:e5796b627ad5fe44fc0dae72f4e323fae7abf4c6b8190624c8f91df0bebf1d92","observation_id":"8d156383-6769-4ac1-bd77-a1e30b0a0576","resolution":{"observed_at":"2026-08-05T13:12:59.008128Z","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":"2026-08-05T13:12:59.011106Z","title":"A comprehensive analysis on the learning curve in kernel ridge regression.Advancesin Neural Information Processing Systems, 37:24659–24723, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.011106Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:1d8444424d17d4cb498cfddde251fc1ab8385a287b498634e20e587e0755b4f8","observation_id":"d632b125-9cac-4be8-8872-821a1dc865f8","resolution":{"observed_at":"2026-08-05T13:12:59.011106Z","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":"2026-08-05T13:12:59.014183Z","title":"A theoretical analysis of the test error of finite-rank kernel ridge regression","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.014183Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:c30a7247a67cfa9726df522b87dbea58a92fe40616160ba760d14fd7df4b2e21","observation_id":"ac7f57df-f598-4dcf-b3b5-c923bb2fad95","resolution":{"observed_at":"2026-08-05T13:12:59.014183Z","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":"2026-08-05T13:12:59.017510Z","title":"Efficient approximation of high-dimensional functions with neural networks.IEEE Transactions on Neural Networks and Learning Systems, 33(7):3079– 3093, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.017510Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:5ccc33af25cd9e03fbcab552230b6d69dd9bd49b1d2b0fd5b079be5d375ca6a4","observation_id":"285a296e-2c36-485d-9f58-84e86e4c39ec","resolution":{"observed_at":"2026-08-05T13:12:59.017510Z","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":"2026-08-05T13:12:59.020516Z","title":"Optimal stable nonlinear approximation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.020516Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:9abbe59ce7494bfd643539514f4ff3ec5a146e9c72b45fd7493e001f3d067e4c","observation_id":"2a6daafd-c40b-4ea1-ae52-01b1df6420d6","resolution":{"observed_at":"2026-08-05T13:12:59.020516Z","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":"2026-08-05T13:12:59.023556Z","title":"An improved uniform convergence bound with fat-shattering dimension","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.023556Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:94912a448a8d0760f9eb0b20dec2fc60bc9e4959c60a1e671819a3723e2bb292","observation_id":"58f9f023-b057-4a09-9c20-a51efdc8d37d","resolution":{"observed_at":"2026-08-05T13:12:59.023556Z","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":"2026-08-05T13:12:59.026735Z","title":"Scientific machine learning through physics–informed neural networks: Where we are and what’s next","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.026735Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:b907b9b7132ebb199d471c9a73d61d25a80915090aa526f586fb00e0aac3e21a","observation_id":"0e799f20-35ca-4e09-8d4e-1d41f7109eaf","resolution":{"observed_at":"2026-08-05T13:12:59.026735Z","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":"2026-08-05T13:12:59.030015Z","title":"Approximation by superpositions of a sigmoidal function.Mathematics of Control, Signals and Systems, 2(4):303–314, 1989","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.030015Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:068cd554b692c8d88b86f346f6462fed7cca3fe3107de846299a8084b787254d","observation_id":"67310d2b-505a-4eb0-8a7e-336300263a0f","resolution":{"observed_at":"2026-08-05T13:12:59.030015Z","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":"2026-08-05T13:12:59.033092Z","title":"Nonlinear approxima- tion and (deep) relu networks.Constructive Approximation, 55(1):127–172, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.033092Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:6dbfd6bac44a712dc49465e3823913b2176f48be9949a51ab1223d70a1e4d647","observation_id":"f52cc146-0b67-4e24-8c00-a0eabd6b6003","resolution":{"observed_at":"2026-08-05T13:12:59.033092Z","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":"2026-08-05T13:12:59.035996Z","title":"Rogue waves and large deviations in deep sea","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.035996Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:a5d02b4e0c99dbf2a33bafb2e9d62184e3fc1686e1ed33d1e79ed09d46611a68","observation_id":"24114f97-7106-4387-92e7-4aeb6a8334b6","resolution":{"observed_at":"2026-08-05T13:12:59.035996Z","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":"2026-08-05T13:12:59.038939Z","title":null,"venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.038939Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:550879797e3a617831bd96fab91aac664a4bcc39905aa840afeafad71401fd9d","observation_id":"4aebdae8-24ab-4f21-88d2-c2ddda60e82d","resolution":{"observed_at":"2026-08-05T13:12:59.038939Z","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":"2026-08-05T13:12:59.041686Z","title":"Wavelet compression and nonlinear n-widths","venue":null,"work_id":null,"year":1993},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.041686Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:9f3bdc8fdcc1db048e4050267b1a6bad9c67f2c2c269d401a319ac7b0a53b553","observation_id":"cc13991b-8f30-44ee-ac7e-c1e9d685925a","resolution":{"observed_at":"2026-08-05T13:12:59.041686Z","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":"2026-08-05T13:12:59.045049Z","title":"Learning