{"as_of":"2026-08-19T06:02:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:987590ed0ee8ffb4b2e1afaf2f279370f658865cf77259939aaebcc62decfec9","coverage":[{"denominator":43,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":43,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-18T22:55:08.245141Z","state":"measured"},{"denominator":46,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":46,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T18:25:45.421473Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-06-30T08:14:26.101219Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.12121","snapshot_observed_at":"2026-08-03T18:25:45.421473Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.05790","last_updated":"2026-08-14T12:43:53Z","snapshot_observed_at":"2026-08-19T05:09:17.422830Z","submitted_at":"2025-12-05T15:16:59Z","title":"Learnability Window in Gated Recurrent Neural Networks","version":9},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-03T18:25:45.421473Z"},"links":{"cited_paper":"/paper/2508.12121","citing_paper":"/paper/2512.05790"},"observation_digest":"sha256:7c51e1f6be10479e813fe6441aebbdb5dbb33733df573b6395e5a94cc9183946","observation_id":"e1068dd9-3aea-4276-823d-b096244f2c99","resolution":{"observed_at":"2026-08-03T18:25:45.421473Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"cited_work":{"arxiv_id":"2508.12121","doi":null,"metadata_source":"pith","pith_arxiv_id":"2508.12121","snapshot_observed_at":"2026-06-30T08:14:26.101219Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","venue":"cs.LG","work_id":"a2b41990-7355-45b2-b880-2ede6b7ec5dc","year":2025},"citing_paper":{"arxiv_id":"2606.29519","last_updated":"2026-08-18T11:59:21Z","snapshot_observed_at":"2026-08-19T05:26:11.763445Z","submitted_at":"2026-06-28T17:30:36Z","title":"Anti-Collapse Dynamics and the Emergence of Multi-Time-Scale Learning in Recurrent Neural Networks","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-06-30T07:34:39.700429Z"},"links":{"cited_paper":"/paper/2508.12121","citing_paper":"/paper/2606.29519"},"observation_digest":"sha256:fb9ae6f013073fa5bffc673e088b4e99421d85b7dc201649ed2c13ab643efedd","observation_id":"8c846844-d4ea-46a4-b9d5-2f313eddab1b","resolution":{"observed_at":"2026-06-30T08:14:26.102657Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.12121","snapshot_observed_at":"2026-08-02T09:43:28.106394Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.29519","last_updated":"2026-08-18T11:59:21Z","snapshot_observed_at":"2026-08-19T05:26:11.763445Z","submitted_at":"2026-06-28T17:30:36Z","title":"Anti-Collapse Dynamics and the Emergence of Multi-Time-Scale Learning in Recurrent Neural Networks","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-02T09:43:28.106394Z"},"links":{"cited_paper":"/paper/2508.12121","citing_paper":"/paper/2606.29519"},"observation_digest":"sha256:8e845774e773c132cfcfc9a3b98be89a4150a07ecbb3ea1d49824f5d060bde4f","observation_id":"edc7a33d-a7a7-4e92-8b53-f3a711caeeb9","resolution":{"observed_at":"2026-08-02T09:43:28.106394Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2508.12121/citation-record","integrity":"/paper/2508.12121/integrity","json":"/paper/2508.12121/citation-record.json","paper":"/paper/2508.12121"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"On the difficulty of training recurrent neural networks","venue":null,"work_id":"91cb2012-8113-45e1-bfc1-61fd7b15f03f","year":2013},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:8ee57c9120f5546a1c23e417c349beff36da7d718b1791564b7dbf5b69d80cfe","observation_id":"f211771f-7512-44e2-a660-ad19331a9a46","resolution":{"observed_at":"2026-05-18T22:56:53.997392Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-06-05T21:23:00.469572Z","title":"Recurrent neural networks: vanishing and exploding gradients are not the end of the