{"as_of":"2026-08-09T18:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7062ece81fe35c74176f29eac31e62bce89847e238693988586cbfd9c99f0452","coverage":[{"denominator":28,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":28,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-14T16:20:15.771616Z","state":"measured"},{"denominator":28,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":28,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.04597/citation-record","integrity":"/paper/2607.04597/integrity","json":"/paper/2607.04597/citation-record.json","paper":"/paper/2607.04597"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T16:20:15.771616Z","title":"Discrete and Continuous Dynamical Systems - B 29(1):351–376","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.04597","last_updated":"2026-07-13T05:25:49Z","snapshot_observed_at":"2026-08-06T19:52:26.021534Z","submitted_at":"2026-07-06T01:58:37Z","title":"Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-14T16:20:15.771616Z"},"links":{"citing_paper":"/paper/2607.04597"},"observation_digest":"sha256:cbd4ad85b95f1212992902a2ecf7d799aefc2f7fd6d56e7d1f31913ca1eac856","observation_id":"adc85753-217e-4882-9b2f-f79f1b59d082","resolution":{"observed_at":"2026-07-14T16:20:15.771616Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T16:20:15.771616Z","title":"Springer, Cham, https://doi.org/10.1007/978-3-030-33143-6","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.04597","last_updated":"2026-07-13T05:25:49Z","snapshot_observed_at":"2026-08-06T19:52:26.021534Z","submitted_at":"2026-07-06T01:58:37Z","title":"Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-14T16:20:15.771616Z"},"links":{"citing_paper":"/paper/2607.04597"},"observation_digest":"sha256:115c90f7c56ee3816e2ed7f517a0f44804a4b4d508168f4ca1b224348e37d5d0","observation_id":"62b783ec-a9e6-440b-b33f-d9719fa3935a","resolution":{"observed_at":"2026-07-14T16:20:15.771616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T16:20:15.771616Z","title":"In: The Eleventh International Conference on Learning Representations","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.04597","last_updated":"2026-07-13T05:25:49Z","snapshot_observed_at":"2026-08-06T19:52:26.021534Z","submitted_at":"2026-07-06T01:58:37Z","title":"Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-14T16:20:15.771616Z"},"links":{"citing_paper":"/paper/2607.04597"},"observation_digest":"sha256:00adb12d6924de1ab7c0c5d595a3c167750a41eea762aec530e419c3445a9f8c","observation_id":"d366ca11-c9c6-40d2-8dd8-984960b6b215","resolution":{"observed_at":"2026-07-14T16:20:15.771616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T16:20:15.771616Z","title":"In: Advances in Neural Information Processing Systems, pp 3134–3144","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.04597","last_updated":"2026-07-13T05:25:49Z","snapshot_observed_at":"2026-08-06T19:52:26.021534Z","submitted_at":"2026-07-06T01:58:37Z","title":"Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-14T16:20:15.771616Z"},"links":{"citing_paper":"/paper/2607.04597"},"observation_digest":"sha256:6cf39fb8a0709d4ad2491d6e4f01955689f2af71fe4d52018d394590d8b42754","observation_id":"fb71a902-7ba8-4e06-81b9-9580fbf802c3","resolution":{"observed_at":"2026-07-14T16:20:15.771616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T16:20:15.771616Z","title":"Com- munications in Mathematics and Statistics 5(1):1–11","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.04597","last_updated":"2026-07-13T05:25:49Z","snapshot_observed_at":"2026-08-06T19:52:26.021534Z","submitted_at":"2026-07-06T01:58:37Z","title":"Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-14T16:20:15.771616Z"},"links":{"citing_paper":"/paper/2607.04597"},"observation_digest":"sha256:21ab3cbab4f5cb1d116ea152f0810d7de7e1b1ead0b2e73c6f8d84f373826e03","observation_id":"e5dcd18c-4389-485d-b51b-38193ee1ec55","resolution":{"observed_at":"2026-07-14T16:20:15.771616Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T16:20:15.771616Z","title":"American Mathematical Society, Providence, RI, https: //doi.org/10.1090/gsm/019","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2607.04597","last_updated":"2026-07-13T05:25:49Z","snapshot_observed_at":"2026-08-06T19:52:26.021534Z","submitted_at":"2026-07-06T01:58:37Z","title":"Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-14T16:20:15.771616Z"},"links":{"citing_paper":"/paper/2607.04597"},"observation_digest":"sha256:2c5a08c62642115ff20ab133a84a975483c3588cfc1497f49cde15dc865d9bef","observation_id":"b86cc8ec-d8bd-4d9b-acbb-774018efdb08","resolution":{"observed_at":"2026-07-14T16:20:15.771616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.11278","last_updated":"2018-03-10T21:47:40Z","snapshot_observed_at":"2026-08-07T05:58:20.280741Z","submitted_at":"2017-10-31T00:26:56Z","title":"Approximating Continuous Functions by ReLU Nets of Minimal Width","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.11278","snapshot_observed_at":"2026-07-14T16:20:15.771616Z","title":"arXiv preprint arXiv:1710.11278 [stat.ML]","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.04597","last_updated":"2026-07-13T05:25:49Z","snapshot_observed_at":"2026-08-06T19:52:26.021534Z","submitted_at":"2026-07-06T01:58:37Z","title":"Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-14T16:20:15.771616Z"},"links":{"cited_paper":"/paper/1710.11278","citing_paper":"/paper/2607.04597"},"observation_digest":"sha256:9f976a2c17e9aebbac30552ebfbb22de01fae6e7392752f5a72cbfd52b514208","observation_id":"821daf5a-a42f-404e-a426-cfd84c03677b","resolution":{"observed_at":"2026-07-14T16:20:15.771616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T16:20:15.771616Z","title":"In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.04597","last_updated":"2026-07-13T05:25:49Z","snapshot_observed_at":"2026-08-06T19:52:26.021534Z","submitted_at":"2026-07-06T01:58:37Z","title":"Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-14T16:20:15.771616Z"},"links":{"citing_paper":"/paper/2607.04597"},"observation_digest":"sha256:b36a88c756cda815576693f1b036859a34bf0dfe5710ab05ba289cc5f34f1a6b","observation_id":"9a2f3ef3-34e2-4a39-b629-823ff9188fe2","resolution":{"observed_at":"2026-07-14T16:20:15.771616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T16:20:15.771616Z","title":"In: Proceedings of the IEEE International Conference on Computer Vision, pp 2961–2969","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.04597","last_updated":"2026-07-13T05:25:49Z","snapshot_observed_at":"2026-08-06T19:52:26.021534Z","submitted_at":"2026-07-06T01:58:37Z","title":"Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-14T16:20:15.771616Z"},"links":{"citing_paper":"/paper/2607.04597"},"observation_digest":"sha256:20612cf7ae48f40ebea15a78c514b038c583d4f5883bdf76174357dc143548a3","observation_id":"be25617c-7439-4d7f-aad7-0ca0e249b2b4","resolution":{"observed_at":"2026-07-14T16:20:15.771616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T16:20:15.771616Z","title":"In: Belgrave D, Zhang C, Lin H, et al (eds) Advances in Neural Infor- mation Processing Systems, vol 38","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.04597","last_updated":"2026-07-13T05:25:49Z","snapshot_observed_at":"2026-08-06T19:52:26.021534Z","submitted_at":"2026-07-06T01:58:37Z","title":"Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-14T16:20:15.771616Z"},"links":{"citing_paper":"/paper/2607.04597"},"observation_digest":"sha256:1ef516717bb9bb0637f011dcfa106f0efefd7136ed7da95af08b82be8a4e6ebe","observation_id":"f3eeafec-0c3e-4244-91bd-4d35f603ee6b","resolution":{"observed_at":"2026-07-14T16:20:15.771616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.00393","last_updated":"2018-09-30T14:55:41Z","snapshot_observed_at":"2026-08-01T17:43:51.083230Z","submitted_at":"2018-09-30T14:55:41Z","title":"Deep, Skinny Neural Networks are not Universal Approximators","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.00393","snapshot_observed_at":"2026-07-14T16:20:15.771616Z","title":"arXiv preprint arXiv:1810.00393 [cs.LG]","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.04597","last_updated":"2026-07-13T05:25:49Z","snapshot_observed_at":"2026-08-06T19:52:26.021534Z","submitted_at":"2026-07-06T01:58:37Z","title":"Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-14T16:20:15.771616Z"},"links":{"cited_paper":"/paper/1810.00393","citing_paper":"/paper/2607.04597"},"observation_digest":"sha256:aca33b4609fdaa20e8a06fc94c8ddf612ee54f91cd0eb59f56b62354fdc6e28c","observation_id":"9ae3c6f5-f6f1-4434-ad95-cf9d6a070acb","resolution":{"observed_at":"2026-07-14T16:20:15.771616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T16:20:15.771616Z","title":"In: Conference on learning theory, PMLR, pp 2306–2327","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.04597","last_updated":"2026-07-13T05:25:49Z","snapshot_observed_at":"2026-08-06T19:52:26.021534Z","submitted_at":"2026-07-06T01:58:37Z","title":"Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-14T16:20:15.771616Z"},"links":{"citing_paper":"/paper/2607.04597"},"observation_digest":"sha256:1405c12bb93ca0e7559f9e6fb00b27bef1ffb6c60f0bc269e660895b584866a3","observation_id":"25ea4329-d5fe-4a0e-8baf-885e645b35d7","resolution":{"observed_at":"2026-07-14T16:20:15.771616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T16:20:15.771616Z","title":"In: Kim B, Yue Y, Chaudhuri S, et al (eds) International Conference on Representation Learning, pp 3097–3130 32","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.04597","last_updated":"2026-07-13T05:25:49Z","snapshot_observed_at":"2026-08-06T19:52:26.021534Z","submitted_at":"2026-07-06T01:58:37Z","title":"Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-14T16:20:15.771616Z"},"links":{"citing_paper":"/paper/2607.04597"},"observation_digest":"sha256:0207e9f98ab386506e897d6089736d306c09620008ecc414b8d97c81206b5b0a","observation_id":"24ae57ce-fa5d-4cd0-8bed-eae72681454c","resolution":{"observed_at":"2026-07-14T16:20:15.771616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-07-14T16:20:15.771616Z","title":"In: Inter- national Conference on Learning Representations, San Diego, CA, USA, URL https://arxiv.org/abs/1412.6980","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.04597","last_updated":"2026-07-13T05:25:49Z","snapshot_observed_at":"2026-08-06T19:52:26.021534Z","submitted_at":"2026-07-06T01:58:37Z","title":"Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-14T16:20:15.771616Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2607.04597"},"observation_digest":"sha256:aabc4eda18c178ba3ff1ff7b78e934f3d901451d434e1da6eaaf52583f8219bf","observation_id":"0ad5d28e-0c9c-4bb2-aec4-313332f1a706","resolution":{"observed_at":"2026-07-14T16:20:15.771616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T16:20:15.771616Z","title":"Journal of the European Mathematical Society 25(5):1671–1709","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.04597","last_updated":"2026-07-13T05:25:49Z","snapshot_observed_at":"2026-08-06T19:52:26.021534Z","submitted_at":"2026-07-06T01:58:37Z","title":"Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-14T16:20:15.771616Z"},"links":{"citing_paper":"/paper/2607.04597"},"observation_digest":"sha256:fb18d51388e9f9a400b7a5f427953730d4a8b45315fe0eb7c7f2b43b5421f706","observation_id":"bf69e126-7a82-40d1-876e-338de6723bd6","resolution":{"observed_at":"2026-07-14T16:20:15.771616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T16:20:15.771616Z","title":"In: Advances in Neural Information Processing Systems, vol 31","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.04597","last_updated":"2026-07-13T05:25:49Z","snapshot_observed_at":"2026-08-06T19:52:26.021534Z","submitted_at":"2026-07-06T01:58:37Z","title":"Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-14T16:20:15.771616Z"},"links":{"citing_paper":"/paper/2607.04597"},"observation_digest":"sha256:12d8772e30ae8e05b35a564a257643ba3d4e84b6e1160936cd4d98fad4235bf3","observation_id":"7eaa6776-02bb-4d06-b05a-1e43b5315ddd","resolution":{"observed_at":"2026-07-14T16:20:15.771616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T16:20:15.771616Z","title":"In: Proceedings of the 41st International Conference on Machine Learning, Proceedings of Machine Learning Research, vol 235","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.04597","last_updated":"2026-07-13T05:25:49Z","snapshot_observed_at":"2026-08-06T19:52:26.021534Z","submitted_at":"2026-07-06T01:58:37Z","title":"Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-14T16:20:15.771616Z"},"links":{"citing_paper":"/paper/2607.04597"},"observation_digest":"sha256:8ee7bc50ce234eb13f7641e993b909a6ed78f9460ce84b69696c084ca719403b","observation_id":"762ec2e7-7e30-4a5c-8a4c-9d8ab1917070","resolution":{"observed_at":"2026-07-14T16:20:15.771616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T16:20:15.771616Z","title":"Pearson