multivariate log-concave distributions","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.045049Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:658caef9136d60b0cdba4b2a7741d5c23a57cc224f8ff0d12fccca792a889cdf","observation_id":"ac034326-5f99-4e49-9988-e7d5636342e8","resolution":{"observed_at":"2026-08-05T13:12:59.045049Z","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":"2026-08-05T13:12:59.048013Z","title":"Memorization with neural nets: Going beyond the worst case","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.048013Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:2bf07015ee3edbd22f2e5052a5ceaacaa681a1132f8fc9d07b3c31c63d5c481e","observation_id":"9060280e-0d96-4d60-ae05-e36f5bd9a47b","resolution":{"observed_at":"2026-08-05T13:12:59.048013Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.11008","last_updated":"2017-10-19T03:39:56Z","snapshot_observed_at":"2026-07-06T05:36:05.666091Z","submitted_at":"2017-03-31T17:56:41Z","title":"Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.11008","snapshot_observed_at":"2026-08-05T13:12:59.051449Z","title":"Computing nonvacuous generalization bounds for deep (stochastic) neural networks with many more parameters than training data.arXiv preprint arXiv:1703.11008, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.051449Z"},"links":{"cited_paper":"/paper/1703.11008","citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:daf85f831b27c8148574f4e17ccd4427d0dbf5420008ecc56f67dc9f0cd0fb5b","observation_id":"e9e4f37f-4da6-4f9e-abe6-13fdd7af4e62","resolution":{"observed_at":"2026-08-05T13:12:59.051449Z","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":"2026-08-05T13:12:59.054961Z","title":"Vc dimension of graph neural networks with pfaffian activation functions.Neural Networks, 182:106924, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.054961Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:aa9fd402c408132ae940ff763063e94ceb93a2fe218f92c0acaf7ed45f179bc6","observation_id":"4c75714e-c378-430a-a60e-db34d7653857","resolution":{"observed_at":"2026-08-05T13:12:59.054961Z","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":"2026-08-05T13:12:59.058379Z","title":"On the efficiency of erm in feature learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.058379Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:1d03a067700c45319e7dd18869f6973da2b40d2a78efb5bffad44344cb0e0053","observation_id":"096939c5-976d-48b0-a51f-be10e6429db5","resolution":{"observed_at":"2026-08-05T13:12:59.058379Z","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":"2026-08-05T13:12:59.061498Z","title":"Springer, 1997","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.061498Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:1cddc3641daa1dba59ea843bf309d92568c7c66f0dcae4f77c602d68020d3dec","observation_id":"4d2470b8-43e1-4b21-9a04-7e6cb00600d4","resolution":{"observed_at":"2026-08-05T13:12:59.061498Z","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":"2026-08-05T13:12:59.064317Z","title":"Benefits of additive noise in composing classes with bounded capacity","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.064317Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:035ca90a35082eee83eaf7de459aba1a717e621bd93f19b54ef60a4f2a9be0b3","observation_id":"947af7e8-690a-46fd-980f-80230c689ddc","resolution":{"observed_at":"2026-08-05T13:12:59.064317Z","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":"2026-08-05T13:12:59.067270Z","title":"Sum-of-squares proofs of logarithmic sobolev inequalities on finite markov chains","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.067270Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:22b3d08a9b0dd09e66708ef8ff4fab53901deb0e66a23a3db57fcabf87d1786f","observation_id":"66f5a519-e1c8-4937-952f-746b9b7a15cd","resolution":{"observed_at":"2026-08-05T13:12:59.067270Z","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":"2026-08-05T13:12:59.070228Z","title":"Efficient graph-based image segmentation.International Journal of Computer Vision, 59(2):167–181, 2004","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.070228Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:4d1a282dcbdd88be39b45b054ac2d892bf063c316a37932b70b4ba7699f0b596","observation_id":"71f3fa5d-502b-4dc7-9304-d685574325db","resolution":{"observed_at":"2026-08-05T13:12:59.070228Z","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":"2026-08-05T13:12:59.073094Z","title":"Sample compression, learnability, and the vapnik-chervonenkis dimension","venue":null,"work_id":null,"year":1995},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.073094Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:d6424008d5313b827771d0815e56376d1b337efc60aa22972ddd6504f2f060a7","observation_id":"3784bf5c-19ac-4aa4-8151-51819bf2b53d","resolution":{"observed_at":"2026-08-05T13:12:59.073094Z","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":"2026-08-05T13:13:00.306872Z","title":"A practical existence theorem for reduced order models based on convolutional autoencoders.Foundations of Data Science, 7(1):72–98, 2025","venue":null,"work_id":"db09a1cc-34a5-4349-a9db-8cba1a30a15f","year":2025},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.076557Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:c2e5d4cbd8d25f40540487affca5f5a6edaecbf4420f96322e9f3baca1776a90","observation_id":"257efec6-902b-43a7-b6b2-d0e8fe6186a6","resolution":{"observed_at":"2026-08-05T13:13:00.310689Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:13:00.294241Z","title":"Benign