story","venue":null,"work_id":"651bf28a-4bdc-47d5-b346-bcc45a47589f","year":2024},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:45590e8a878b18abab0944c2d7ee767292d76aa809e96f8e60f5f656a88c4e21","observation_id":"b04674ce-2a6f-49f5-b892-b626668664cf","resolution":{"observed_at":"2026-05-18T22:56:53.961041Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-06-05T21:23:00.469572Z","title":"Random orthogonal additive filters: A solution to the van- ishing/exploding gradient of deep neural networks","venue":null,"work_id":"292faf82-e0b7-422d-8c48-96dda17820ca","year":2025},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:59069d70680cca20a1c564e8f3661497b0cf74ac848ffb6bbc9792d85da9362d","observation_id":"c6ae864d-1c90-4376-8935-a5cb9c19e88c","resolution":{"observed_at":"2026-05-18T22:56:53.950867Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2111.00396","last_updated":"2022-08-05T17:54:38Z","snapshot_observed_at":"2026-08-14T01:02:41.198730Z","submitted_at":"2021-10-31T03:32:18Z","title":"Efficiently Modeling Long Sequences with Structured State Spaces","version":3},"cited_work":{"arxiv_id":"2111.00396","doi":"10.48550/arxiv.2111.00396","metadata_source":"pith","pith_arxiv_id":"2111.00396","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Efficiently Modeling Long Sequences with Structured State Spaces","venue":"cs.LG","work_id":"4150b761-b8bf-4d9b-a2f8-cb2d1b73d378","year":2021},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"cited_paper":"/paper/2111.00396","citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:537fa39b104806ef68a571268f3c88a94f55e764dd08758a66664f9128041777","observation_id":"e6d22542-8151-4df5-ae76-52756d9d8565","resolution":{"observed_at":"2026-05-18T22:56:53.090297Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-06-05T21:23:00.469572Z","title":"Combining recurrent, convolutional, and continuous-time models with linear state space layers","venue":null,"work_id":"325cb993-d7b2-409c-9687-d1157b009bea","year":2021},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:b1ca96a426197385d6ca0f46b3aa718acb1c4e50ed68e62f6535acf633b49cf0","observation_id":"ab352fa3-20e6-40a8-9b50-34272b635a27","resolution":{"observed_at":"2026-05-18T22:56:53.973062Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-06-05T21:23:00.469572Z","title":"The- oretical foundations of deep selective state-space models","venue":null,"work_id":"d7b2c9c3-14da-40a6-9df5-2ebd1afddca5","year":2024},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:dfabbe39707dd1bbf8a784ea8c747aa3452cfde1f5aec34376ce302f366ae2bd","observation_id":"89bd8fea-3be9-4a9d-b57e-69649a622e17","resolution":{"observed_at":"2026-05-18T22:56:53.980207Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-06-05T21:23:00.469572Z","title":"Wide neural networks of any depth evolve as linear models under gradient descent","venue":null,"work_id":"1cc32b39-57be-4c39-8d76-72f200bd828b","year":2019},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:b200de625176f9b236f987097af5115005065a46f454aa88b6898d6e2286289e","observation_id":"353fbccc-3a5a-4265-9870-719e2930951f","resolution":{"observed_at":"2026-05-18T22:56:53.953965Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6120","last_updated":"2014-02-19T17:26:57Z","snapshot_observed_at":"2026-08-14T23:50:45.351114Z","submitted_at":"2013-12-20T20:24:00Z","title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","version":3},"cited_work":{"arxiv_id":"1312.6120","doi":"10.48550/arxiv.1312.6120","metadata_source":"pith","pith_arxiv_id":"1312.6120","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","venue":"cs.NE","work_id":"adbbf9c7-c3a4-4cb7-9a00-c98b12f8a315","year":2013},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"cited_paper":"/paper/1312.6120","citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:17323e8d3b03a9f5bb7e0690141612063094d067729a244a4f95b166d8c69927","observation_id":"c0efe837-4a93-46e3-ab53-02b0dbafa55b","resolution":{"observed_at":"2026-05-18T22:56:53.084512Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-07-11T04:49:31.258619+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T04:49:31.258619+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-06-05T21:23:00.469572Z","title":"Orthogonal