{"as_of":"2026-08-10T16:24:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:377ffc1706680a1c521c7d7808d24d1e2af2c8de9011f49ac36b909f87ec8037","coverage":[{"denominator":70,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":70,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T15:02:53.641160Z","state":"measured"},{"denominator":70,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":70,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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/2512.18471/citation-record","integrity":"/paper/2512.18471/integrity","json":"/paper/2512.18471/citation-record.json","paper":"/paper/2512.18471"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:02:45.586658Z","title":"Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition,","venue":null,"work_id":null,"year":1965},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:45.586658Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:176ee2c30788590c5b5a1b3cafaa46d11758f8f5c38236faf7002362e0377d04","observation_id":"87c359e7-fa03-4ae5-83f8-e96a7cfc49f0","resolution":{"observed_at":"2026-08-03T15:02:45.586658Z","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":"2026-08-03T15:02:45.761714Z","title":null,"venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:45.761714Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:558f474166633b799315fcc22e8f003224251320fcd682e807cd4ed5edbc896f","observation_id":"c916fa1a-fdb2-4067-9928-a02683f06eb7","resolution":{"observed_at":"2026-08-03T15:02:45.761714Z","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":"2026-08-03T15:02:46.006472Z","title":"Understanding machine learning: From theory to algorithms,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:46.006472Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:44271d45efc5884aef42803d84bc4af28592eaf9963701988c743c88bbbb5b93","observation_id":"f389d9a2-3b33-4003-915e-48af6f8a5cdb","resolution":{"observed_at":"2026-08-03T15:02:46.006472Z","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":"2026-08-03T15:02:46.166077Z","title":"Catastrophic interference in connection- ist networks: The sequential learning problem,","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:46.166077Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:6159e11b14b3ccbd65fc0f5456537d519fe6578ca19d656b40c9559fb2ec6bff","observation_id":"71a4810a-1077-4720-9510-f39dcea2ab8e","resolution":{"observed_at":"2026-08-03T15:02:46.166077Z","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":"2026-08-03T15:02:46.410325Z","title":"Catastrophic forgetting in connectionist networks,","venue":null,"work_id":null,"year":1999},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:46.410325Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:c9c54eba31c02b80b6e6c5f72c850ada538f08f1945d4956206a2bf2db7bab5b","observation_id":"9307bb0d-1741-4777-8a79-90f4aa853915","resolution":{"observed_at":"2026-08-03T15:02:46.410325Z","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":"2026-08-03T15:02:46.583567Z","title":"Continual lifelong learning with neural networks: A review,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:46.583567Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:054338d4f02e13d8178c9226426df21a194bfff2049c754d470fd363af7c16b1","observation_id":"56225271-5d5f-413a-b527-58886acd1754","resolution":{"observed_at":"2026-08-03T15:02:46.583567Z","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":"2026-08-03T15:02:46.650100Z","title":"Buzs ´aki,Rhythms of the Brain","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:46.650100Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:8179558f4ebee5b9da0f36adec33173803f747a6f2f961c89b57fb7ced280179","observation_id":"a0b74834-ff55-4200-b95b-c05d6fb76fc7","resolution":{"observed_at":"2026-08-03T15:02:46.650100Z","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":"2026-08-03T15:02:46.750476Z","title":"The columnar organization of the neocortex,","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:46.750476Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:a6e67e8aac7fbb18229cfbea0f5ae62cf63375cb0da7973f12bfce932bbfd5b8","observation_id":"0e45a919-8399-4bbc-b865-81350111fa0c","resolution":{"observed_at":"2026-08-03T15:02:46.750476Z","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":"2026-08-03T15:02:46.844353Z","title":"A hierarchy of temporal receptive windows in human cortex,","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:46.844353Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:a59aa04bb9375d11c0bbe353a3831549708a4c545d5cc162b4b2ff526056257b","observation_id":"14cf011f-3ef2-4ccf-aa88-b0aaaef099ad","resolution":{"observed_at":"2026-08-03T15:02:46.844353Z","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":"2026-08-03T15:02:47.007516Z","title":"The architecture