overfitting without linearity: Neural network classifiers trained by gradient descent for noisy linear data","venue":null,"work_id":"9309a5f2-b645-404b-984e-e5d02244f951","year":2022},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.079580Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:47d4ea09da4bd082bc8100e0693d96302ede4f799846c86a5c5c43c575d30304","observation_id":"026dd872-161a-4278-a995-0a98b385c809","resolution":{"observed_at":"2026-08-05T13:13:00.298753Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:13:00.282967Z","title":"On the approximate realization of continuous mappings by neural networks.Neural networks, 2(3):183–192, 1989","venue":null,"work_id":"d4f624bd-80d8-448f-93be-c8c57c631d41","year":1989},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.082455Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:a329e8bd7f3f0da4a9eeb3a3779a248d128782b8968327e33e6270c90472a0d2","observation_id":"2ce89b83-8b00-4725-9ab6-2f79e360e3e9","resolution":{"observed_at":"2026-08-05T13:13:00.286480Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:13:00.271389Z","title":"Scaling description of generalization with number of parameters in deep learning","venue":null,"work_id":"9bca2b5d-6bb3-4c95-a8ef-f5d23740be90","year":2020},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.085258Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:028e267a3f2a89cf1570d1c570453ed4e74a31d999940e7c19ae45535278e3b5","observation_id":"df8b1230-0488-4559-bb42-c957c305a12b","resolution":{"observed_at":"2026-08-05T13:13:00.274984Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:13:00.258716Z","title":"Random feature neural networks learn black-scholes type pdes without curse of dimensionality","venue":null,"work_id":"e6a19ba6-8ed8-4c70-b017-6468547b3d97","year":2023},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.088149Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:34db3544d88c686b7a563e7a6931def34c574f8254b29666bd4d9664f5adb20e","observation_id":"f06a432a-192f-4afb-bc03-39cda905eb2f","resolution":{"observed_at":"2026-08-05T13:13:00.263034Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:13:00.246360Z","title":"Risk bounds for reservoir computing.Journal of Machine Learning Research, 21(240):1–61, 2020","venue":null,"work_id":"0ebc27fd-f749-488d-8103-9e136b985b74","year":2020},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.090865Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:d10fab5b6ae3127295071e4def8dfd822534194871d7a321559d181507dffd34","observation_id":"1b758a22-ea81-4ba1-9d80-5960b993bb1a","resolution":{"observed_at":"2026-08-05T13:13:00.250116Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:13:00.234658Z","title":"A new proof of szemerédi’s theorem.Geometric & Functional Analysis GAFA, 11(3):465– 588, 2001","venue":null,"work_id":"e8b65fa4-d1cd-46f6-9a65-b27003db5bfc","year":2001},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.093524Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:fd9b787eb9b39261c3ef227b4d1452118d5391aac59929ed77a2d4218c72b865","observation_id":"10ea82f1-372c-4249-9da4-1581a0b0a31e","resolution":{"observed_at":"2026-08-05T13:13:00.238332Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:13:00.222235Z","title":"Universal function approximation by deep neural nets with bounded width and relu activations","venue":null,"work_id":"a7d77916-1f94-4e62-8703-411fe114f538","year":2019},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.096244Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:02c9b9804bc457dcb8765ea547c29e3a298423738505f8de8ced0fd3e997be8a","observation_id":"b1e9f30e-709f-4185-8e0a-2b2b0b0094b6","resolution":{"observed_at":"2026-08-05T13:13:00.225949Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:13:00.210872Z","title":"Probability inequalities for sums of bounded random variables.J","venue":null,"work_id":"6658e50d-59c8-4fe2-9202-0419ecea6c69","year":1963},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.099372Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:6341bd410a17c5c15ad6258ea73294e5e8b10806aa77db1704e95f47ea429cf7","observation_id":"746e2942-bd0b-43f4-a09a-fdc5ab73d076","resolution":{"observed_at":"2026-08-05T13:13:00.214546Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.12335","last_updated":"2025-06-26T04:08:57Z","snapshot_observed_at":"2026-07-06T19:17:51.711221Z","submitted_at":"2024-09-18T22:05:07Z","title":"Bridging the Gap Between Approximation and Learning via Optimal Approximation by ReLU MLPs of Maximal Regularity","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.12335","snapshot_observed_at":"2026-08-05T13:12:59.102611Z","title":"Bridging the gap between approximation and learning via optimal approximation by relu mlps of maximal regularity.arXiv preprint arXiv:2409.12335, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.102611Z"},"links":{"cited_paper":"/paper/2409.12335","citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:06d74f80205a3c04ff3f2d57844e2fd0f5f45d896fddc416b41a2640c0d8799f","observation_id":"08cfef2c-51c7-41e7-82e3-a3ae0305dd92","resolution":{"observed_at":"2026-08-05T13:12:59.102611Z","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":"2026-08-05T13:13:00.199594Z","title":"Horn