recurrent neural networks with scaled Cayley transform","venue":null,"work_id":"ad2fbc79-a7ec-4bd4-82a8-1f53f85a4579","year":2018},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:70be7b9d216a9f974f520b62381e42950e4cb91e982f129b3bd702f57fb46389","observation_id":"a7a4674d-9409-4c65-9015-6225c241fbf7","resolution":{"observed_at":"2026-05-18T22:56:53.957522Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-06-05T21:23:00.469572Z","title":"Efficient or- thogonal parametrisation of recurrent neural networks using householder reflections","venue":null,"work_id":"309731e0-7a79-49d5-9d32-c74c31a33ca6","year":2017},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:c32d3b6bfb3a35d057e0220b5e8616813fc47499c0bc450bceafd0a5737e589b","observation_id":"b2501153-d220-4620-88bd-d34509dee70b","resolution":{"observed_at":"2026-05-18T22:56:53.964088Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-06-05T21:23:00.469572Z","title":"Unitary evolution recurrent neural networks","venue":null,"work_id":"46f268f7-d4a5-4d60-b5b0-6eda4c2124d3","year":2016},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:0f44358030344e42d674647d770dd39fc773e5319dc3da0ab83f66c29434297f","observation_id":"89e192ec-57cc-4f6e-8682-a8480b528a2b","resolution":{"observed_at":"2026-05-18T22:56:53.947692Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-06-05T21:23:00.469572Z","title":"Full- capacity unitary recurrent neural networks","venue":null,"work_id":"e290f487-6c20-4557-ab6e-b88058424c0c","year":2016},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:80f5902224fa2fa98196e6a00ab22f029a05c93cb8ae8d859d06bfa6ecc135ee","observation_id":"a40be806-1602-4e3d-85d3-7e30a81bc8e8","resolution":{"observed_at":"2026-05-18T22:56:53.990267Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-06-05T21:23:00.469572Z","title":"On orthogonality and learning recurrent networks with long term dependencies","venue":null,"work_id":"28fb374f-227e-41bc-bd4c-d846efdefe46","year":2017},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:934b9b794d51973d96437bc4881c584671287dc2185485a779b558c60f6c1a57","observation_id":"0db2ed53-b035-4913-b059-f03d2f72a607","resolution":{"observed_at":"2026-05-18T22:56:53.983744Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.12070","last_updated":"2021-04-24T03:31:59Z","snapshot_observed_at":"2026-08-17T12:11:02.240083Z","submitted_at":"2020-06-22T08:44:52Z","title":"Lipschitz Recurrent Neural Networks","version":3},"cited_work":{"arxiv_id":"2006.12070","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2006.12070","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Lipschitz recurrent neural networks","venue":null,"work_id":"55c4a84d-c52e-471c-add9-99292693d715","year":2006},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"cited_paper":"/paper/2006.12070","citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:a5a27f7fb2272e3788f0b7f1b65e39c1ea3d35a81fabd75273de9d778ed723e6","observation_id":"7a2c8a29-b131-44ae-9f13-e440692ce421","resolution":{"observed_at":"2026-05-18T22:56:53.079495Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.12080","last_updated":"2019-10-28T13:13:02Z","snapshot_observed_at":"2026-08-14T16:24:53.903346Z","submitted_at":"2019-05-28T20:41:27Z","title":"Non-normal Recurrent Neural Network (nnRNN): learning long time dependencies while improving expressivity with transient dynamics","version":2},"cited_work":{"arxiv_id":"1905.12080","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1905.12080","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Non-normal recurrent neural network (nnrnn): learning long time dependencies while improving expressivity with transient