of complexity,","venue":null,"work_id":null,"year":1973},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:47.007516Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:aa7552b4c8a9808b8507f4dc6e2e96334392df41c501f68198891eb51161e306","observation_id":"0f707aa9-3979-4487-9630-b92fb8dbf247","resolution":{"observed_at":"2026-08-03T15:02:47.007516Z","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":"2026-08-03T15:02:47.160605Z","title":"A global geometric framework for nonlinear dimensionality reduction,","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:47.160605Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:c9366179531128ff63bbf16a0d76423ebf9947970c1416742e4be763e9cf50e7","observation_id":"8f8e7d39-c944-458f-a287-f202fddf36fb","resolution":{"observed_at":"2026-08-03T15:02:47.160605Z","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":"2026-08-03T15:02:47.263470Z","title":"Testing the manifold hypothesis,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:47.263470Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:9d1dabab46c7103507f8d612a514b32de254ebf953dc7d73ec0d39e498c37797","observation_id":"a01f5611-fc4a-4806-9f92-8fd57b4a0129","resolution":{"observed_at":"2026-08-03T15:02:47.263470Z","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":"2026-08-03T15:02:47.377575Z","title":"Gromov,Metric Structures for Riemannian and Non-Riemannian Spaces","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:47.377575Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:3bb530125f271bfbe22c0a1710d1dfed21d949051024ebf8d771be8ab333e8f2","observation_id":"f503b3fa-c357-45c9-9d9d-283b1f40eacd","resolution":{"observed_at":"2026-08-03T15:02:47.377575Z","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":"2026-08-03T15:02:47.483843Z","title":null,"venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:47.483843Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:277e01624b099b6bb712926b625740aa435741593328bc6476daa05e9f1af1c6","observation_id":"e757a384-6989-4e5e-9fb2-def6b898e813","resolution":{"observed_at":"2026-08-03T15:02:47.483843Z","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":"2026-08-03T15:02:47.609063Z","title":"Catastrophic forgetting, rehearsal and pseudorehearsal,","venue":null,"work_id":null,"year":1995},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:47.609063Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:f24bba411f2c7a5c68380878d326ce467d0c0bb6e6b501179d9daa0f1c3206c9","observation_id":"e813f956-fa22-44ad-b324-fb8fc52392d9","resolution":{"observed_at":"2026-08-03T15:02:47.609063Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1511.05952","last_updated":"2016-02-25T17:55:31Z","snapshot_observed_at":"2026-07-06T04:37:00.543211Z","submitted_at":"2015-11-18T20:54:44Z","title":"Prioritized Experience Replay","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1511.05952","snapshot_observed_at":"2026-08-03T15:02:47.770642Z","title":"Prioritized experience replay,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:47.770642Z"},"links":{"cited_paper":"/paper/1511.05952","citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:379e4a1396fa7630387766317e2f926f7051fceee9cf0d1dd8979573485d55f9","observation_id":"68f57b12-9e4c-409c-8ca8-a9c5ef5e9b45","resolution":{"observed_at":"2026-08-03T15:02:47.770642Z","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":"2026-08-03T15:02:47.939639Z","title":"Overcoming catas- trophic forgetting in neural networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:47.939639Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:67aee4a3a564e3b69fec9a6e8d67540ee630739d27ace38520416c5e8f2fc795","observation_id":"31009171-07b8-4bb5-9d35-b3631d43058e","resolution":{"observed_at":"2026-08-03T15:02:47.939639Z","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":"2026-08-03T15:02:48.093171Z","title":"Feudal reinforcement learning,","venue":null,"work_id":null,"year":1993},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:48.093171Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:ca50aa2216f758af6f3c2e22770d3005ec0d1209012f8cc3abfd9b8bb496978d","observation_id":"44e5c350-39cc-4f55-a7e7-dfeda3e0f1c1","resolution":{"observed_at":"2026-08-03T15:02:48.093171Z","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":"2026-08-03T15:02:48.202529Z","title":"Hierarchical reinforcement learning with the maxq value function decomposition,","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:48.202529Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:55b703f390927cc6fda18aa3d2d91043edc270ff906fd1a466a85112c01bcb47","observation_id":"6c5fc5a4-0ff4-42a7-bddf-7368cbcabf39","resolution":{"observed_at":"2026-08-03T15:02:48.202529Z","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":"2026-08-03T15:02:48.372386Z","title":"Benefits of depth in