and Charles R","venue":null,"work_id":"999bb787-217c-4903-82db-cff3d895d4b6","year":2013},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.106339Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:9073b8007cdcb93a9ffae7b9a15fc8db40f956311e11a82bf48ebbc07886e206","observation_id":"158e3600-77b1-4f40-8ed8-6e88ba9992d1","resolution":{"observed_at":"2026-08-05T13:13:00.202989Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:12:59.109136Z","title":"Multilayer feedforward networks are universal approximators","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.109136Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:7bc720bf59e9d88f8c25832d539efdd9845639726cc9a207a0b3ff3ad12a6fc7","observation_id":"f77593e1-e5f7-4b5a-8c45-ab169f382f95","resolution":{"observed_at":"2026-08-05T13:12:59.109136Z","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":"2026-08-05T13:12:59.112083Z","title":"Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks.Neural networks, 3(5):551–560, 1990","venue":null,"work_id":null,"year":1990},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.112083Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:ba9d595bb009534e7834ba623537f5e706d9d380346acbce891743968610358d","observation_id":"997a6988-a872-421a-a3e4-14a68d44b62c","resolution":{"observed_at":"2026-08-05T13:12:59.112083Z","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":"2026-08-05T13:13:00.171873Z","title":"Instance-dependent generalization bounds via optimal transport.Journal of Machine Learning Research, 24(349):1–51, 2023","venue":null,"work_id":"72248930-3eec-432f-940b-d6efc1cad8a8","year":2023},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.115015Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:2006d390f08754ec53b14f8a763d2f878df98418ea27bc6fb2456ad848d87337","observation_id":"e7552dd5-ba2d-4c61-88fb-b62f8add477c","resolution":{"observed_at":"2026-08-05T13:13:00.176332Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:13:00.159194Z","title":"Learning image priors through patch-based diffusion models for solving inverse problems.Advancesin Neural Information Processing Systems, 37:1625–1660, 2024","venue":null,"work_id":"45b3e48f-4b9b-4327-9acf-d883a13869ca","year":2024},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.117900Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:f3de8d216bd74ae186594887d57371f863eb11d0115cf8130abc74d3b16c2892","observation_id":"d969f136-a2dd-4206-b512-655e62077d4f","resolution":{"observed_at":"2026-08-05T13:13:00.163463Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:13:00.147158Z","title":"Neural tangent kernel: Convergence and generalization in neural networks","venue":null,"work_id":"5314936d-4489-47de-a84a-dd557c6ae88f","year":2018},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.120942Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:b750392d28e73839e31933fea5060e09a78e8cba04ffd2f1605a421d019293a4","observation_id":"e0be3bad-c53f-4622-9812-aa9046628b05","resolution":{"observed_at":"2026-08-05T13:13:00.151002Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:13:00.133481Z","title":"Deep neural networks with relu-sine-exponential activations break curse of dimensionality in approximation on hölder class","venue":null,"work_id":"e365b19b-99a1-47b0-8e38-68e2acdf637e","year":2023},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.124379Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:ce22c5976a8286e2951f1fecf67bd63f947b164902840da0e755c8c938192bbd","observation_id":"e83c85af-11ec-4608-9ac0-2b71d11d29e0","resolution":{"observed_at":"2026-08-05T13:13:00.138190Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:13:00.122031Z","title":"Universal approximation with deep narrow networks","venue":null,"work_id":"cfc8328f-2370-424d-8c3f-57ac3c116fa9","year":2020},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.127724Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:b7503842693780fc751393bdd7da6255f041ea2569bec50c4e2faad413024119","observation_id":"dc72d492-8e24-496a-85df-af7b031fe64b","resolution":{"observed_at":"2026-08-05T13:13:00.125790Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:13:00.109995Z","title":"Provable memorization capacity of transformers","venue":null,"work_id":"e519609c-28d0-46c3-97df-157f02d4dab9","year":2023},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.130581Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:63f7b0eacdb7ca88f04555ad5eb5c32eba3b48f63a277dfb2c2b4e699affc008","observation_id":"bcdab113-170f-4eac-a76b-2a2064ca52ff","resolution":{"observed_at":"2026-08-05T13:13:00.113526Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:13:00.098135Z","title":"Benignoverfittingintwo-layerreluconvolutional neural networks","venue":null,"work_id":"d67b93f0-15e0-4f5a-9e9c-61e28f414a11","year":2023},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.133691Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:779ff8c66233c7736c381a71ee5b3af85eade9cb98c306adbfd4ac659e28a17b","observation_id":"8e27d569-e0ae-4d24-a828-38a98b7f22df","resolution":{"observed_at":"2026-08-05T13:13:00.102069Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:12:59.136527Z","title":"Neural operator: Learning maps between function spaces with applications to