{"as_of":"2026-08-16T11:20:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6645d146bfe9579e0fcfe25032de4f0d9b37e3fb7d2d64ebbe3168b5d4490316","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":7,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":7,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":7,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":7,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T15:11:57.208703Z","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":"2026-07-03T00:47:30.807766Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1708.02691","last_updated":"2017-12-20T17:38:26Z","snapshot_observed_at":"2026-08-14T20:42:27.113220Z","submitted_at":"2017-08-09T01:37:21Z","title":"Universal Function Approximation by Deep Neural Nets with Bounded Width and ReLU Activations","version":3},"cited_work":{"arxiv_id":"1708.02691","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1708.02691","snapshot_observed_at":"2026-07-03T00:47:30.807766Z","title":"Universal function approximation by deep neural nets with bounded width and relu activations","venue":null,"work_id":"1dfc35de-a276-45e4-b345-020089b8c94d","year":2017},"citing_paper":{"arxiv_id":"1906.11235","last_updated":"2019-06-26T17:57:10Z","snapshot_observed_at":"2026-08-05T12:05:41.221966Z","submitted_at":"2019-06-26T17:57:10Z","title":"Invariance-inducing regularization using worst-case transformations suffices to boost accuracy and spatial robustness","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-25T15:42:57.529773Z"},"links":{"cited_paper":"/paper/1708.02691","citing_paper":"/paper/1906.11235"},"observation_digest":"sha256:5d9d08297fc191bc51fba7acf87c01603a61bf242c6aba9ae50edc84e0386f70","observation_id":"fee70d4e-034a-4446-85cd-d215469662dc","resolution":{"observed_at":"2026-05-25T15:45:59.661062Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1708.02691","last_updated":"2017-12-20T17:38:26Z","snapshot_observed_at":"2026-08-14T20:42:27.113220Z","submitted_at":"2017-08-09T01:37:21Z","title":"Universal Function Approximation by Deep Neural Nets with Bounded Width and ReLU Activations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.02691","snapshot_observed_at":"2026-08-14T15:11:57.208703Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.01842","last_updated":"2022-02-22T23:41:01Z","snapshot_observed_at":"2026-08-15T18:35:27.221140Z","submitted_at":"2019-08-05T20:22:29Z","title":"Nonparametric Regression on Low-Dimensional Manifolds using Deep ReLU Networks : Function Approximation and Statistical Recovery","version":5},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-14T15:11:57.208703Z"},"links":{"cited_paper":"/paper/1708.02691","citing_paper":"/paper/1908.01842"},"observation_digest":"sha256:2346e25fa216c51babe5e8c5e194ccbf673690ce43766a383e461cfe97d82840","observation_id":"ead81ccd-72d9-4b21-a7f4-fe8f62c0f43a","resolution":{"observed_at":"2026-08-14T15:11:57.208703Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.02691","last_updated":"2017-12-20T17:38:26Z","snapshot_observed_at":"2026-08-14T20:42:27.113220Z","submitted_at":"2017-08-09T01:37:21Z","title":"Universal Function Approximation by Deep Neural Nets with Bounded Width and ReLU Activations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.02691","snapshot_observed_at":"2026-08-14T11:36:40.037460Z","title":"Universal function approximation by deep neural nets with bounded width and relu activations,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.08594","last_updated":"2019-08-29T23:11:08Z","snapshot_observed_at":"2026-08-14T11:31:46.325608Z","submitted_at":"2019-08-23T00:58:21Z","title":"Training Optimus Prime, M.D.: Generating Medical Certification Items by Fine-Tuning OpenAI's gpt2 Transformer Model","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T11:36:40.037460Z"},"links":{"cited_paper":"/paper/1708.02691","citing_paper":"/paper/1908.08594"},"observation_digest":"sha256:1bed5552adced27d3bfdd97f3509f56e5d1b52a27564cf0a4a3e3dedf4f9552d","observation_id":"58e4f88d-fd94-4825-94e8-ff5bf30bdd3a","resolution":{"observed_at":"2026-08-14T11:36:40.037460Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.02691","last_updated":"2017-12-20T17:38:26Z","snapshot_observed_at":"2026-08-14T20:42:27.113220Z","submitted_at":"2017-08-09T01:37:21Z","title":"Universal Function Approximation by Deep Neural Nets with Bounded Width and ReLU Activations","version":3},"cited_work":{"arxiv_id":"1708.02691","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1708.02691","snapshot_observed_at":"2026-07-03T00:47:30.807766Z","title":"Universal function approximation by deep neural nets with bounded width and relu