neural networks,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:48.372386Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:a8af36f88f68e613f186c3eaaf18d5a7b11fee8d67b500a28493b9980b862212","observation_id":"bc1494ae-7d21-47f7-ab81-4c0c58900b84","resolution":{"observed_at":"2026-08-03T15:02:48.372386Z","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":"2026-08-03T15:02:48.501522Z","title":"Proto-value functions: A laplacian framework for learning representation and control in markov decision processes,","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:48.501522Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:513aa8caba959a4dcf1ba14d8853773b174636efebfe9fd6d32fef29d55e2079","observation_id":"1fa681e0-2540-440a-8f31-5c17634dd878","resolution":{"observed_at":"2026-08-03T15:02:48.501522Z","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":"2026-08-03T15:02:48.587376Z","title":"A comprehensive survey of continual learning: Theory, method and application,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:48.587376Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:cf012b4030cc4155b834153443ec7c286247aeb96f55b3108d7e768f5d0c57b3","observation_id":"2bf48162-642f-48bd-b1e9-b673009cd650","resolution":{"observed_at":"2026-08-03T15:02:48.587376Z","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":"2026-08-03T15:02:48.706698Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:48.706698Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:e9276fba1d309f63aa35e92cd9eb7e15268dd2fdb2ff4e24dadb6bfeb301563a","observation_id":"034647c3-0fb5-4908-9941-0f7d7734da6b","resolution":{"observed_at":"2026-08-03T15:02:48.706698Z","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":"2026-08-03T15:02:48.809653Z","title":"Vershynin,High-Dimensional Probability: An Introduction with Applications in Data Science","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:48.809653Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:ec6e53024e2825b9311af8be94cc52881e6e24ee6e86fe2dfecc6bfb19e20d1b","observation_id":"50f4a7f2-a14e-47de-b94a-47c1c99c2921","resolution":{"observed_at":"2026-08-03T15:02:48.809653Z","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":"2026-08-03T15:02:48.953417Z","title":null,"venue":null,"work_id":null,"year":1959},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:48.953417Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:40584983d0609c7c30e9cffc1eb6084ef40095e63a4bc90854e44566e460eaeb","observation_id":"bca98fb7-927d-4b46-b2cd-485870e54b2e","resolution":{"observed_at":"2026-08-03T15:02:48.953417Z","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":"2026-08-03T15:02:49.061479Z","title":null,"venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:49.061479Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:c36d93c897024ead0c6b5d0526ae3e336dbc6c05c84658ae2b16e491b247bd9f","observation_id":"30f50604-895c-4168-bead-705ef7e4d4e0","resolution":{"observed_at":"2026-08-03T15:02:49.061479Z","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":"2026-08-03T15:02:49.164867Z","title":"Gromov,Metric Structures for Riemannian and Non-Riemannian Spaces","venue":null,"work_id":null,"year":1999},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:49.164867Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:22db746ae24aaf39f89f95f43d032ffc5c0202fcfbf91308e38426ac9b43ca12","observation_id":"17566e0e-16fb-4b23-838e-096aeafd2856","resolution":{"observed_at":"2026-08-03T15:02:49.164867Z","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":"2026-08-03T15:02:49.289287Z","title":"On the gromov–hausdorff distance,","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:49.289287Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:f5e759316130236da0340ac503eba869bea824ba4db7d7b651025e0a3d5e85d1","observation_id":"fa65b970-6400-43cc-b08c-8f371c1716a3","resolution":{"observed_at":"2026-08-03T15:02:49.289287Z","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":"2026-08-03T15:02:49.407468Z","title":"Diffusion maps,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:49.407468Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:e27f315706bcb6bb76fee9a5ac2134108ad2b0e599124c64aa62d4ee99c63ded","observation_id":"d80f63a0-df53-4bb4-8948-83306d90f313","resolution":{"observed_at":"2026-08-03T15:02:49.407468Z","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":"2026-08-03T15:02:49.466366Z","title":"Burago, Y","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:49.466366Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:7987c845d6f3097b54c4d8bebad5fe371966f5419469a1332d3a2f078a7b2f60","observation_id":"c0f8495a-86c5-4981-ab13-1d41f7bb8d71","resolution":{"observed_at":"2026-08-03T15:02:49.466366Z","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":"2026-08-03T15:02:49.536216Z","title":"The