pdes","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.136527Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:e1c6694965ff2dce924640ddbad280578472aa96c5b5f0fbacdda2412ce7e482","observation_id":"86addfbe-3a60-4943-8ce0-ee385054a6fc","resolution":{"observed_at":"2026-08-05T13:12:59.136527Z","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":"2026-08-05T13:13:00.078302Z","title":"Small transformers compute universal metric embeddings","venue":null,"work_id":"45baadee-e464-4158-8e38-637c441f2e67","year":2023},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.139621Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:02bde2d4ce32d976f543833de47945cc24e7f0c71a63f6a0099240878697193d","observation_id":"a56e90ec-ced0-42a2-a087-3fcc4d7f77a1","resolution":{"observed_at":"2026-08-05T13:13:00.082419Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.03327","last_updated":"2025-02-05T16:22:46Z","snapshot_observed_at":"2026-07-06T20:31:41.231839Z","submitted_at":"2025-02-05T16:22:46Z","title":"Is In-Context Universality Enough? MLPs are Also Universal In-Context","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.03327","snapshot_observed_at":"2026-08-05T13:12:59.142441Z","title":"Is in-context universality enough? mlps are also universal in-context","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.142441Z"},"links":{"cited_paper":"/paper/2502.03327","citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:d22833e07663d5d92f33fdb87740fde44fc019c1f3239fa2fa43a58f47f90adf","observation_id":"176dbf16-26da-40ad-8009-8b4d397fc23b","resolution":{"observed_at":"2026-08-05T13:12:59.142441Z","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":"2026-08-05T13:13:00.065585Z","title":"Universal approximation theorems for differentiable geometric deep learning","venue":null,"work_id":"3322d230-c87f-4d9b-9fc2-695ec44aaae1","year":2022},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.145708Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:b127ab6d59aa2f821a8f93a06552c84254f417a4d9bd223fa29dc3bdf81db55a","observation_id":"81bb2d03-3475-46d6-be2c-21695f9105d6","resolution":{"observed_at":"2026-08-05T13:13:00.070137Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:13:00.053582Z","title":"Sur l’intégration des fonctions discontinues","venue":null,"work_id":"396f4601-d4be-4441-88b2-de5693e44e77","year":1910},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.149361Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:e56e93caf75b1fcfe7b107b30e4ddd15548d96ba3a9168fcc0bfbefd82229e4f","observation_id":"30540c55-3a27-450b-96cf-d5c45d04c6ab","resolution":{"observed_at":"2026-08-05T13:13:00.057526Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:13:00.040507Z","title":"Oracle inequalities for high-dimensional prediction.Bernoulli, 25(2):1225–1255, 2019","venue":null,"work_id":"12cec582-cbbe-4305-9aa7-640925c5b010","year":2019},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.152316Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:d1f74ccd5f3cdfb288483864c092f946bb8f4ca830117d71e4701a6c56943b3f","observation_id":"dddf0e92-6330-421b-978c-c8e37317f49c","resolution":{"observed_at":"2026-08-05T13:13:00.044688Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:13:00.027720Z","title":"Springer-Verlag, Berlin, 1991","venue":null,"work_id":"1f6ca849-e415-474b-ab41-218017547d90","year":1991},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.155320Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:e0950e02526079398e6a30a6ce37b8fba91aa4fc264244e69f3ab6606d8b99f3","observation_id":"63e7e358-402e-445f-b4f4-a824904f7b44","resolution":{"observed_at":"2026-08-05T13:13:00.031713Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:13:00.011554Z","title":"Lower bounds on the vc-dimension of smoothly parametrized function classes","venue":null,"work_id":"7a8505eb-59c6-4084-b90c-50d3747eda6c","year":1994},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.158270Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:543a4878d646c4b4d112529d75159c462cd74e3f736d445994d10bc9554fa9e2","observation_id":"2a1fb042-7d99-498a-a3a6-1714f0057f71","resolution":{"observed_at":"2026-08-05T13:13:00.016177Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.16563","last_updated":"2025-02-06T12:02:36Z","snapshot_observed_at":"2026-08-05T07:00:48.859508Z","submitted_at":"2024-05-26T13:19:32Z","title":"Higher-Order Transformer Derivative Estimates for Explicit Pathwise Learning Guarantees","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.16563","snapshot_observed_at":"2026-08-05T13:12:59.161173Z","title":"Higher-order transformer derivative estimates for explicit pathwise learning guarantees.arXiv preprint arXiv:2405.16563, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.161173Z"},"links":{"cited_paper":"/paper/2405.16563","citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:4a07d9096a6870b74d3e995b8cad1401845ea265a8f9354821609ce254ddf68d","observation_id":"7c873cfe-aec8-48eb-9b9e-cbf4a8df8148","resolution":{"observed_at":"2026-08-05T13:12:59.161173Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1312.4400","last_updated":"2014-03-04T05:15:42Z","snapshot_observed_at":"2026-08-02T17:47:13.893077Z","submitted_at":"2013-12-16T15:34:13Z","title":"Network In Network","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.4400","snapshot_observed_at":"2026-08-05T13:12:59.164642Z","title":"Network in network.arXiv preprint arXiv:1312.4400, 