{"as_of":"2026-08-10T01:45:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f263ce11dd9b024ec67e5d56bc0ff1eafdb9196823ecede4b87bdec085cdb0ef","coverage":[{"denominator":80,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":80,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T19:14:45.556138Z","state":"measured"},{"denominator":80,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":80,"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/2507.06381/citation-record","integrity":"/paper/2507.06381/integrity","json":"/paper/2507.06381/citation-record.json","paper":"/paper/2507.06381"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:57.791155Z","title":"Chen, Yulia Rubanova, Jesse Bettencourt, and David Duvenaud","venue":null,"work_id":"0e64265b-8a67-4d7c-96c0-941327e7ae89","year":2018},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:39.918226Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:ade9ad63f05934a3f482997c34bc3880098bb1070e5b8ae1e259823b849679c6","observation_id":"6bcd5434-203d-47f5-9db7-9eb23b205b25","resolution":{"observed_at":"2026-08-06T19:14:57.878724Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:39.984022Z","title":"Deep learning.Nature, 521(7553):436–444, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:39.984022Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:c5705acbd357e2f9c78c7b54b1d55e4f40074d996f75c5dfebb20b49c3d3a16f","observation_id":"751a5659-3f38-4e81-9f06-985effa6dca3","resolution":{"observed_at":"2026-08-06T19:14:39.984022Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:57.521172Z","title":"Opening the black box: low-dimensional dynamics in high- dimensional recurrent neural networks","venue":null,"work_id":"e02696cc-10a1-4b9e-9a5b-658341cfd342","year":2013},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:40.019997Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:330309a9b09bb73a7c1f2fb84e9ab6a18616e71debbdda10b5d07f7ebce404cb","observation_id":"15951f7c-9b8d-4394-8751-37fdb6097563","resolution":{"observed_at":"2026-08-06T19:14:57.651006Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:57.292965Z","title":"Farrell, S","venue":null,"work_id":"0dbf0dcf-3217-44a6-bcf7-de7418d302da","year":2023},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:40.081225Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:56f99a03afe29b476e52c8832027898df83e94e62733e242e82b2dc568583a77","observation_id":"d927423c-d749-4b38-b829-78bbadb23d9b","resolution":{"observed_at":"2026-08-06T19:14:57.396507Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:57.045343Z","title":"Driscoll, Krishna V","venue":null,"work_id":"2cb2fd92-6a56-42d7-8d0e-0ece8c181a0e","year":2024},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:40.125988Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:31263441ac543292a855d93f89d59a452e6ce603bc03184da5e40c0cad70e5c4","observation_id":"b4491594-e1b0-4b8f-859a-c8e3b9f29fcc","resolution":{"observed_at":"2026-08-06T19:14:57.175155Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:56.782693Z","title":"The simplicity bias in multi-task rnns: Shared attractors, reuse of dynamics, and geometric representation","venue":null,"work_id":"445dd270-2126-4c83-8812-7df4c8671599","year":2023},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:40.192087Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:2d1079236f046d384786e23bd8c46aee04843fdf288a7f6b3dcc4853c7083e4f","observation_id":"e3155769-3c82-4f9f-8b14-73189e193fad","resolution":{"observed_at":"2026-08-06T19:14:56.916455Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:56.537236Z","title":"The interplay between randomness and structure during learning in rnns","venue":null,"work_id":"ee1c4d9f-b10c-4b39-a5d8-437a24df8a30","year":2020},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:40.259276Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:1e71fafe34d48d0b44ebc4da71c37592dee38ff79067e0e35cbbc16ec1d78968","observation_id":"9503b921-12e3-4923-b62a-7533116c8135","resolution":{"observed_at":"2026-08-06T19:14:56.661934Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:40.330312Z","title":"Pytorch: An imperative style, high-performance deep learning library, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:40.330312Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:88baf419acef4fa1ef717d696413ff639d95a9592233062f0443089c439f70a5","observation_id":"7a62f08e-66c4-4eaa-9225-d562b818cb3d","resolution":{"observed_at":"2026-08-06T19:14:40.330312Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:56.317998Z","title":"Hodgkin and A.F","venue":null,"work_id":"5d1104f1-5666-4d6e-94b7-e4c35f4dd31f","year":1952},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:40.393344Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:904421ad3bfa4528dd645cc9cbdd9678e835534b7cc63fd62196c1a3d8e92d55","observation_id":"5a3f862a-bab8-46b5-946c-f0713fa1bdb8","resolution":{"observed_at":"2026-08-06T19:14:56.429213Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:56.149581Z","title":null,"venue":null,"work_id":"1bd2297c-9849-4379-9739-bd6e7e49b1f3","year":1986},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:40.446478Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:b919339f01b8595cc26bb79e64ce0571b26027c1a112ddc51d411746bd20bd26","observation_id":"ffcc11dc-386c-4cd1-b51d-b529b841fc58","resolution":{"observed_at":"2026-08-06T19:14:56.211295Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:55.945399Z","title":"Neural