hippocampus as a cognitive graph","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:49.536216Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:d79a55e2249c88b25c5fc12c1ef83be6bf5d21ffa899ddb4ebbc34fe1be0a8a0","observation_id":"54bfcaf5-3deb-4c37-9df3-3631c79ab88b","resolution":{"observed_at":"2026-08-03T15:02:49.536216Z","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":"2026-08-03T15:02:49.612370Z","title":"Memory, navigation and theta rhythm in the hippocampal-entorhinal system,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:49.612370Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:ce708688cc2e3e78986b923006e3a862f45b804405e7803138ebaf18fee799f0","observation_id":"c417f06f-7d9f-4e86-a3b1-b1474d7a8fd1","resolution":{"observed_at":"2026-08-03T15:02:49.612370Z","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":"2026-08-03T15:02:49.665038Z","title":"Simplified neuron model as a principal component analyzer,","venue":null,"work_id":null,"year":1982},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:49.665038Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:ed31ee15d2dd0c58f8f705c44512398a4d2cfdd4569a6ae5559ae8b2866460e9","observation_id":"0480e7ca-db8f-41d4-b918-45125c48cee2","resolution":{"observed_at":"2026-08-03T15:02:49.665038Z","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":"2026-08-03T15:02:49.782703Z","title":"Optimal unsupervised learning in a single-layer linear feedforward neural network,","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:49.782703Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:c66236612bb8d30727306cde5c35cba302d9857923d8259a0e2fdf1f5381f00b","observation_id":"5b3b11e1-e5bd-4822-8769-381467fadad4","resolution":{"observed_at":"2026-08-03T15:02:49.782703Z","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":"2026-08-03T15:02:49.861059Z","title":"Reactivation of hippocampal ensemble memories during sleep,","venue":null,"work_id":null,"year":1994},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:49.861059Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:8e7dcc5ddd09263765699551aebaa4e4ddf2df3e3d7989ce211b5a34bcc45d1e","observation_id":"3f404564-2056-40ad-803c-a217e51704db","resolution":{"observed_at":"2026-08-03T15:02:49.861059Z","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":"2026-08-03T15:02:50.008069Z","title":"Hierarchical process memory: memory as an integral component of information processing,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:50.008069Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:7547e96a5d623315c671a3351f895863b6e3ad722a7c578e928c59bcdca53912","observation_id":"3d87dec5-1cbc-42fc-b857-f7be6f70b2fc","resolution":{"observed_at":"2026-08-03T15:02:50.008069Z","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":"2026-08-03T15:02:50.141989Z","title":"A continual learning survey: Defying forgetting in classification tasks,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:50.141989Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:0c03e98718e58f438b36e037ee54c3db1a40965bc6ff0e5cb7ced1c984839eb5","observation_id":"2ac6198b-0926-40e4-9d6f-d6726a829133","resolution":{"observed_at":"2026-08-03T15:02:50.141989Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2512.10976","last_updated":"2026-05-08T19:25:17Z","snapshot_observed_at":"2026-07-06T22:38:45.907386Z","submitted_at":"2025-12-03T00:51:25Z","title":"The Homological Brain: Parity Principle and Amortized Inference","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2512.10976","snapshot_observed_at":"2026-08-03T15:02:50.255939Z","title":"The homological brain: Parity principle and amortized inference,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:50.255939Z"},"links":{"cited_paper":"/paper/2512.10976","citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:aa3d1ba375d5c1047846f8343e13fe1be4d4aa64c9890a6fff21af2a6b9263df","observation_id":"b9459fe4-d97c-4889-9256-2a51c17d8ec4","resolution":{"observed_at":"2026-08-03T15:02:50.255939Z","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":"2026-08-03T15:02:50.406322Z","title":"Active inference: a process theory,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:50.406322Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:5efd7a0b092009af1dd28a327af175a7c0df2d9047fe92eec9d3d3bbcfb1bcf0","observation_id":"4bb05a04-f9cb-4c1e-b3aa-83e3f2db75ed","resolution":{"observed_at":"2026-08-03T15:02:50.406322Z","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":"2026-08-03T15:02:50.564236Z","title":"Memory consolidation,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:50.564236Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:b534cc1a23e83d4e89f7a33aafcf8334aad492d4db80c61d4edceb82e025e09a","observation_id":"b4becc62-f718-478f-ab94-dcce1afb04a9","resolution":{"observed_at":"2026-08-03T15:02:50.564236Z","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":"2026-08-03T15:02:50.645587Z","title":"Relationships