2013","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.164642Z"},"links":{"cited_paper":"/paper/1312.4400","citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:97fc4d36024b5d0ca8fd2942d99f77d52bda8f74ff35447194193b8ddc9dc304","observation_id":"0088cf96-b902-4ff6-8e9a-75492ff46040","resolution":{"observed_at":"2026-08-05T13:12:59.164642Z","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":"2026-08-05T13:12:59.994600Z","title":"Relating data compression and learnability, 1986","venue":null,"work_id":"f4d87097-da8c-47de-894c-bb2934fca0da","year":1986},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.167848Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:5147fcf162c9cb0ad4700fbb4ba647d77dcd481811e9919f901267ec5bdbc05d","observation_id":"6fc56a7f-4828-4f3a-8fa4-559ef720c079","resolution":{"observed_at":"2026-08-05T13:12:59.998305Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:12:59.981951Z","title":"Citeseer, 1996","venue":null,"work_id":"8f1fd5fb-3ff5-4307-8f8e-9a1fb1cbf97a","year":1996},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.170895Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:d1acfa2d6b1d63136c282c6b0a5fb7ac21231c64b2c39daa0678da6e69d743b6","observation_id":"6c96bace-4dd9-488c-928e-9e0afc152a84","resolution":{"observed_at":"2026-08-05T13:12:59.986249Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:12:59.969136Z","title":"Deep network approximation for smooth functions","venue":null,"work_id":"938083f3-0766-425d-b669-4ea60d5a0db3","year":2021},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.173947Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:766d5652fe17cd34a4a5b043b485f91c921cdaec483daae19120e3809ec07631","observation_id":"1b38a275-b6d7-49ec-9627-47cddf6234f7","resolution":{"observed_at":"2026-08-05T13:12:59.973285Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:12:59.957162Z","title":"Learning nonlinear operators via deeponet based on the universal approximation theorem of operators.Nature machineintelligence, 3(3):218–229, 2021","venue":null,"work_id":"961ecbd0-0cd5-4002-b5f3-888210433abb","year":2021},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.176907Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:4b15b3f92c3cce5a700544a6d7fc4e352b40c2cd63bd10ba1c20d85ebcd1ea48","observation_id":"4b30f3b3-ad1a-481b-8dc4-d397bb0cf661","resolution":{"observed_at":"2026-08-05T13:12:59.961050Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:12:59.945190Z","title":"Superpixel-based image segmentation using convex optimization","venue":null,"work_id":"7a4bbf12-fe1e-46c5-aa5b-52c1052604f0","year":2089},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.179779Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:3d346aafca3acc786840e2e49a84a1000373f40dbaddc58ffabbe733930e3a2c","observation_id":"9ae10ef9-8649-4c51-8e1c-c38b68ee8561","resolution":{"observed_at":"2026-08-05T13:12:59.949037Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:12:59.932495Z","title":"Memory capacity of two layer neural networks with smooth activations","venue":null,"work_id":"edb4d556-f094-4e76-b9d9-a37397a14eb1","year":2024},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.182714Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:ff6c5c34a3e3f38101b3a7f97ed5d5ad84e270e33edadcbbdf40f9bc944409ab","observation_id":"573f25b5-449c-48f0-85e9-b486fa14e952","resolution":{"observed_at":"2026-08-05T13:12:59.936535Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:12:59.922573Z","title":"Concentration Inequalities and Model Selection","venue":null,"work_id":"ebe842ec-533f-44e1-8988-ee194d02d8fd","year":2007},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.185419Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:8f39eed7f5f4cd880994e818a30ab016fd499f60872bc293a5fc4039b617608d","observation_id":"fba0bc47-90d7-4a48-af6a-fa2f433139cd","resolution":{"observed_at":"2026-08-05T13:12:59.925859Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:12:59.188688Z","title":"The generalization error of random features regression: Precise asymptotics and the double descent curve.Communications on Pure and Applied Mathematics, 75(4):667–766, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.188688Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:2dacb38d8b7678e79411abc6f97607e6ba87fd824cbcec7e0f1ebe2360bf885a","observation_id":"48950d9c-bfd4-4772-bdf7-d9932b9f7a2d","resolution":{"observed_at":"2026-08-05T13:12:59.188688Z","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":"2026-08-05T13:12:59.905752Z","title":"Understanding the dynamics of the frequency bias in neural networks, 2024","venue":null,"work_id":"dd6a4ccb-39a2-4477-a2a8-2de61f319d97","year":2024},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.192248Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:69dce8b8a7001e9b7136443960d7a082956209de96db53d92ef40c22d518c472","observation_id":"78b784e5-f09c-4db3-8528-86710a652234","resolution":{"observed_at":"2026-08-05T13:12:59.909295Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:12:59.894536Z","title":"Sample compression schemes for vc classes.Journal of the ACM (JACM), 63(3):1–10, 2016","venue":null,"work_id":"92b387da-b48f-4981-bf2e-2bb860834d1a","year":2016},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.194967Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:16a8e309c15f438af06a55c8c10ac60d32c121c3294251b8f9f0404eaab44e27","observation_id":"cca3c2e9-b0a8-487c-aaf3-3d7161527c3c","resolution":{"observed_at":"2026-08-05T13:12:59.897932Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:12:59.884227Z","title":"Simplicity