machine translation by jointly learning to align and translate, 2016","venue":null,"work_id":"dd25a698-0c22-4676-a0bc-21e60a8abd5e","year":2016},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:40.524230Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:252913ae9e9f80f4981cd32396663922a5a48eba0e8c4e901473293d57009176","observation_id":"b76bca2a-fe1f-4fb4-95e5-66f358994d31","resolution":{"observed_at":"2026-08-06T19:14:56.028684Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:55.740452Z","title":"van der Schaft","venue":null,"work_id":"a965a2dd-f11a-40df-8da0-644f3514e506","year":1990},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:40.608273Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:c017a478c7508d173a3f308cb523a586388ef68780affcef0bd37b928d4b5fc7","observation_id":"0dc743c5-477b-4a95-8999-72e80ddad49f","resolution":{"observed_at":"2026-08-06T19:14:55.828166Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:55.467561Z","title":"Neural tangent kernel: Convergence and generalization in neural networks","venue":null,"work_id":"29651ef6-2162-475c-a7d6-6c911bfda55b","year":2018},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:40.674754Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:6ff4ff7454624176e0d8b8d98cfdd1950d069fc7db2c768c238649ac8dabca0d","observation_id":"edf50c3d-68f4-4e11-9552-bbdc10940332","resolution":{"observed_at":"2026-08-06T19:14:55.584613Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:55.147654Z","title":"The recurrent neural tangent kernel","venue":null,"work_id":"72e3eb7c-3965-4edc-97c4-a4514ea728e1","year":2020},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:40.769883Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:b10219baf4217ab429100d6b485e55af21aa9f5e153451503277ba773796d571","observation_id":"b8b711e3-95ec-40d4-9e0f-f31e0a28d2b3","resolution":{"observed_at":"2026-08-06T19:14:55.328658Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:54.918128Z","title":"Exploring the impact of activation functions in training neural ODEs","venue":null,"work_id":"d5b2ef50-2f47-4d24-ad20-9568fb0e4e5b","year":2025},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:40.836877Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:99db3e9045bb0be6f5324065ab06713e91efecf12a9b358872948ca7e30116ce","observation_id":"b888ef48-1cc0-4815-a6ae-05069d90ac05","resolution":{"observed_at":"2026-08-06T19:14:55.028188Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:40.915070Z","title":"Deep residual learning for image recognition, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:40.915070Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:1b1e8c4285d5202366d2ac5cd49e535d4f92103ee99191eff0950bb8d6b2b5db","observation_id":"b089b806-a031-4afa-8f85-824f4319dfc2","resolution":{"observed_at":"2026-08-06T19:14:40.915070Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:54.790093Z","title":"On lyapunov exponents for rnns: Understanding information propagation using dynamical systems tools","venue":null,"work_id":"972fc9ee-3937-4de5-82b5-7700984a388b","year":2022},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:41.004387Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:bb2237aa60b71f00eed7bb5dcbcf6a6caa542d4bfe26353ce80cbc387d2e8a65","observation_id":"5cd33bfc-d565-4711-be70-6d82366257c2","resolution":{"observed_at":"2026-08-06T19:14:54.836119Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:54.656872Z","title":null,"venue":null,"work_id":"4d4c4ee5-09c9-467d-a017-4f46365faea5","year":1988},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:41.061692Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:a6c17b6398dfd4d77c1147ec10511ba86d0074d0d6bd193cd139d992fce60446","observation_id":"ae81d3f3-6ba9-47e9-aaa7-528ccc3095fa","resolution":{"observed_at":"2026-08-06T19:14:54.709713Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:54.516284Z","title":null,"venue":null,"work_id":"c8fc3f48-6e57-45fe-a441-66a7faa0c9cb","year":2006},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:41.172089Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:da9f96618907e7f721b7660368950f6f37d9a1122f2f46bb0ed057aaef98c2d0","observation_id":"d6fe292f-f84e-4f9c-8dd1-5d4e42268334","resolution":{"observed_at":"2026-08-06T19:14:54.582710Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:54.367145Z","title":null,"venue":null,"work_id":"039e481d-bfd0-41dd-8a1e-f5c449de30e0","year":2009},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:41.278822Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:3a252f4c16621b21c7b7291e96e0e742994105b8a05d89e093a8dd1028c6d199","observation_id":"03f58af1-c494-402e-a894-67052ab5c741","resolution":{"observed_at":"2026-08-06T19:14:54