dynamics","venue":null,"work_id":"7368d721-cf17-45ee-8bc9-e39eab07d2c3","year":1905},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"cited_paper":"/paper/1905.12080","citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:7626805941fa82d56a1d0bb49f74d72b5727fd329bb1ce8bf0e47114fd4ee4da","observation_id":"12354a7a-c443-46c9-add7-db0abbf01730","resolution":{"observed_at":"2026-05-18T22:56:53.095224Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-06-05T21:23:00.469572Z","title":"RNNs incrementally evolving on an equilibrium manifold: A panacea for vanishing and exploding gradients?","venue":null,"work_id":"cb248524-eddb-4b79-bae2-4a194897c4cd","year":2020},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:78743a5b8d435850b9b4baa934bbc7955d8f94377f816bb7ecc5f2b73a0b10af","observation_id":"d330ffd7-560d-4321-b3e1-4d8ceef26c46","resolution":{"observed_at":"2026-05-18T22:56:53.976737Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-06-05T21:23:00.469572Z","title":"AntisymmetricRNN: A dynamical system view on recurrent neural networks","venue":null,"work_id":"495ea835-5819-4980-8093-4e06b70ab522","year":2019},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:ca19ea5a5ee1cabfd667257fc7b2ae74fdff2747ba471f55327bb419f442ef52","observation_id":"8d1c8dd4-881e-40a8-91f5-2efba6367df1","resolution":{"observed_at":"2026-05-18T22:56:54.001225Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-06-05T21:23:00.469572Z","title":"Coupled oscillatory recurrent neural network (cornn): An accurate and (gradient) stable architecture for learning long time dependencies","venue":null,"work_id":"4185ee2e-0a21-47bf-85c9-8a852b855a67","year":2021},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:7f5655abe50da9a7f3d35a7aff082edbae9071c350cd6bfd4c6525f6e74797e7","observation_id":"bbedf6cc-f1ec-468c-a22b-db747f5676f4","resolution":{"observed_at":"2026-05-18T22:56:53.993632Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.04744","last_updated":"2022-02-25T15:20:52Z","snapshot_observed_at":"2026-08-16T17:50:34.239285Z","submitted_at":"2021-10-10T09:43:02Z","title":"Long Expressive Memory for Sequence Modeling","version":2},"cited_work":{"arxiv_id":"2110.04744","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.04744","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Long expressive memory for sequence modeling","venue":null,"work_id":"df9c65e6-741b-4814-8e9e-d5fc631ef101","year":2021},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"cited_paper":"/paper/2110.04744","citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:f4bd48a5c8969929ef596c85a3bfb97c65d6c7dd464248b37bfa5c48b254632b","observation_id":"4e2291be-a2df-45a6-9663-7cd79c39ca20","resolution":{"observed_at":"2026-05-18T22:56:53.074205Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-06-05T21:23:00.469572Z","title":"A clockwork RNN","venue":null,"work_id":"c39ed2d8-51f5-4752-a59a-70ec05fd1a65","year":2014},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:d6db611c681ad02d22419fc32329437e7a948eed90b4a7cedcee1121e6afc473","observation_id":"5f5ae107-cb6f-4051-9efc-de1f65970b89","resolution":{"observed_at":"2026-05-18T22:56:53.966771Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-06-05T21:23:00.469572Z","title":"Dynamical isometry and a mean field theory of RNNs: Gating enables signal propagation in recurrent neural networks","venue":null,"work_id":"beb620f7-54fb-4ef0-a9bf-9b495558e05c","year":2018},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:14e50e7c07c57d8ff4f6ca7cea9119e14d9c8eb2c0993f39e71b13ee57985ddf","observation_id":"bad1cee6-5426-4d86-a6e2-cc46b044d718","resolution":{"observed_at":"2026-05-18T22:56:53.969804Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1901.08987","last_updated":"2019-05-24T01:10:22Z","snapshot_observed_at":"2026-08-14T17:25:50.300815Z","submitted_at":"2019-01-25T17:05:54Z","title":"Dynamical Isometry and a Mean Field Theory of LSTMs and GRUs","version":2},"cited_work":{"arxiv_id":"1901.08987","doi":null,"metadata_source":"pith","pith_arxiv_id":"1901.08987","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Dynamical Isometry and a Mean Field Theory of LSTMs and