{"as_of":"2026-08-09T15:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6c55801d518fa8706d411a1c9dec0c852b357d607c98661f9558088b55da9be2","coverage":[{"denominator":79,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":79,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T13:26:47.255305Z","state":"measured"},{"denominator":79,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":79,"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/2502.07256/citation-record","integrity":"/paper/2502.07256/integrity","json":"/paper/2502.07256/citation-record.json","paper":"/paper/2502.07256"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:26:48.528357Z","title":"Reconstructing computational dynamics from neural measurements with recurrent neural networks","venue":null,"work_id":"23552a57-d465-4149-8a6c-a7b0b9b3cbc1","year":2022},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:46.843620Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:300ac95fc2ed17b7cdc598358c9e467f3204b8782b9f8958617cd3e5ee1bb750","observation_id":"9b867ff8-f8ae-48d1-8910-e80541a9332f","resolution":{"observed_at":"2026-08-08T13:26:48.532967Z","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":"2026-08-08T13:26:48.513054Z","title":"Inferring brain-wide interactions using data- constrained recurrent neural network models","venue":null,"work_id":"f632d60d-4e89-4ff4-aac0-c610f025cf13","year":2020},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:46.852237Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:38081f7a53b3d8f623bff8a39f0744ef8251218ca2d1f12f46684e4c07624f5f","observation_id":"66ed2f12-ce76-434c-b752-517fbb3f9e4f","resolution":{"observed_at":"2026-08-08T13:26:48.517797Z","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":"2026-08-08T13:26:48.494653Z","title":"A neural network that finds a naturalistic solution for the production of muscle activ- ity","venue":null,"work_id":"ec7a1e4a-2dea-4184-8506-f2d9b5a9ea54","year":2015},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:46.859722Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:f118e5858f50f0bb03839d1f07550b3c0bff33c973d70eb13e78cab11acd1f5a","observation_id":"bb861f19-6f29-43ca-b6db-a310f3709e79","resolution":{"observed_at":"2026-08-08T13:26:48.501783Z","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":"2026-08-08T13:26:46.866526Z","title":"Extracting computational mechanisms from neural data using low-rank rnns","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:46.866526Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:384fbceb59738db8e9d8ab2fd484ae95e912d7a3fa478184f6ef08834ce7f7df","observation_id":"42bb804c-36b1-4686-93d5-88e9f19b58db","resolution":{"observed_at":"2026-08-08T13:26:46.866526Z","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":"2026-08-08T13:26:48.469314Z","title":"Attractor dynamics gate cortical information flow during decision-making","venue":null,"work_id":"e5705994-aeac-4bd0-89bd-72fd5b59b2f6","year":2021},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:46.873182Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:fc619893d0bd9355c65371a155db5946f029a87b115aae60d912bcefcd5aebf3","observation_id":"e111b1ac-739d-4586-8121-9643be7b066e","resolution":{"observed_at":"2026-08-08T13:26:48.474740Z","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":"2026-08-08T13:26:48.454147Z","title":"A unifying perspective on neural manifolds and circuits for cognition","venue":null,"work_id":"41d7d633-3d19-4ebd-9f50-2db0f064c89b","year":2023},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:46.879872Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:e0212675bc617c4d4d230082f86b54ecaabf67d044cb2c9365fc0a2e83950b56","observation_id":"cc435fd2-6026-41c2-9475-c7166fc18918","resolution":{"observed_at":"2026-08-08T13:26:48.459199Z","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":"2026-08-08T13:26:48.438490Z","title":"Recurrent neural networks are universal approx- imators","venue":null,"work_id":"2349d21f-0c1d-407c-9988-3314704f5fe2","year":2006},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:46.886414Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:548200a4b998674f2567328e34247cb343450f1055a22ac284716ba81c367a68","observation_id":"0c3d86a9-1df2-4f27-bc55-9f5195d42e05","resolution":{"observed_at":"2026-08-08T13:26:48.443449Z","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":"2026-08-08T13:26:46.893291Z","title":"Shap- ing dynamics with multiple populations in low-rank re- current networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:46.893291Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:b142990c51d6c533fbc853207b789b9280e35886fc8491021cc8cd8108cd1809","observation_id":"de92ae45-78b8-4f79-bf2f-f387c280194e","resolution":{"observed_at":"2026-08-08T13:26:46.893291Z","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":"2026-08-08T13:26:46.899821Z","title":"Context-dependent computation by recurrent dynamics in prefrontal