.424360Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:54.246481Z","title":"Zavatone-Veth","venue":null,"work_id":"0566c7f0-2dbc-4ea5-95a3-143276ca5ae8","year":2025},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:41.380516Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:3126d7a00bf2b447b28010de4fe3cab2e767b44e90fe92c51dd805fd91f17e02","observation_id":"d56f07b5-d41f-4580-86ee-2d1a36cbeed2","resolution":{"observed_at":"2026-08-06T19:14:54.318538Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:54.113740Z","title":null,"venue":null,"work_id":"ff515c89-cbf1-46e6-89a2-ef49f8fa4b01","year":2020},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:41.500163Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:afca3cd7a5da1129f413b1280a06ce20ab22a63cbd30cb2eb8bb58d0c6974b7c","observation_id":"0e254ef9-cae6-4954-9a5d-bd96ab092cb0","resolution":{"observed_at":"2026-08-06T19:14:54.186020Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:53.949345Z","title":"Transition to chaos in random neuronal networks","venue":null,"work_id":"530abe8f-6648-4594-922a-1b5808f1d032","year":2015},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:41.581494Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:b9aaaa3fb84ae9499b161b427ab036088429799417941be133c3cdf2e97095c4","observation_id":"08929efc-2a2f-4be5-bc2e-cf5b21138b13","resolution":{"observed_at":"2026-08-06T19:14:54.026473Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:53.777477Z","title":"How connectivity structure shapes rich and lazy learning in neural circuits","venue":null,"work_id":"8e54dd3f-f090-4e61-83e9-f9edceb5e945","year":2024},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:41.644890Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:3a92efb46b9ac081015ee0ef03aba2c791ed2f89e797730df01bc35ba9045a95","observation_id":"866c8fed-1612-4292-b8f4-f27a86f65541","resolution":{"observed_at":"2026-08-06T19:14:53.858218Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:53.569602Z","title":"Organiz- ing recurrent network dynamics by task-computation to enable continual learning","venue":null,"work_id":"62e8be13-c9c2-445f-ac57-c288e1c19faf","year":2020},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:41.691105Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:6f5269c1a3cf0b921f02b5170c4f66fb76641e3ff5a07b04ac9b46ffa4b9e6d1","observation_id":"f8f35350-1759-4c2d-b31e-8619b307bda1","resolution":{"observed_at":"2026-08-06T19:14:53.677361Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:53.413683Z","title":"Learning representations by back-propagating errors","venue":null,"work_id":"7abe26b5-04c7-4d4c-b275-6da930096a39","year":1986},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:41.809974Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:e5b4cb65271a95229a2a4e62b5dc80bfb9a48c2376ffb74d0f9b012a69db1360","observation_id":"28e9b5fe-29c3-4422-8de5-22dfc29fb4ed","resolution":{"observed_at":"2026-08-06T19:14:53.490996Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:53.245431Z","title":"Kistler, Richard Naud, and Liam Paninski","venue":null,"work_id":"2d5772a5-e002-4f72-8499-76eb5353b7c5","year":2014},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:41.884440Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:49e04a96411b0465cc157e98ccc3e2e33353f1af537c338b27a0270fa9fbea09","observation_id":"3b92b044-d843-493e-b489-81ef1a515940","resolution":{"observed_at":"2026-08-06T19:14:53.349987Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:53.121384Z","title":"Mean-field theory of two-layer neural networks: dimension-free bounds and kernel limit","venue":null,"work_id":"ad1bcb57-c81e-4872-9f3a-b52262b6d991","year":2018},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:41.967387Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:010dad5389c06ee82b2757538d12c9d9ec15f507e9def6ccd62e8ac0e28eaf3d","observation_id":"0621b738-4db5-455e-bfd0-1df797d4d26a","resolution":{"observed_at":"2026-08-06T19:14:53.165255Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:52.985541Z","title":"Context-dependent computation by recurrent dynamics in prefrontal cortex","venue":null,"work_id":"0eaef3f5-0ee1-4818-9960-46b9266f9ca9","year":2013},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:42.040762Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:ccc6eb7f37602a9855e1009f7f04ca0eac4f9ca00b5b4858e16bc230be60eba9","observation_id":"ca283e1c-4659-4146-bbf9-c99dac9b35a2","resolution":{"observed_at":"2026-08-06T19:14:53.023125Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:52.851702Z","title":"Open the black box of recurrent neural network by decoding the internal