between nondeterministic and deterministic tape complexities,","venue":null,"work_id":null,"year":1970},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:50.645587Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:1c4aaf39b93861778f0c50d8fcee9290555a36a57503362a5a6b19ced562be39","observation_id":"7e21813f-afca-4a01-8905-1b9bc1da9a58","resolution":{"observed_at":"2026-08-03T15:02:50.645587Z","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":"2026-08-03T15:02:50.814298Z","title":"Shawe-Taylor and N","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:50.814298Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:8f14d5039d9e7b58db3c18278aa62a5fa2f19735841808a84d4230a48db2e923","observation_id":"ac3c856d-4dd8-4586-ae32-c1fa842e18fc","resolution":{"observed_at":"2026-08-03T15:02:50.814298Z","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":"2026-08-03T15:02:50.962435Z","title":"Willard,General topology","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:50.962435Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:7668f55096f32609a95468566b5c14ac0503bc590bc8695916db2c8a542877b0","observation_id":"5263b9b7-234d-48cb-a822-33f9ef80f2c7","resolution":{"observed_at":"2026-08-03T15:02:50.962435Z","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":"2026-08-03T15:02:51.070727Z","title":"Bellman,Dynamic Programming","venue":null,"work_id":null,"year":1957},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:51.070727Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:b62b3abc0ba9ac7160a711d881c99906c183d3c092488012ad3252d0505b98bf","observation_id":"437e7f6f-2368-4011-acaa-95eab114fcbf","resolution":{"observed_at":"2026-08-03T15:02:51.070727Z","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":"2026-08-03T15:02:51.210170Z","title":"The theta-gamma neural code,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:51.210170Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:aad3b86d0532f819d37393ee6c397b564a22748d9e4bd8211383b5259d0a1bbf","observation_id":"dd355730-2046-4025-96d0-3bc61206d3db","resolution":{"observed_at":"2026-08-03T15:02:51.210170Z","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":"2026-08-03T15:02:51.286465Z","title":"The hippocampo-neocortical dialogue,","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:51.286465Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:07c0121e7651eec3e4a83352e105007c6b4415c479a28e5060d628bee3507067","observation_id":"968599b9-da6d-47a2-bc46-a5065be801c5","resolution":{"observed_at":"2026-08-03T15:02:51.286465Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1801.00173","last_updated":"2018-01-16T08:54:12Z","snapshot_observed_at":"2026-08-08T10:21:14.704361Z","submitted_at":"2017-12-30T18:27:35Z","title":"Theory of Deep Learning III: explaining the non-overfitting puzzle","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1801.00173","snapshot_observed_at":"2026-08-03T15:02:51.402132Z","title":"Theory of deep learning iii: Explaining the non-overfitting puzzle,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:51.402132Z"},"links":{"cited_paper":"/paper/1801.00173","citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:04d060d8773756773c19b3ec0a86757c613bf02085d0952d9c712fa219781543","observation_id":"45591153-5370-4639-b4a9-67541276db72","resolution":{"observed_at":"2026-08-03T15:02:51.402132Z","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":"2026-08-03T15:02:51.500247Z","title":"Hatcher,Algebraic topology, 2005","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:51.500247Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:e9449586d79df67b172b44ed3994af14847f5231a8eb0c5a971f9d82907411f6","observation_id":"e6ccd7e4-c49e-49c5-b445-19ce51144afb","resolution":{"observed_at":"2026-08-03T15:02:51.500247Z","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":"2026-08-03T15:02:51.560896Z","title":"Kahneman,Thinking, fast and slow","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:51.560896Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:33c19a0c5e2ac4e820952e81741bb1139ea86a08c744b6257e5ce542829b4dc8","observation_id":"fed5ce68-d56f-42ae-a309-902deba26ce9","resolution":{"observed_at":"2026-08-03T15:02:51.560896Z","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":"2026-08-03T15:02:51.613900Z","title":null,"venue":null,"work_id":null,"year":1967},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:51.613900Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:822be5540ec89e76218e95192b7b0158fd7d37a0fa7d5166a9bcf8f4fa7eb5ef","observation_id":"953eaf3d-4cd7-4299-ba5f-bfcb269e284f","resolution":{"observed_at":"2026-08-03T15:02:51.613900Z","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":"2026-08-03T15:02:51.722054Z","title":"Nakahara,Geometry, topology