GRUs","venue":"cs.LG","work_id":"88356995-bfb4-4a5a-847c-a3a4c5c6cd59","year":2019},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"cited_paper":"/paper/1901.08987","citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:03cbcf68330695b6366d9716eb3f2c1cdba2c6e7889d691992dac314da690115","observation_id":"8dd79e26-8867-4b9f-aabd-89214dd38094","resolution":{"observed_at":"2026-05-18T22:56:53.069687Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-06-05T21:23:00.469572Z","title":"Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice","venue":null,"work_id":"8ce5f68f-54db-4fa0-988e-bd16f37291a6","year":2017},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:b03d962f681372e79fc6fe1f9b50ce50bf9920b9013768a2fb1d22a804dce0b1","observation_id":"1c583dac-2a54-4bc5-a826-04117f3f28f3","resolution":{"observed_at":"2026-05-18T22:56:54.005528Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-06-05T21:23:00.469572Z","title":"Gating revisited: Deep multi-layer rnns that can be trained","venue":null,"work_id":"d29d72c1-7c14-40fa-a874-4843aa7c85ce","year":2022},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:32f611411ecaf950666dc99b6f59ea16c7f8282d5e6dc2ae9abb88a5ffeb7efb","observation_id":"a19ec61c-b24f-495b-ab85-d61518182afb","resolution":{"observed_at":"2026-05-18T22:56:53.986888Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1804.04849","last_updated":"2018-09-13T10:55:56Z","snapshot_observed_at":"2026-08-14T19:26:20.823272Z","submitted_at":"2018-04-13T09:18:17Z","title":"The unreasonable effectiveness of the forget gate","version":3},"cited_work":{"arxiv_id":"1804.04849","doi":null,"metadata_source":"pith","pith_arxiv_id":"1804.04849","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"The unreasonable effectiveness of the forget gate","venue":"cs.NE","work_id":"c602c7b5-d501-4f21-a073-f5fab7892bd2","year":2018},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"cited_paper":"/paper/1804.04849","citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:59c379f117bf0c5b5d3edf04dfacc0de574dce23d9e9b4921045e014e85b86fc","observation_id":"89ae9eda-c50a-44a6-bcc4-cd46fd8e4dd3","resolution":{"observed_at":"2026-05-18T22:56:53.060486Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-06-05T21:23:00.469572Z","title":"Theory of gating in recurrent neural networks","venue":null,"work_id":"0643983e-de84-4e9b-8b9c-2d94d132caf2","year":2022},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:9670a0b890906dc4213bc6288bcdfb6237de3abcd3722c0ea9bc322ebb47f5ce","observation_id":"d87d8ffc-b123-478b-81e9-df3a48681389","resolution":{"observed_at":"2026-05-18T22:56:53.902763Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-06-05T21:23:00.469572Z","title":"Gates create slow modes in recurrent neural networks","venue":null,"work_id":"2c38036a-6f10-49e0-8fee-3fab3a79f2a8","year":2020},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:5c58ac989c03d58e6039b630e562556c409e93a5ee7a68cd428bf38491cf698d","observation_id":"17afe4e7-845f-4888-89f3-3101bdd7a3a9","resolution":{"observed_at":"2026-05-18T22:56:53.944547Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-06-05T21:23:00.469572Z","title":"Adaptive time scales in recurrent neural networks","venue":null,"work_id":"ed6bf7dd-50ae-42ba-9aab-d3c12a7a5a02","year":2020},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:d90cd4f66dc5d74e3ffc76f67bdbcf32d3e13b00f527ae8658481a2bf44320f0","observation_id":"5cc43551-6de6-40fe-815c-7aa5d37dbb13","resolution":{"observed_at":"2026-05-18T22:56:53.917922Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-06-05T21:23:00.469572Z","title":"Can recurrent neural networks warp time?","venue":null,"work_id":"bb6158f3-7f47-43fe-bb33-29a52d59d7d0","year":2018},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:071baee884050e842abfa40a5f340e4a49029a2c82c198ffdf7ddef3d783a283","observation_id":"73957f23-c072-4b76-924b-7c8d6b249f21","resolution":{"observed_at":"2026-05-18T22:56:53.905972Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-06-05T21:23:00.469572Z","title":"Optimization and