dynamics","venue":null,"work_id":"a9139239-ac2d-4c68-98a6-80185551214d","year":2022},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:42.096193Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:e8a612789f0c6c7d2c6b1c38da4fff110e8bf4dab1d759e6530b740435d1ad41","observation_id":"d7730b37-f5e1-46cb-bac6-a87a6b8265d6","resolution":{"observed_at":"2026-08-06T19:14:52.905112Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:52.673656Z","title":"Izhikevich","venue":null,"work_id":"ab209b77-0a7f-4cd6-9061-230a27482a7f","year":2007},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:42.166124Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:6b98b5ab06d0ca7dfa874e4433cd1dec19bae4396973dc487951b6e00263b8f8","observation_id":"ad34bcac-d812-4065-b0de-4bbfcdd22d28","resolution":{"observed_at":"2026-08-06T19:14:52.738057Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:52.530991Z","title":null,"venue":null,"work_id":"401844ed-648f-4f5e-844b-4e779f2c1afb","year":2001},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:42.241945Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:a71e0c163c996f93085c8e4adc425b901f26941c989fba10c0bfe515833c8d95","observation_id":"41603c75-a71c-4bb9-a1d5-e2b25ce8d6a1","resolution":{"observed_at":"2026-08-06T19:14:52.607481Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:52.377662Z","title":"Exploring flip flop memories and beyond: Training recurrent neural networks with key insights","venue":null,"work_id":"9db0b942-0279-44fe-b9bc-ff69b473ce82","year":2024},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:42.285615Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:b5ddcd9f77465af1d2890d38f0cc5b8c19e5b5c13e68cc87f506793420d00be9","observation_id":"faf556b6-96ce-45ae-b740-9cd7aa1baa2d","resolution":{"observed_at":"2026-08-06T19:14:52.461666Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:52.205365Z","title":"Gradient-based learning drives robust representations in recurrent neural networks by balancing compression and expansion","venue":null,"work_id":"d538ff1f-85d2-4857-8123-544f137e2009","year":2022},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:42.370886Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:4e51bce6b4dbfa15c6b437e95e6af00a380d1ec5f0ec3e71be5db3b3ea99f944","observation_id":"6641f980-1782-4b6a-8ce5-1e0f0f941d65","resolution":{"observed_at":"2026-08-06T19:14:52.270142Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:52.054169Z","title":null,"venue":null,"work_id":"1017292e-d8d2-479b-bee7-6e3114ca9b30","year":2020},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:42.431661Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:91ef94c3320195744018141252772e878334e16fb0910babd6651578bfca5137","observation_id":"be77e28a-05a4-40d1-9197-47ed1cf513b8","resolution":{"observed_at":"2026-08-06T19:14:52.128968Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:51.913861Z","title":"Predictive learning as a network mechanism for extracting low-dimensional latent space representations","venue":null,"work_id":"ffd076d6-4c02-4b99-a4a4-2050d398e81e","year":2021},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:42.479355Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:1e28ba3c609b565757bb77f49f1c835b0e3d8c71520359521d45a95a35166bc1","observation_id":"d6a82ea2-cfb8-4757-b9c0-d81350bf268d","resolution":{"observed_at":"2026-08-06T19:14:51.993453Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:51.747515Z","title":"Pereira, and William Bialek","venue":null,"work_id":"54bf8213-a28b-46d0-84f7-455294c87db7","year":1999},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:42.591429Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:157feb85efba9e40c0a81ec19b1dbe9b516b2363629dbb827da1a5d6ec2eedf5","observation_id":"e640a77a-8668-4bb4-960b-b1774c24b04d","resolution":{"observed_at":"2026-08-06T19:14:51.820962Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:51.556898Z","title":"Joglekar, Henry F","venue":null,"work_id":"bcd8793a-faeb-4c70-9a76-9badea130d1d","year":2019},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:42.660141Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:fc6a4575a7d40e8b6af25fb00b667323caab42c96a7e429c2211b6ecdded2992","observation_id":"af704ddb-f153-4999-b777-e0eb75762b5b","resolution":{"observed_at":"2026-08-06T19:14:51.656492Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.18377","last_updated":"2024-06-07T23:38:25Z","snapshot_observed_at":"2026-07-06T17:36:52.920342Z","submitted_at":"2024-02-28T14:52:58Z","title":"Out-of-Domain Generalization in Dynamical Systems Reconstruction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.18377","snapshot_observed_at":"2026-08-06T19:14:42.727915Z","title":"Out-of- domain generalization in dynamical systems reconstruction","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:42.727915Z"},"links":{"cited_paper":"/paper/2402.18377","citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:d8ba366301acd470f9db721093111335883be9142806ee60a86a1d59e493749b","observation_id":"b6916a2d-9ae4-4372-80b6-9f889c441dd5","resolution":{"observed_at":"2026-08-06T19:14:42.727915Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:51.429732Z","title":"Ergodic theory of differentiable dynamical systems","venue":null,"work_id":"d29ecd25-0ad2-4bc0-b2f8-0564c2c8e950","year":1979},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:42.796558Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:3f42276aa45c5ebafdad28acb6f5c3dc91995305f7500063e737dbdefab9f33c","observation_id":"663c856a-2f82-4c5d-90b7-5d0a8de208fc","resolution":{"observed_at":"2026-08-06T19:14:51.483380Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:51.263863Z","title":"Finite-time