and physics","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:51.722054Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:7e06fdfbfffeab51aa8bce39c8c9dad7995b162f9b4672003eae2aa6f4a46958","observation_id":"a9f5fd20-cb13-4a0b-8c58-3dadc4a874b7","resolution":{"observed_at":"2026-08-03T15:02:51.722054Z","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":"2026-08-03T15:02:51.783909Z","title":"Amortized inference in probabilistic reasoning,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:51.783909Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:f8cab70df8a9da90aa05ae664428b972c127c6788f86fc820704be1ceec47eb7","observation_id":"be149ce9-c1a2-4a6b-945c-9ce3576216b3","resolution":{"observed_at":"2026-08-03T15:02:51.783909Z","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":"2026-08-03T15:02:51.915899Z","title":"The magical number seven, plus or minus two: Some limits on our capacity for processing information","venue":null,"work_id":null,"year":1956},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:51.915899Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:ae14be89712aaf5b111cbcf7917028f0538fcf27822134273ff3c8d15272ae78","observation_id":"ab776e95-654a-4b2d-aea9-c1ed7f89f13e","resolution":{"observed_at":"2026-08-03T15:02:51.915899Z","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":"2026-08-03T15:02:52.083468Z","title":"Canonical microcircuits for predictive coding,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:52.083468Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:3e22962bb61fac76c35b24b988422b21b0bf1285a09ef49e59deb734f0f4da21","observation_id":"ef8c3666-07d8-463b-a09f-650ba0b807b6","resolution":{"observed_at":"2026-08-03T15:02:52.083468Z","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":"2026-08-03T15:02:52.174189Z","title":"The “wake-sleep","venue":null,"work_id":null,"year":1995},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:52.174189Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:ef4791a12ec06d545472a1a47094032a8a286d736af7d7fad85280117244fb3e","observation_id":"ef24c3df-0e4c-41f6-a678-9b7a5aae8db0","resolution":{"observed_at":"2026-08-03T15:02:52.174189Z","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":"2026-08-03T15:02:52.233536Z","title":null,"venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:52.233536Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:526a2d563b7ab02973dcf7a871ef002de67f257cc64756b1a8b739fed0bf7929","observation_id":"ad9e5013-5455-4940-94a4-b4fd2c817fc4","resolution":{"observed_at":"2026-08-03T15:02:52.233536Z","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":"2026-08-03T15:02:52.286416Z","title":"Pearl,Causality","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:52.286416Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:feba8dda053bf6e384f7e7bb472f4a8781702dee38660919165d28bb44fe8098","observation_id":"7a4b5f7c-401c-4c7c-bd1c-bf8c312170da","resolution":{"observed_at":"2026-08-03T15:02:52.286416Z","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":"2026-08-03T15:02:52.323107Z","title":"Hippocampal place-cell sequences depict future paths to remembered goals,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:52.323107Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:d951b9f951fc50adf7e19e1159aeea15748c719b5751702ab4617734dbb8e9bf","observation_id":"1b8f829c-cfe7-446f-b02f-046fe4b0e3b5","resolution":{"observed_at":"2026-08-03T15:02:52.323107Z","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":"2026-08-03T15:02:52.408450Z","title":"The mechanisms for pattern completion and pattern separation in the hippocampus,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:52.408450Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:9f064543ad4d8359bcb1e92e84ee7d514c9fc11fd6c6382fe32737a06ee05424","observation_id":"68bfc725-2bb7-45bb-88e5-b3d824689d90","resolution":{"observed_at":"2026-08-03T15:02:52.408450Z","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":"2026-08-03T15:02:52.486470Z","title":"The importance of mixed selectivity in complex cognitive tasks,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:52.486470Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:8bebed3210ee2a2862514231c071ddf0099e802b8c7e564b168b710a4e5a922e","observation_id":"9d2fad0c-ec09-44d9-adca-6869f058b10b","resolution":{"observed_at":"2026-08-03T15:02:52.486470Z","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":"2026-08-03T15:02:52.564775Z","title":"Linking connectivity, dynamics, and computations in low-rank recurrent neural