cortex","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:46.899821Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:97c0f3b29cf97001b9ec5b48800b3fdf7ece7a569c12326618ca73a58727a54a","observation_id":"c64bc86d-598a-4d72-b97e-cadc15495d12","resolution":{"observed_at":"2026-08-08T13:26:46.899821Z","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":"2026-08-08T13:26:48.401873Z","title":"Backpropagation algo- rithms and reservoir computing in recurrent neural net- works for the forecasting of complex spatiotemporal dy- namics","venue":null,"work_id":"e98a9993-505c-4829-9191-9a9f77edfc31","year":2020},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:46.904600Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:aae51332a33d04b4c820bb53ae984ba29d58e12e253449740282d6dfb2da844b","observation_id":"970154cb-92ab-4d31-a7cf-85bb938677f7","resolution":{"observed_at":"2026-08-08T13:26:48.407014Z","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":"2026-08-08T13:26:48.383946Z","title":"Circuit mech- anisms for the maintenance and manipulation of in- formation in working memory","venue":null,"work_id":"a57d37a0-c4fb-4973-b51d-6191b0562de9","year":2019},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:46.909913Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:4fede758d2fdf5abdc156c215b3dfd3f945d6ef36e9bf6262861845eeec42904","observation_id":"4f41054d-2ade-414d-98bc-3d73b4010831","resolution":{"observed_at":"2026-08-08T13:26:48.389165Z","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":"2026-08-08T13:26:48.367270Z","title":"Peeking inside the black-box: a survey on explainable artificial intelli- gence (xai)","venue":null,"work_id":"ed66422f-51a3-48a1-bac2-2e19c851d8fa","year":2018},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:46.915805Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:3cfb153eca1cdc4617b90773b3846978e44e4ea9de01312af04e227710222693","observation_id":"534c3adc-9de6-42a2-a818-0bb0e7bef5d9","resolution":{"observed_at":"2026-08-08T13:26:48.372522Z","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":"2026-08-08T13:26:48.350291Z","title":"Golub, Surya Ganguli, and David Sussillo","venue":null,"work_id":"9acb3ba3-2e81-470a-8144-0b32ce356f47","year":2019},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:46.921977Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:75b47b8cb8b1b60c42625cb7aa773d8c7359e1cd165d61d014eb0481ad930ed5","observation_id":"17ad82b9-b469-4bec-9e2e-c98b47ae9d52","resolution":{"observed_at":"2026-08-08T13:26:48.356029Z","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":"2026-08-08T13:26:46.927938Z","title":"Opening the black box: low-dimensional dynamics in high-dimensional recurrent neural networks","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:46.927938Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:6ac5c7bdc4e8397c05c6e569237dcde6e806b1d5d82b0166be78907d1f90e48f","observation_id":"2a3affd1-f462-43a0-8b9a-7a2a87684f09","resolution":{"observed_at":"2026-08-08T13:26:46.927938Z","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":"2026-08-08T13:26:48.322731Z","title":"Golub and David Sussillo","venue":null,"work_id":"f5244caa-356b-413d-8595-3e802af9fb7e","year":2018},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:46.933868Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:af75be732b32357ac95490026fab84839b3bdf960703f1486e5fbbbdc30920dd","observation_id":"6b85254e-491c-44b9-9b47-5110c0779ef8","resolution":{"observed_at":"2026-08-08T13:26:48.327693Z","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":"2026-08-08T13:26:48.305537Z","title":"Rethinking brain- wide interactions through multi-region ‘network of net- works’ models","venue":null,"work_id":"c069d416-11d6-4f5b-8c88-3410208d6a94","year":2020},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:46.941499Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:9cc612ab462d32bbabd2782483e50d3867f779dd399ecfe4f4ee65a46b34d2a4","observation_id":"c8ae22a2-59dc-4b54-a218-62958cdb4654","resolution":{"observed_at":"2026-08-08T13:26:48.311342Z","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":"2026-08-08T13:26:48.287305Z","title":null,"venue":null,"work_id":"79c03a73-a2f6-453b-9b5a-813cd8f5b875","year":2022},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:46.947109Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:ba149a7cb3d8da3591b61d8815f6a3258aa02703abde8b4ca343ee35e34fdb1d","observation_id":"7213b2ee-0bcd-4f80-b832-d0e137f03b70","resolution":{"observed_at":"2026-08-08T13:26:48.292417Z","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":"2026-08-08T13:26:48.270364Z","title":"Alvarez, Asohan Amaras- ingham, Habiba Azab, Zhe S","venue":null,"work_id":"d72e572c-ec71-4f08-829a-4e4b126b65b7","year":2023},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:46.951969Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:feafbb91bdc5e0a7df3f8573bbc0d7ef53a9ec0a113ca9354ad6790d4563ce99","observation_id":"270637c7-0633-4d8b-9b06-db935b5a7b96","resolution":{"observed_at":"2026-08-08T13:26:48.275814Z","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":"2026-08-08T13:26:48.253549Z","title":"The simplicity bias in multi-task rnns: Shared attractors, reuse of dynamics, and geometric