lyapunov exponents of deep neural networks","venue":null,"work_id":"69c66ea7-34a9-4fb4-bfe5-e916d5df6044","year":2024},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:42.856520Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:0190e62d73b8d1468979c60c6d901e1b219dd55aa02f3d00878c8db24be8a027","observation_id":"e22ae7ba-5102-422f-84fc-3bc742a276b9","resolution":{"observed_at":"2026-08-06T19:14:51.336343Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:51.079945Z","title":"On the difficulty of learning chaotic dynamics with rnns","venue":null,"work_id":"ee4c412d-3660-4510-bac0-a1c3c09891a7","year":2022},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:42.973592Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:8aff68a4fec171758282a882d9d6de82a8df2dc5f24022ea91b6726b1620b60a","observation_id":"f72e09cb-db5d-4dd3-8df5-3317c0eb127c","resolution":{"observed_at":"2026-08-06T19:14:51.158337Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:50.816140Z","title":null,"venue":null,"work_id":"143e4ad1-1d63-4ac8-bfc4-29efefa4ab1d","year":1988},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:43.072895Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:682307a14df30b484aa4233d62101054841f037c8981353803fb11fe5ae4ccdd","observation_id":"2fd4d2ec-bc34-4faa-940b-5048d9c9848d","resolution":{"observed_at":"2026-08-06T19:14:50.914324Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.00579","last_updated":"2018-03-12T20:23:23Z","snapshot_observed_at":"2026-08-03T08:01:57.197117Z","submitted_at":"2017-11-02T00:48:13Z","title":"On the difference between variational and unitary coupled cluster theories","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.00579","snapshot_observed_at":"2026-08-06T19:14:43.143635Z","title":"A proposal on machine learning via dynamical systems","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:43.143635Z"},"links":{"cited_paper":"/paper/1711.00579","citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:6cf217ef8438bfbb05ac2ad1def8891d145e07b350b26fd9daffcc2fb5237cd4","observation_id":"1a5affb0-b3ac-47b2-9c21-4ff3844ba3f0","resolution":{"observed_at":"2026-08-06T19:14:43.143635Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.01038","last_updated":"2017-08-03T07:46:59Z","snapshot_observed_at":"2026-08-07T21:02:16.220466Z","submitted_at":"2017-08-03T07:46:59Z","title":"Optimal Stopping and the Sufficiency of Randomized Threshold Strategies","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.01038","snapshot_observed_at":"2026-08-06T19:14:43.216345Z","title":"Maximum principle based algorithms for deep learning","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:43.216345Z"},"links":{"cited_paper":"/paper/1708.01038","citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:80af542eb46a5cdf016bc3d885943b4c9b0db349d80a35d3a8c7eba8b79aeaa2","observation_id":"0f899738-3cd3-4304-a83a-2585551233d4","resolution":{"observed_at":"2026-08-06T19:14:43.216345Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:50.542581Z","title":"Discretize-optimize vs","venue":null,"work_id":"d42178dc-fd2a-4c40-9bf8-48f03ba2fe8b","year":2020},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:43.270182Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:6bd91c64f874fd65fd1d9dd0e4202a20bacdd0574f57e2e86c1aa8e271a12c71","observation_id":"a5c4c323-278e-4063-aecb-ec820ed6fa92","resolution":{"observed_at":"2026-08-06T19:14:50.708663Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:50.332492Z","title":null,"venue":null,"work_id":"0c290abf-53ee-4d96-a77c-e1763820a3e3","year":1962},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:43.365705Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:a0c8d0a355c0a68a862c206a785e6d46faca41021251f8fb16f2d4c017c70467","observation_id":"35d5db53-b68d-40f3-921c-f75a149a6bef","resolution":{"observed_at":"2026-08-06T19:14:50.438469Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:43.430223Z","title":"Golub and Charles F","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:43.430223Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:2d88b10a6e304039eefbf2be6975fa4ba811bd87239b37e89bf029ca646bc2ff","observation_id":"2ec0a005-f3d0-478f-9485-b5035a8c9005","resolution":{"observed_at":"2026-08-06T19:14:43.430223Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:50.198371Z","title":"Introductory Functional Analysis with Applications","venue":null,"work_id":"ea504a80-b686-4bc3-9ea9-32aa490a79a9","year":1989},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:43.521175Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:50a49e2df705493825a693d119497483aecc9f89bb563c0170652c4cc077b7de","observation_id":"51363e91-30f7-4e26-b9bc-06a2f2d4c7c0","resolution":{"observed_at":"2026-08-06T19:14:50.261126Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:43.579521Z","title":"Oliphant, Matt Haberland, Tyler Reddy, David Cournapeau, Evgeni Burovski, Pearu Peterson, Warren