applications of echo state networks with leaky-integrator neurons","venue":null,"work_id":"4eae42e3-91c3-4972-a889-94f609f2e760","year":2007},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:1f8675a17b5a68cf8fa95fe91301cc02ad327e1b7c63dd9b845eda14f9df2b7b","observation_id":"23967350-2931-43ef-8aba-86f86dcab035","resolution":{"observed_at":"2026-05-18T22:56:53.938082Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-06-05T21:23:00.469572Z","title":"Backpropagation through time: what it does and how to do it","venue":null,"work_id":"062b7dae-ef17-449f-a23f-c0eb21e65519","year":1990},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:2106317014bdfcf0da6037975849184953a6fad6d58ba8845817a7c126545a4e","observation_id":"7090d4ae-ec89-419f-abfc-2fc7c27aa5ca","resolution":{"observed_at":"2026-05-18T22:56:53.941358Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.04747","last_updated":"2017-06-15T13:21:04Z","snapshot_observed_at":"2026-08-15T03:49:17.013617Z","submitted_at":"2016-09-15T17:32:34Z","title":"An overview of gradient descent optimization algorithms","version":2},"cited_work":{"arxiv_id":"1609.04747","doi":"10.48550/arxiv.1609.04747","metadata_source":"pith","pith_arxiv_id":"1609.04747","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"An overview of gradient descent optimization algorithms","venue":"cs.LG","work_id":"840f481e-6e07-4454-8939-95804142c46d","year":2016},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"cited_paper":"/paper/1609.04747","citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:798e9a63ebae716a350f5277cc062e6bb191c4ceebbac4c3dade1f4256a3a1f5","observation_id":"730947af-0410-46c0-9408-74d179ea8f72","resolution":{"observed_at":"2026-05-18T22:56:53.055492Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-01T05:08:09.422576+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-01T05:08:09.422576+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-07-06T16:22:38.582822Z","title":"Long short-term memory","venue":null,"work_id":"c0deeb3f-6ea9-435c-bccc-90ae1a94f872","year":1997},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:60a5b775530fb279681446029cc8713e43c9f32e21cbaa2d30e13b3e3d8c2b9e","observation_id":"3e85532c-0cec-4a35-9f16-2ade2bd70d20","resolution":{"observed_at":"2026-05-18T22:56:53.896308Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1406.1078","last_updated":"2014-09-03T00:25:02Z","snapshot_observed_at":"2026-08-15T13:36:27.756066Z","submitted_at":"2014-06-03T17:47:08Z","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","version":3},"cited_work":{"arxiv_id":"1406.1078","doi":"10.48550/arxiv.1406.1078","metadata_source":"pith","pith_arxiv_id":"1406.1078","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","venue":"cs.CL","work_id":"af085a26-bb72-4b1a-8e38-107776555081","year":2014},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"cited_paper":"/paper/1406.1078","citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:4705eb132ecad1cda275504eb964dccb9418f5633a30513d15a75abe01ba9239","observation_id":"984688a7-b763-4b09-ba5b-0f19434a5e2c","resolution":{"observed_at":"2026-05-18T22:56:53.065155Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-07-16T20:21:34.843836+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-16T20:21:34.843836+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-06-05T21:23:00.469572Z","title":"Attention is all you