networks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:52.564775Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:990891bfc062263cb42fac00e7d23afd548bad55b2c9f54f02191ccee0eecf73","observation_id":"6b1f2402-aec3-4ceb-9f3a-733f836ab67d","resolution":{"observed_at":"2026-08-03T15:02:52.564775Z","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":"2026-08-03T15:02:52.673678Z","title":null,"venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:52.673678Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:a5ea6ce5cb5f63a29fcf4c2af2a35461fdbf5056aca3f96fe86fa5ca84678d7a","observation_id":"d681becc-2c42-4c62-a540-b101286498ab","resolution":{"observed_at":"2026-08-03T15:02:52.673678Z","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":"2026-08-03T15:02:52.834485Z","title":"Building machines that learn and think like people,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:52.834485Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:d68a76a177e4ed47d7370664061dd97418ce6bf1f94e4215189f721bf36ad508","observation_id":"c311f8c9-9abd-44fa-b4d5-671ddb2e6caa","resolution":{"observed_at":"2026-08-03T15:02:52.834485Z","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":"2026-08-03T15:02:52.946134Z","title":"How does the brain solve visual object recognition?","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:52.946134Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:6b67413143785016b9f3a4f39211d2fc6788657c2d38548cbfc22324c53507b5","observation_id":"43bf53f5-fea6-41f5-8e7e-0c853ad95230","resolution":{"observed_at":"2026-08-03T15:02:52.946134Z","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":"2026-08-03T15:02:53.054471Z","title":"Predictive reward signal of dopamine neurons,","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:53.054471Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:776fb6f018cf228a1c54faf0e2cfec90b0b844bc7637df2b9cd6053ec7e327dc","observation_id":"ccdbd48d-da8b-43cd-959d-839996904ee1","resolution":{"observed_at":"2026-08-03T15:02:53.054471Z","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":"2026-08-03T15:02:53.168467Z","title":"Prefrontal phase locking to hippocampal theta oscillations,","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:53.168467Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:798ef825d7377154bd7ceabbd0f024fc6e44d7a86eb56a00876bd5097bc58234","observation_id":"9b5a5b4e-66a1-4ee8-829f-62a0dbaf4513","resolution":{"observed_at":"2026-08-03T15:02:53.168467Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.12712","last_updated":"2023-04-13T20:41:31Z","snapshot_observed_at":"2026-08-03T04:49:15.195814Z","submitted_at":"2023-03-22T16:51:28Z","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.12712","snapshot_observed_at":"2026-08-03T15:02:53.301077Z","title":"Sparks of artificial general intelligence: Early experiments with gpt-4,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:53.301077Z"},"links":{"cited_paper":"/paper/2303.12712","citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:11a235fe397e0cb7296e1f1d3740217ae7c403ef454e99f1ce6199d12e767288","observation_id":"c05e28be-7775-4cf7-9ebe-279136ea2658","resolution":{"observed_at":"2026-08-03T15:02:53.301077Z","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":"2026-08-03T15:02:53.432158Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:53.432158Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:32c5104f2d9995cf2b5d524b9c8e9fd6523cf76f23574e17fe4e99dec49e11fe","observation_id":"59798aff-ba17-46d0-a175-d149326a1a96","resolution":{"observed_at":"2026-08-03T15:02:53.432158Z","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":"2026-08-03T15:02:53.537887Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:53.537887Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:096930b0a4e01af1ef4d71af7405db836a316ee37239cb0a5a8dbbd28412740a","observation_id":"c37b68f1-867b-4827-b039-3a07093fa1b2","resolution":{"observed_at":"2026-08-03T15:02:53.537887Z","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":"2026-08-03T15:02:53.641160Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","version":2},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-03T15:02:53.641160Z"},"links":{"citing_paper":"/paper/2512.18471"},"observation_digest":"sha256:f53b27ccc5ab325b2e7ae8bc158e0bc873315ece02e51fa9617ae365a9ffd7c5","observation_id":"06bb7b55-df65-48aa-b420-66e95cbff7e0","resolution":{"observed_at":"2026-08-03T15:02:53.641160Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2512.18471","last_updated":"2026-06-23T21:30:15Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T15:14:18.981414Z","submitted_at":"2025-12-20T19:10:38Z","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning"},"reference_resolution":{"displayed":70,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":70,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":70},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 70 of 70 outbound references and 0 inbound Pith citation observations for arXiv:2512.18471."}