Weckesser, Jonathan Bright, Stéfan J","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:43.579521Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:2435fe17749d13a331988198ca467a66b61a88207950e306d6153ff1a14ab207","observation_id":"1784fa58-995f-4304-bd87-1119166edc4e","resolution":{"observed_at":"2026-08-06T19:14:43.579521Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:43.648251Z","title":"JAX: composable transformations of Python+NumPy programs, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:43.648251Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:4f598c28279af08e3e5d335ac7d9e4fc82b8a72ca5b0e4d0be2af8b66d5cd5d4","observation_id":"b3990b7f-8032-4e58-a6ef-07f33f54bf81","resolution":{"observed_at":"2026-08-06T19:14:43.648251Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:49.942225Z","title":null,"venue":null,"work_id":"c446c9a6-2596-4aa5-a0c1-4545c8945e77","year":1983},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:43.719303Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:125429d4be6afacd8d81b095b35c932a39d2693844e965055eaec0d3f1ff911f","observation_id":"39f19a18-8eea-41b5-b7c6-e9fbb78251f4","resolution":{"observed_at":"2026-08-06T19:14:50.098234Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:49.730586Z","title":null,"venue":null,"work_id":"f13aa383-e9d5-47b8-b430-47a8b56b9879","year":2024},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:43.769416Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:d1ab188a7b4405f2218ea63440ef827309634bcb5bd01a7d4d62669bb8643a3a","observation_id":"c77261cf-996b-4d13-ac77-469fed33f12e","resolution":{"observed_at":"2026-08-06T19:14:49.842177Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.10869","last_updated":"2023-11-21T02:49:07Z","snapshot_observed_at":"2026-07-06T16:49:17.188146Z","submitted_at":"2023-11-17T20:59:57Z","title":"Evolutionary algorithms as an alternative to backpropagation for supervised training of Biophysical Neural Networks and Neural ODEs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.10869","snapshot_observed_at":"2026-08-06T19:14:43.804067Z","title":"Evolutionary algorithms as an alternative to backpropagation for supervised training of biophysical neural networks and neural odes","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:43.804067Z"},"links":{"cited_paper":"/paper/2311.10869","citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:692480f92855d9a061df66432f84c2c993ad681dd1cacdd2258385314293cfa6","observation_id":"d165a6fd-a44c-4b04-9457-6f7a549c9b66","resolution":{"observed_at":"2026-08-06T19:14:43.804067Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:49.469794Z","title":"per-trial trajectories","venue":null,"work_id":"6641224e-2d79-491f-b3bc-eead4d8bef1b","year":2019},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:43.867990Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:337a57269d75f0207f620597e424228521b2e2666c1f38b1f3d0a3370bbea515","observation_id":"3c5a6cfe-3e1e-48c3-9f6b-08afc86ca7b4","resolution":{"observed_at":"2026-08-06T19:14:49.617299Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:49.305742Z","title":null,"venue":null,"work_id":"306f7317-9df5-4fc5-af7e-a6048c6855cf","year":null},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:43.967059Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:9472d6faecb5e5396783e50dca20dc21d86880c9ec255bd542958ade2d36730a","observation_id":"6de78107-afbc-4548-af0a-bd560277e5ec","resolution":{"observed_at":"2026-08-06T19:14:49.410199Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:49.014880Z","title":null,"venue":null,"work_id":"1c9521e9-08e4-4156-bb01-63c7ac2a8b06","year":null},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:44.076252Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:d2cf08510c8cfcf7e8d4bba739d1c67da84234572999a06f74e1d24eeb2bf58f","observation_id":"acdb671c-4e22-442a-a492-6af5fd9d72ff","resolution":{"observed_at":"2026-08-06T19:14:49.166800Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:48.865035Z","title":"extrapolating","venue":null,"work_id":"5a1fff3e-d442-43a0-907a-4254dc0ec387","year":null},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:44.125388Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:15d1564a6f6caef8ad00aacce030dda9f993fc6d11ea6991dbdf7c9a6b028993","observation_id":"66353913-9291-4d7f-a4a4-63ec20d59341","resolution":{"observed_at":"2026-08-06T19:14:48.918598Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:48.692392Z","title":"direct integral","venue":null,"work_id":"6cdf63c2-1400-4e53-a332-1f7c75e786ee","year":null},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:44.199670Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:9ce75bd3a7954507ff1c1a346c1b774445c1f17735a070153158c8b12df9d1c1","observation_id":"f1bac7ea-b1ad-401c-b7af-262289526aa6","resolution":{"observed_at":"2026-08-06T19:14:48.789270Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:48.481071Z","title":null,"venue":null,"work_id":"7062f037-56aa-4628-b934-946d68c95092","year":null},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:44.270776Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:99dcfa382d5d8b576ff558d3b8010c86883ab936a0415b4d5d47cb0cef0cf133","observation_id":"ec660845-8aff-421f-8d38-59cecf229a08","resolution":{"observed_at":"2026-08-06T19:14:48.559397Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:48.230872Z","title":"The