Education, Harlow","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.04597","last_updated":"2026-07-13T05:25:49Z","snapshot_observed_at":"2026-08-06T19:52:26.021534Z","submitted_at":"2026-07-06T01:58:37Z","title":"Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-14T16:20:15.771616Z"},"links":{"citing_paper":"/paper/2607.04597"},"observation_digest":"sha256:4eb013c2f9d6ccd883b393416ec99f42dfe321cdcd4ca13c46fdb34ae4e5a83f","observation_id":"05add4e0-b300-477b-a362-9a2a687a1a52","resolution":{"observed_at":"2026-07-14T16:20:15.771616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T16:20:15.771616Z","title":"Lyryx, Calgary, AB, Canada","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.04597","last_updated":"2026-07-13T05:25:49Z","snapshot_observed_at":"2026-08-06T19:52:26.021534Z","submitted_at":"2026-07-06T01:58:37Z","title":"Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-14T16:20:15.771616Z"},"links":{"citing_paper":"/paper/2607.04597"},"observation_digest":"sha256:a17909b27a1f48856bd08f51e2607165603eeec168337d5347e6ea05254d783f","observation_id":"c110179e-647c-428c-935e-306d1006105d","resolution":{"observed_at":"2026-07-14T16:20:15.771616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T16:20:15.771616Z","title":"Proceedings of the American Mathematical Society 11(2):274–277","venue":null,"work_id":null,"year":1960},"citing_paper":{"arxiv_id":"2607.04597","last_updated":"2026-07-13T05:25:49Z","snapshot_observed_at":"2026-08-06T19:52:26.021534Z","submitted_at":"2026-07-06T01:58:37Z","title":"Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-14T16:20:15.771616Z"},"links":{"citing_paper":"/paper/2607.04597"},"observation_digest":"sha256:601d4230b42508b0fb3fef495a209d5efdd55a0fc767885ae7e294fa06b4408c","observation_id":"9a20a505-30db-4e19-aff9-6271b7a0e7d0","resolution":{"observed_at":"2026-07-14T16:20:15.771616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T16:20:15.771616Z","title":"In: International Conference on Learning Representations","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.04597","last_updated":"2026-07-13T05:25:49Z","snapshot_observed_at":"2026-08-06T19:52:26.021534Z","submitted_at":"2026-07-06T01:58:37Z","title":"Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-14T16:20:15.771616Z"},"links":{"citing_paper":"/paper/2607.04597"},"observation_digest":"sha256:a5ae44a4ddd79a98b763938d54a8ad0a71b7f079b564b8db36854bdbe4d73141","observation_id":"734e0411-b5c0-443d-91cd-5cb4c2077b98","resolution":{"observed_at":"2026-07-14T16:20:15.771616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T16:20:15.771616Z","title":"arXiv preprint arXiv:2407.18384 [cs.LG]","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.04597","last_updated":"2026-07-13T05:25:49Z","snapshot_observed_at":"2026-08-06T19:52:26.021534Z","submitted_at":"2026-07-06T01:58:37Z","title":"Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-14T16:20:15.771616Z"},"links":{"citing_paper":"/paper/2607.04597"},"observation_digest":"sha256:5c8708ab508e08567335900245df1d5653498c6af686bdee8d2173fa0310e14c","observation_id":"eeda28ed-658d-4262-93e5-e88cbdb61972","resolution":{"observed_at":"2026-07-14T16:20:15.771616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.06007","last_updated":"2024-02-09T16:13:20Z","snapshot_observed_at":"2026-07-06T09:37:32.530064Z","submitted_at":"2020-07-12T14:53:30Z","title":"Universal Approximation Power of Deep Residual Neural Networks via Nonlinear Control Theory","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.06007","snapshot_observed_at":"2026-07-14T16:20:15.771616Z","title":"arXiv preprint arXiv:2007.06007 [cs.LG]","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.04597","last_updated":"2026-07-13T05:25:49Z","snapshot_observed_at":"2026-08-06T19:52:26.021534Z","submitted_at":"2026-07-06T01:58:37Z","title":"Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-14T16:20:15.771616Z"},"links":{"cited_paper":"/paper/2007.06007","citing_paper":"/paper/2607.04597"},"observation_digest":"sha256:9c10899b036fe7047072a9ec99741132b2c7128885fc530d34453a80f59c5178","observation_id":"96acae49-ca29-42a7-861b-93da9975fca1","resolution":{"observed_at":"2026-07-14T16:20:15.771616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T16:20:15.771616Z","title":"In: Larochelle H, Ranzato M, Hadsell R, et al (eds) Advances in Neural Information Processing Systems, vol 33","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.04597","last_updated":"2026-07-13T05:25:49Z","snapshot_observed_at":"2026-08-06T19:52:26.021534Z","submitted_at":"2026-07-06T01:58:37Z","title":"Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-14T16:20:15.771616Z"},"links":{"citing_paper":"/paper/2607.04597"},"observation_digest":"sha256:4baf9b1867951585aad6fd6b501dff456f79c99a3c252c6fc5000e8fd3e7a72f","observation_id":"0eb8d8d0-187b-40e8-ba1b-a87a0658e292","resolution":{"observed_at":"2026-07-14T16:20:15.771616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T16:20:15.771616Z","title":"Cambridge Mathematical Textbooks, Cambridge University Press, Cambridge","venue":null,"work_id":null,"year":1991},"citing_paper":{"arxiv_id":"2607.04597","last_updated":"2026-07-13T05:25:49Z","snapshot_observed_at":"2026-08-06T19:52:26.021534Z","submitted_at":"2026-07-06T01:58:37Z","title":"Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-14T16:20:15.771616Z"},"links":{"citing_paper":"/paper/2607.04597"},"observation_digest":"sha256:0737405579a87b21c4f7d4a6ba289be98706ec31cd593b94482d91a65cf2800d","observation_id":"50116907-19f0-41de-95f8-fd958bf4c5fd","resolution":{"observed_at":"2026-07-14T16:20:15.771616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T16:20:15.771616Z","title":"arXiv preprint arXiv:2511.06837 [cs.LG] 33","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.04597","last_updated":"2026-07-13T05:25:49Z","snapshot_observed_at":"2026-08-06T19:52:26.021534Z","submitted_at":"2026-07-06T01:58:37Z","title":"Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-07-14T16:20:15.771616Z"},"links":{"citing_paper":"/paper/2607.04597"},"observation_digest":"sha256:8509d67364e507c8aa303a8125ee7fc3e15f587f2bc5fb196e679c6682b53974","observation_id":"77e50ef8-0cee-4245-ac50-e9e6d9e66869","resolution":{"observed_at":"2026-07-14T16:20:15.771616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T16:20:15.771616Z","title":"In: Proceedings of the 37th International Conference on Machine Learning, Proceedings of Machine Learning Research, vol","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.04597","last_updated":"2026-07-13T05:25:49Z","snapshot_observed_at":"2026-08-06T19:52:26.021534Z","submitted_at":"2026-07-06T01:58:37Z","title":"Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-14T16:20:15.771616Z"},"links":{"citing_paper":"/paper/2607.04597"},"observation_digest":"sha256:c0134f3f67e4a41d52fe15707a8a88224a4dc33006122dcdb6b2f10b9889b575","observation_id":"94768e1f-f5b9-4cd4-b1cc-c6c3171872b5","resolution":{"observed_at":"2026-07-14T16:20:15.771616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T16:20:15.771616Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.04597","last_updated":"2026-07-13T05:25:49Z","snapshot_observed_at":"2026-08-06T19:52:26.021534Z","submitted_at":"2026-07-06T01:58:37Z","title":"Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-14T16:20:15.771616Z"},"links":{"citing_paper":"/paper/2607.04597"},"observation_digest":"sha256:cd1672eb8433940bc2bb12f6158b5142a0f0dc1950f4ee9f201de7fd7eb84574","observation_id":"3905de91-526d-4153-bc3f-d2db18af7603","resolution":{"observed_at":"2026-07-14T16:20:15.771616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.04597","last_updated":"2026-07-13T05:25:49Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T19:52:26.021534Z","submitted_at":"2026-07-06T01:58:37Z","title":"Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One"},"reference_resolution":{"displayed":28,"state_counts":{"malformed_identifier":2,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":26,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":28},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 0 inbound Pith citation observations for arXiv:2607.04597."}