activations","venue":null,"work_id":"1dfc35de-a276-45e4-b345-020089b8c94d","year":2017},"citing_paper":{"arxiv_id":"1910.03193","last_updated":"2020-04-15T00:51:54Z","snapshot_observed_at":"2026-08-15T10:02:22.851586Z","submitted_at":"2019-10-08T03:21:14Z","title":"DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-15T03:17:25.281108Z"},"links":{"cited_paper":"/paper/1708.02691","citing_paper":"/paper/1910.03193"},"observation_digest":"sha256:23a2510f54f1ac3581b8c052f81c3b050d1a86b2b91e20af2b36b0d729a11b30","observation_id":"faff3d9f-20c7-4a41-bcc2-2c92c3173cc4","resolution":{"observed_at":"2026-05-15T03:17:25.366854Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1708.02691","last_updated":"2017-12-20T17:38:26Z","snapshot_observed_at":"2026-08-14T20:42:27.113220Z","submitted_at":"2017-08-09T01:37:21Z","title":"Universal Function Approximation by Deep Neural Nets with Bounded Width and ReLU Activations","version":3},"cited_work":{"arxiv_id":"1708.02691","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1708.02691","snapshot_observed_at":"2026-07-03T00:47:30.807766Z","title":"Universal function approximation by deep neural nets with bounded width and relu activations","venue":null,"work_id":"1dfc35de-a276-45e4-b345-020089b8c94d","year":2017},"citing_paper":{"arxiv_id":"2112.14523","last_updated":"2026-04-28T23:07:38Z","snapshot_observed_at":"2026-08-16T07:55:00.690393Z","submitted_at":"2021-12-29T12:29:23Z","title":"Deep neural network approximation theory for high-dimensional functions","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-05-24T12:37:24.021894Z"},"links":{"cited_paper":"/paper/1708.02691","citing_paper":"/paper/2112.14523"},"observation_digest":"sha256:79d8edc0d2b02d838f04c8077154ae996b98c34dcbea9cfd1d17d49c4ff14386","observation_id":"95d48016-bba6-49cb-88c1-8471e15fca47","resolution":{"observed_at":"2026-05-24T12:39:29.122660Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1708.02691","last_updated":"2017-12-20T17:38:26Z","snapshot_observed_at":"2026-08-14T20:42:27.113220Z","submitted_at":"2017-08-09T01:37:21Z","title":"Universal Function Approximation by Deep Neural Nets with Bounded Width and ReLU Activations","version":3},"cited_work":{"arxiv_id":"1708.02691","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1708.02691","snapshot_observed_at":"2026-07-03T00:47:30.807766Z","title":"Universal function approximation by deep neural nets with bounded width and relu activations","venue":null,"work_id":"1dfc35de-a276-45e4-b345-020089b8c94d","year":2017},"citing_paper":{"arxiv_id":"2401.01335","last_updated":"2024-06-14T21:17:17Z","snapshot_observed_at":"2026-08-15T08:59:30.302596Z","submitted_at":"2024-01-02T18:53:13Z","title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","version":3},"reference_index":185,"source":"arxiv_source","source_observed_at":"2026-05-14T23:00:20.720030Z"},"links":{"cited_paper":"/paper/1708.02691","citing_paper":"/paper/2401.01335"},"observation_digest":"sha256:bc471909cc98febaad9a80a6cb10d07630f30f3b9ad4815be8a5dc25d6bb033e","observation_id":"0a210c41-b5af-4248-b917-d9450c1fc6d2","resolution":{"observed_at":"2026-05-14T23:00:21.201381Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1708.02691","last_updated":"2017-12-20T17:38:26Z","snapshot_observed_at":"2026-08-14T20:42:27.113220Z","submitted_at":"2017-08-09T01:37:21Z","title":"Universal Function Approximation by Deep Neural Nets with Bounded Width and ReLU Activations","version":3},"cited_work":{"arxiv_id":"1708.02691","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1708.02691","snapshot_observed_at":"2026-07-03T00:47:30.807766Z","title":"Universal function approximation by deep neural nets with bounded width and relu activations","venue":null,"work_id":"1dfc35de-a276-45e4-b345-020089b8c94d","year":2017},"citing_paper":{"arxiv_id":"2606.10089","last_updated":"2026-06-08T19:16:32Z","snapshot_observed_at":"2026-08-12T09:27:24.769295Z","submitted_at":"2026-06-08T19:16:32Z","title":"A Theory on Flow Matching with Neural Networks","version":1},"reference_index":211,"source":"arxiv_source","source_observed_at":"2026-06-27T16:59:34.084575Z"},"links":{"cited_paper":"/paper/1708.02691","citing_paper":"/paper/2606.10089"},"observation_digest":"sha256:6ad74723ffadf8e270ca0e2a37946ea5607025f18fa22d3886f6dea12a470d65","observation_id":"91a41d86-68d8-4fd2-b994-0c8e04c46263","resolution":{"observed_at":"2026-07-03T00:47:30.809391Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/1708.02691/citation-record","integrity":"/paper/1708.02691/integrity","json":"/paper/1708.02691/citation-record.json","paper":"/paper/1708.02691"},"outbound":[],"paper":{"arxiv_id":"1708.02691","last_updated":"2017-12-20T17:38:26Z","latest_version":3,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-14T20:42:27.113220Z","submitted_at":"2017-08-09T01:37:21Z","title":"Universal Function Approximation by Deep Neural Nets with Bounded Width and ReLU Activations"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 7 inbound Pith citation observations for arXiv:1708.02691."}