bias in 1-hidden layer neural networks","venue":null,"work_id":"04c9c0c5-2b6f-4bbe-b225-f0c8a61a5071","year":2023},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.198185Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:2fead5646c3cbc4287566f86276e90c58992ecf133fcc50a61cfec8a59d94f7a","observation_id":"522d6279-3232-45db-850f-b6709127a134","resolution":{"observed_at":"2026-08-05T13:12:59.888012Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:12:59.873071Z","title":"Robust feature learning for multi-index models in high dimensions","venue":null,"work_id":"e3bd261f-c579-4b3f-9f4d-61dffa1f7069","year":2024},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.201179Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:4c2a65e27fa49fd35e49d3f3eb004b0d15a531488ddf51ca287f15e3ce8e2b41","observation_id":"b63d93bc-16b8-4ecc-a58c-d357512a98f2","resolution":{"observed_at":"2026-08-05T13:12:59.877108Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.08410","last_updated":"2026-04-27T14:17:09Z","snapshot_observed_at":"2026-07-06T17:01:18.018700Z","submitted_at":"2023-12-13T11:27:15Z","title":"Universal approximation property of Banach space-valued random feature models including random neural networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.08410","snapshot_observed_at":"2026-08-05T13:12:59.203986Z","title":"Universal approximation property of random neural networks.arXiv preprint arXiv:2312.08410, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.203986Z"},"links":{"cited_paper":"/paper/2312.08410","citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:757a6b40cc97b5bb54aa3196ac3f2b428e8a0099de10a0a2c17bee37c28c1d7c","observation_id":"ce33b782-8c76-4f5f-8bb2-30939a58d50e","resolution":{"observed_at":"2026-08-05T13:12:59.203986Z","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":"2026-08-05T13:12:59.862032Z","title":"A PAC-bayesian approach to spectrally- normalized margin bounds for neural networks","venue":null,"work_id":"644e5135-4d0a-4816-a7d3-209ba25c16fd","year":2018},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.207348Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:12181cb745cce37fec89a33820fe737e2f358ddda72cc819403b8ed036593e70","observation_id":"b6619cc1-933b-4a46-8e0a-d1023c0888c3","resolution":{"observed_at":"2026-08-05T13:12:59.865692Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:12:59.850529Z","title":"Fast samplers for inverse problems in iterative refinement models","venue":null,"work_id":"a8dfdbb2-3901-40b8-8361-9f291cbdaf45","year":2024},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.210527Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:4150bcd716fdc794011d7beb012303d6fa50b04eff1b07d262805a37eb47dc72","observation_id":"b4726d83-07a3-448c-9c65-505922e8074b","resolution":{"observed_at":"2026-08-05T13:12:59.853931Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:12:59.213464Z","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":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.213464Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:080a79e727b7c118e561b4f0ed0c2694b89e1335e538ce497064ef184a098012","observation_id":"a5df71a5-201a-4d21-8009-7a05bdc98ae3","resolution":{"observed_at":"2026-08-05T13:12:59.213464Z","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":"2026-08-05T13:12:59.833019Z","title":"Mathematical theory of deep learning.arXiv preprint, 2024","venue":null,"work_id":"6061a5b6-283a-4b8f-94ee-d1adb1f703b1","year":2024},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.216416Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:84777d2f044f119366c10885ffcbbfa550d2b19fea75b79e50a9e83ef793a918","observation_id":"fbea8ccc-c40d-4ad7-9ccd-e4c20acb5a28","resolution":{"observed_at":"2026-08-05T13:12:59.836506Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:12:59.822435Z","title":"Lipschitz widths.ConstructiveApproximation, 57(2):759–805, 2023","venue":null,"work_id":"be3af59e-1720-46a9-9228-2bb721969d39","year":2023},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.219580Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:a00bd9ca8fd4875c08e8e3c18d6823ce3929afa6fa516b78f0aa043faca6c2d6","observation_id":"06c9aeba-d301-4036-afda-7f04b227ce05","resolution":{"observed_at":"2026-08-05T13:12:59.825899Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:12:59.812177Z","title":"n-widths in approximation theory, volume 7 of Ergebnisse der Mathematik und ihrer Grenzgebiete (3) [Results in Mathematics and Related Areas (3)]","venue":null,"work_id":"b46c86a1-72db-4bd3-bc57-cefea9d8dc25","year":1985},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.222956Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:f5b01ef3b0aca184e3ff4d2d93662f7a2409e985525aee0a1fe4cdc1d4a30b47","observation_id":"4f1983e7-3f2a-4dcd-bb93-6f05752812b8","resolution":{"observed_at":"2026-08-05T13:12:59.815676Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:12:59.802089Z","title":"I-theory on depth vs width: hierarchical function composition","venue":null,"work_id":"62c9f5b2-0694-4bd2-ad3c-037547615bb6","year":2015},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.226163Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:a1ca840f685f7395cc38dbb5a75623a3c3271776a5ea8a9bfa2deae1923755a6","observation_id":"57d04c48-57fa-495f-b466-108435c80b6f","resolution":{"observed_at":"2026-08-05T13:12:59.805870Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:12:59.791987Z","title":"Compositional