need","venue":null,"work_id":"eab8352b-f1d2-4404-b528-775ac299dab8","year":2017},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:04168accfd84e1fbdb9f69fff06dd2d6a7854887c0ad7c624b747ede4cc84e9c","observation_id":"e0c2a609-5360-4eb3-9f6f-be4c1a489cf6","resolution":{"observed_at":"2026-05-18T22:56:53.934686Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"913c54dd-d3e6-4054-a1ce-641e7efc2784","year":2008},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:8825fb6bacc727190fb53dd248e37deed607e3544e7e586b0cc0cde0bcf2f305","observation_id":"75f61c9b-f7f2-44f5-abd9-1df708be0d1e","resolution":{"observed_at":"2026-05-18T22:56:53.899257Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"ff36225a-040f-4014-ad04-c8c67c86561f","year":2003},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:7350192538e7626f71a21a24c559130d34782b6a88025efdca7c90b4944ba477","observation_id":"89e8ea66-6c92-4451-9652-eaaee10f62c4","resolution":{"observed_at":"2026-05-18T22:56:53.931569Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-08-17T19:26:44.032537Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":"1412.6980","doi":"10.1002/mrm.28086","metadata_source":"pith","pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Adam: A Method for Stochastic Optimization","venue":"cs.LG","work_id":"1910796d-9b52-4683-bf5c-de9632c1028b","year":2014},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:16022fff2f9d8abe59a1f49c35caa428289d856b9c770024c5cac3fe3a0bfb81","observation_id":"bb086ed9-e410-49fa-aca4-e6ef37c8d7a8","resolution":{"observed_at":"2026-05-18T22:56:53.050661Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-06-05T21:23:00.469572Z","title":"Since the space is finite-dimensional, all norms are equivalent","venue":null,"work_id":"7e61fc3d-166e-4bc8-89b0-43a08aa6a589","year":null},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:ed4135ccc69fe42c68dbca9f3a5413c633675bc880581aa9b5f9305ee2a5a50a","observation_id":"87eec651-35c7-4f25-a325-c8bba785b83e","resolution":{"observed_at":"2026-05-18T22:56:53.928285Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-06-05T21:23:00.469572Z","title":"The direction of perturbation E in (57) is now the tuple E ≡ (B1, B2","venue":null,"work_id":"fdae0f45-d8ea-44d2-b762-a9b15c960158","year":null},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:a32342ec33364556a777e73a6c3a6ad6156dc8853cf8eefeadd5964e6bef52b9","observation_id":"5643366b-19e2-4810-9da2-4e00990d4b73","resolution":{"observed_at":"2026-05-18T22:56:53.921153Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-06-05T21:23:00.469572Z","title":"We now apply the product rule (58) to Fn by setting g(ε) = Fn−1(ε), h (ε) = An + εBn","venue":null,"work_id":"6c9c635d-4842-4d53-9853-dc497e02cf64","year":null},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:92c5e8c112cd8793d6067aa629e436641ff62573a914ca500b7dd19bd7970e10","observation_id":"530c547d-5771-4def-a316-a88ad32a6611","resolution":{"observed_at":"2026-05-18T22:56:53.910271Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"6fd8e123-6c73-40b1-987f-07b8e349a720","year":null},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:fd0a5da19c300804e7e051eaee908fb5c1aa4ba6fb7dc53f0fccc2675411017e","observation_id":"b0b41e47-471e-4ece-83ef-0d7ec1e64cfc","resolution":{"observed_at":"2026-05-18T22:56:53.924650Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-06-05T21:23:00.469572Z","title":"In the main text, Bj represents gate-induced corrections, which are typically low-norm compared to the dominant dynamics in Aj","venue":null,"work_id":"5b5b7beb-57a2-4a55-abe7-a9db1f742d96","year":null},"citing_paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","version":5},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-18T22:55:08.245141Z"},"links":{"citing_paper":"/paper/2508.12121"},"observation_digest":"sha256:1990706f4a0a06355a479c74ff78d37187e497db89ee5b066814c241603ade75","observation_id":"b4a15046-73c8-4970-9fed-49c45013aad8","resolution":{"observed_at":"2026-05-18T22:56:53.914409Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2508.12121","last_updated":"2026-04-21T17:54:21Z","latest_version":5,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-11T14:51:10.929242Z","submitted_at":"2025-08-16T18:19:34Z","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks"},"reference_resolution":{"displayed":43,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":3,"verified_exact":10,"verified_fuzzy":30},"total_outbound_references":43},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 3 inbound Pith citation observations for arXiv:2508.12121."}