linear approach relies on the variation of parameters for small inputs q","venue":null,"work_id":"2158c336-c796-48d9-9321-a7caa61fb7f2","year":null},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:44.311610Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:f51d46198f1cd727850829a881b5f5bc3c97e9c8226da31111726862c45a539f","observation_id":"d8c4a162-32dc-4fcc-89f9-e29b731ce77d","resolution":{"observed_at":"2026-08-06T19:14:48.366664Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:47.988764Z","title":null,"venue":null,"work_id":"653735cb-7858-46af-a866-1b81a6f6dba1","year":null},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:44.362555Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:00a587855fda5ebac8a1b63050507c6f5e192ccb41bf756403c480b6cef4212d","observation_id":"26e8cabc-8e58-4c48-bb7f-7340c1e33ca0","resolution":{"observed_at":"2026-08-06T19:14:48.103873Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:47.684551Z","title":"View\" of Computation Graph Wj Supplementary Figure 9: Visual depiction of computation graph “view","venue":null,"work_id":"505057cf-b22e-4a3b-811e-204493cf03dc","year":null},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:44.450835Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:cd2f398705e67af29c768459fefc59a8dd2a1bda8b874fc587d6c88e8f2d767d","observation_id":"b8b4be57-70f9-4ae7-b243-a242a303c056","resolution":{"observed_at":"2026-08-06T19:14:47.852542Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:47.538500Z","title":"block arrowhead matrix","venue":null,"work_id":"c5c76105-40af-4a54-833a-00898bb6d6e9","year":2025},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:44.533650Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:98f039dff857ed356dda75bfea33605b892bae6707d5c9c3d8c8629bc558f591","observation_id":"46862ad1-e2ed-4e6c-9c45-c0f9abea96eb","resolution":{"observed_at":"2026-08-06T19:14:47.609967Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:47.275548Z","title":null,"venue":null,"work_id":"798be707-91db-4d8a-9884-600e02336207","year":null},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:44.633308Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:24793f3e030d866ff9a65566271caa07c4e39f45f9fc974953c1bf75f62948db","observation_id":"732e2c43-c370-47ef-b7cc-518fb5bb39f3","resolution":{"observed_at":"2026-08-06T19:14:47.410535Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:47.093105Z","title":null,"venue":null,"work_id":"627c8d4b-3122-455d-8916-546d122769b8","year":null},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:44.735360Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:b313891ffa6b495cd1ffbe32ff9bde517cdb944c1146defec68b6cf507be7715","observation_id":"af347287-25b0-4acd-ab96-dad6c0de486b","resolution":{"observed_at":"2026-08-06T19:14:47.148945Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:47.079685Z","title":null,"venue":null,"work_id":"9b4b6f10-239e-43de-9224-61bb9d2f9ce3","year":null},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:44.760676Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:82b3af6a7a67e6396380e291186a06225c6afc2a2dba547f4972fa825f2d3ea5","observation_id":"0198fb55-9298-4ddd-8daf-778baef5addb","resolution":{"observed_at":"2026-08-06T19:14:47.083469Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:46.966099Z","title":null,"venue":null,"work_id":"20c34b2b-bbb8-4c9f-98b2-120fa59b26e8","year":null},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:44.814477Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:6500608d7764c37ef08e30ea37e4b14040b885c335230e1148af4f5b6ec31cb1","observation_id":"a4aec197-4259-45ce-bbc9-7726f03cebfd","resolution":{"observed_at":"2026-08-06T19:14:47.005723Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:46.861314Z","title":null,"venue":null,"work_id":"b05b1ba8-9281-4874-9ebc-3325574cbb54","year":null},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:44.888157Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:d1dce96950176b9fb605dc58bb05020ee7047edeb78b0ab96be80615ff31159d","observation_id":"cdd03140-a0a1-4d47-babe-a0cf3cce8b14","resolution":{"observed_at":"2026-08-06T19:14:46.910077Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:46.759860Z","title":null,"venue":null,"work_id":"8201846e-37b6-4331-acbc-0a297f354345","year":null},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:44.933242Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:c98a308c083296c1ce84c5043f661c492d16cab96ee350ee1643a53f356590e5","observation_id":"4e19e4cd-1fcf-413e-8556-0dee65e90f05","resolution":{"observed_at":"2026-08-06T19:14:46.813146Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:46.613107Z","title":null,"venue":null,"work_id":"63386a52-f604-4513-bf68-822b51177f94","year":null},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