sparsity of learnable functions.Bulletin of the American Mathematical Society, 61(3):438–456, 2024","venue":null,"work_id":"82986584-471d-41f7-accf-203d95b971bd","year":2024},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.229724Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:668f7b3e4ec70969277950f26f4d5b02391aef115c66a71595cb83efdfadb443","observation_id":"0a7aeb68-2b29-4e77-9bba-96edff00503b","resolution":{"observed_at":"2026-08-05T13:12:59.795377Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:12:59.232612Z","title":"Random features for large-scale kernel machines","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.232612Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:881f7267b3339f96d6ed5afe97ece72969f9f26107ac5c73c53a857ab3830050","observation_id":"51cf89b3-2748-4482-89e1-b22c9807a7d2","resolution":{"observed_at":"2026-08-05T13:12:59.232612Z","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":"2026-08-05T13:12:59.774873Z","title":"Learning a classification model for segmentation","venue":null,"work_id":"aca21bfc-91b5-4c00-95e0-26a009778edd","year":2003},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.235629Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:38bb490b37e50dd3039b50ab5aad8be52573dc70bb5c437a2c4ed8e441391412","observation_id":"3278677a-5582-4c3b-b1bf-31c44acc3a80","resolution":{"observed_at":"2026-08-05T13:12:59.778453Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.05109","last_updated":"2026-06-19T12:24:49Z","snapshot_observed_at":"2026-07-06T20:02:53.153763Z","submitted_at":"2024-12-06T15:10:04Z","title":"Generating Rectifiable Measures through Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.05109","snapshot_observed_at":"2026-08-05T13:12:59.238677Z","title":"Generating rectifiable measures through neural networks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.238677Z"},"links":{"cited_paper":"/paper/2412.05109","citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:f3d0240faf64e89dcf5a5969fa169adf5ad4f6a11d662aa12cfb1142044233a0","observation_id":"3ba7776b-be07-48b9-a56e-1d5d51613b9c","resolution":{"observed_at":"2026-08-05T13:12:59.238677Z","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":"2026-08-05T13:12:59.764941Z","title":"Nonparametric regression via deep neural networks.The Annals of Statistics, 48(4):1875–1897, 2020","venue":null,"work_id":"edfd24d8-f892-4dd8-b290-49957bec5570","year":2020},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.242520Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:caf6baffb6f666c59738e246a77735d2bf9f63926df6cf840e760c0f4b73e8db","observation_id":"9158be5c-d05b-4781-b4df-74ae4a796f10","resolution":{"observed_at":"2026-08-05T13:12:59.768606Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.04847","last_updated":"2025-04-07T09:00:22Z","snapshot_observed_at":"2026-08-07T16:08:03.724152Z","submitted_at":"2025-04-07T09:00:22Z","title":"Nonlocal techniques for the analysis of deep ReLU neural network approximations","version":1},"cited_work":{"arxiv_id":"2504.04847","doi":null,"metadata_source":"pith","pith_arxiv_id":"2504.04847","snapshot_observed_at":"2026-08-05T13:12:59.338659Z","title":"Nonlocal techniques for the analysis of deep ReLU neural network approximations","venue":"cs.LG","work_id":"b6a89d80-2676-4058-a08d-8c7fcf60fe7e","year":2025},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.245464Z"},"links":{"cited_paper":"/paper/2504.04847","citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:b3e9bf4189fe896917081da893f0f6d76079b047179aba57efae32e408b3595c","observation_id":"3644dd05-d54a-4f3b-acde-722ae91dac93","resolution":{"observed_at":"2026-08-05T13:12:59.343986Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:12:59.753961Z","title":"A multivariate Riesz basis of ReLU neural networks.Appl","venue":null,"work_id":"3b882386-7515-49d6-aeda-af86733c38db","year":2024},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.248700Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:8a78185ab463acedb3c70fc01f637273fa030a9e1fd0d3f876701593fcb5ff08","observation_id":"6c35d260-12c5-4c72-9dab-c835f7fb3ef3","resolution":{"observed_at":"2026-08-05T13:12:59.757792Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T13:12:59.741619Z","title":"Pac-bayesian generalisation error bounds for gaussian process classification","venue":null,"work_id":"0b12fd31-2bad-4e02-8622-9651b21f080e","year":2002},"citing_paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:59.251659Z"},"links":{"citing_paper":"/paper/2509.00924"},"observation_digest":"sha256:2e83d587ae4fe7fa4288e82d04c0fa5357dafde141faffd3c8c8098f499e506e","observation_id":"73412c9b-aee9-453d-9656-283be00b3030","resolution":{"observed_at":"2026-08-05T13:12:59.744932Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2509.00924","last_updated":"2025-08-31T16:20:27Z","latest_version":1,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-06T22:15:18.072877Z","submitted_at":"2025-08-31T16:20:27Z","title":"Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":52,"verified_exact":3,"verified_fuzzy":45},"total_outbound_references":118},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 100 of 118 outbound references and 1 inbound Pith citation observation for arXiv:2509.00924."}