:45.002737Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:3734c3353710730d278a0c49c43c15141a29fef70de658458e3a52d1117235bd","observation_id":"96dedfa9-f3fb-4df9-ae13-4730166706b8","resolution":{"observed_at":"2026-08-06T19:14:46.695009Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:46.520846Z","title":null,"venue":null,"work_id":"a47e3a19-109e-4962-a2e7-ed3402b40d2d","year":null},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:45.061534Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:014d7ddd59c5be80e444f290127e94c43ea832050c47d601c37d796d7fca4c82","observation_id":"485000c7-b466-41bd-a074-dba0ab1cff89","resolution":{"observed_at":"2026-08-06T19:14:46.555791Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:46.401384Z","title":null,"venue":null,"work_id":"3d683ce4-a97e-476a-a675-33f89bdb8cf2","year":null},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:45.119820Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:7b92b31678edf966180f7a0d08c048a608249fb30073a6b6e8e0692b6f2b1af4","observation_id":"7b42a4bd-03af-4872-92ab-9ab3588b406d","resolution":{"observed_at":"2026-08-06T19:14:46.452308Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:46.297747Z","title":null,"venue":null,"work_id":"f4974a0d-9d99-4b41-bdb3-a0017e4f06d7","year":null},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:45.176910Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:bbc30991e73b80f5f2a8be0aa1c6e017af9717f0127cfbfd8156ebb610d08680","observation_id":"ab01e0fb-89e0-45c4-bef9-99b81cef4216","resolution":{"observed_at":"2026-08-06T19:14:46.345240Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:46.183002Z","title":null,"venue":null,"work_id":"ee60a211-3383-481f-bdec-e71b669fbe92","year":null},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:45.250200Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:17d9c86a0aa7d468d021aa88d4542165d9defc2eaebc0a1bb4c693e2b209629c","observation_id":"dcb70147-91f1-4f12-8dbb-a1cf5251f03d","resolution":{"observed_at":"2026-08-06T19:14:46.250178Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:46.078823Z","title":null,"venue":null,"work_id":"a19c4f0f-b0bd-479a-8a65-8ea9d7f75616","year":null},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:45.317050Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:7c599248fbe1871d8791ee565ca8a237cdaee2e10eae7d09545c146871448bce","observation_id":"abdcdedf-4fc1-4fc5-a9cf-b5253bf04e00","resolution":{"observed_at":"2026-08-06T19:14:46.122831Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:45.984660Z","title":null,"venue":null,"work_id":"0cde9fc7-b2aa-42e2-b8a1-2149e75fe491","year":null},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:45.387642Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:fbb1ce6f9d87b425703fa4dfd12db5285eea9e95973ee6a8509fdc0ee10634a0","observation_id":"6ecfb125-af0d-4a11-9a76-eb20603666e1","resolution":{"observed_at":"2026-08-06T19:14:46.026698Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:45.881313Z","title":null,"venue":null,"work_id":"10922594-8479-48a7-87dd-c56fd6028c8c","year":null},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:45.421401Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:b8b5a1b8dcb678b38da1df018f179ff5ffa97cf266c5135f2b2d3529b71a0592","observation_id":"ecb72c83-a967-40ae-9fda-00c158797b7c","resolution":{"observed_at":"2026-08-06T19:14:45.931489Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:45.783341Z","title":null,"venue":null,"work_id":"d8987b3c-947d-4185-9fec-e822d599667d","year":null},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:45.483349Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:ce319a0178fdc91e41d70968cb12bd4ee2ebd6574b6df9699c29ae085f4ebd4b","observation_id":"1573e2f9-a50f-43a2-a648-3d4b08193d29","resolution":{"observed_at":"2026-08-06T19:14:45.838571Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:14:45.662739Z","title":"Answer: [NA] Justification: LLMs are not a core component of our research and they were not used in generation of the paper","venue":null,"work_id":"0d4d74f5-a72f-4124-af2d-6bf8dddf9bd9","year":null},"citing_paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-06T19:14:45.556138Z"},"links":{"citing_paper":"/paper/2507.06381"},"observation_digest":"sha256:ed9aff35e879f081ed7ab790253b55eb8b19c457bdd8d7d773493f36afee350c","observation_id":"d434a528-97c3-43fe-9fba-63080984e24a","resolution":{"observed_at":"2026-08-06T19:14:45.725074Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.06381","last_updated":"2025-07-08T20:33:15Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-08T19:27:45.247348Z","submitted_at":"2025-07-08T20:33:15Z","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks"},"reference_resolution":{"displayed":80,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":40,"verified_exact":0,"verified_fuzzy":39},"total_outbound_references":80},"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 10 August 2026, this Paper Citation Record lists 80 of 80 outbound references and 0 inbound Pith citation observations for arXiv:2507.06381."}