representation","venue":null,"work_id":"12414472-70d5-42f4-9003-552c7aa60d82","year":2023},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:46.957261Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:c855f2955e753680dd6d4c1a697a288e41b0850b97fbece1fee651bac722ffcc","observation_id":"62dea907-4a73-4b12-b108-d16dde1b9ee5","resolution":{"observed_at":"2026-08-08T13:26:48.259043Z","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":"2026-08-08T13:26:48.232123Z","title":"Buice, Caswell Barry, Robin Hayman, Neil Burgess, and Ila R","venue":null,"work_id":"05da89e6-62a6-431f-84a6-04c4d8fb459a","year":2013},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:46.962413Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:72267562cdf79dfc0a28f588ae6bee21bde45b3b76fac35c3f0a647766dc547d","observation_id":"515fefea-cb15-48cd-98e5-1199e5fc9fa1","resolution":{"observed_at":"2026-08-08T13:26:48.237325Z","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":"2026-08-08T13:26:48.214139Z","title":"The intrinsic attractor mani- fold and population dynamics of a canonical cognitive circuit across waking and sleep","venue":null,"work_id":"4ec77fea-083a-40a1-bc40-91d4ceaccfdd","year":2019},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:46.967349Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:10b700e5dd5a223b5edf14a9a483e2df2ea3dbaf572a5b0f61426e4ac4995afa","observation_id":"62e17234-6456-4bf8-a188-61084455176b","resolution":{"observed_at":"2026-08-08T13:26:48.220309Z","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":"2026-08-08T13:26:48.196363Z","title":"A coupled attractor model of the rodent head direc- tion system","venue":null,"work_id":"389c375a-3413-42d3-851a-227874b5242e","year":1996},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:46.972397Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:d5362ecaa21090e6659db69affb9d39525aac459b709caea507189dfaf292f73","observation_id":"505d9837-3722-4d25-bd92-7a47680e4f09","resolution":{"observed_at":"2026-08-08T13:26:48.201801Z","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":"2026-08-08T13:26:48.180262Z","title":"Recurrent network models of sequence generation and memory","venue":null,"work_id":"5b7048cf-8c22-4e4a-bd9d-82611c762f47","year":2016},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:46.977300Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:c23e79655a3998775b02e1a55b193a15b391b21a0766170ef3eb0604cab9d3b7","observation_id":"bfe89103-1e5a-4668-bc70-dad0c2a1b258","resolution":{"observed_at":"2026-08-08T13:26:48.185229Z","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":"2026-08-08T13:26:48.163265Z","title":"Dynamics on the manifold: Identifying computational dynamical activity from neural population recordings","venue":null,"work_id":"57b4d4f5-f095-4dea-b3b4-43f4f04460d2","year":2021},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:46.982373Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:7b268389e8a3e62f98f0a88d56f53e5f2bd34d7d8cdf1aaf760e089a2c5f7ffd","observation_id":"92596539-c6fc-449f-a61d-b6f7b137799f","resolution":{"observed_at":"2026-08-08T13:26:48.168408Z","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":"2026-08-08T13:26:48.146535Z","title":"Recurrent dynamics of prefrontal cortex during context-dependent decision- making","venue":null,"work_id":"5f113ec9-25fd-416e-873a-2582a98c39fc","year":2020},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:46.987467Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:628430e8f1c16c7de3fae392a424ff44dc6ff617eacf33705b2e945ec1ac91b6","observation_id":"781e1c88-04d7-4d73-8172-0b803676fa97","resolution":{"observed_at":"2026-08-08T13:26:48.152067Z","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":"2026-08-08T13:26:48.129807Z","title":"On the difficulty of learning chaotic dynamics with rnns","venue":null,"work_id":"4f60c40f-c73a-411b-8388-0f66c21b4bea","year":2022},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:46.993301Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:01fb24380e967d2c3f3db4baa5bf1d478cec4a00735675de7f5e0960eba04767","observation_id":"fb519bac-27dd-4c2f-97ba-89fbc1371395","resolution":{"observed_at":"2026-08-08T13:26:48.135689Z","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":"2026-08-08T13:26:46.998598Z","title":"On the difficulty of training recurrent neural networks","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:46.998598Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:e178c0c035a249ccf7105b8ef240f026693bc42bfbc7c49b5445119c3da9a09c","observation_id":"9cb7b87b-7a0d-460d-a288-fedf3263fa82","resolution":{"observed_at":"2026-08-08T13:26:46.998598Z","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":"2026-08-08T13:26:47.003353Z","title":"Bifurcations in the learning of recurrent neural networks 3","venue":null,"work_id":null,"year":1992},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.003353Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:d2c860acdfb6ef687f0d777c12c6a4da5b01070512075c052aaa1fbbdeafb1bb","observation_id":"a06aa2d3-ce38-43e7-b31f-6e76f0d5a42b","resolution":{"observed_at":"2026-08-08T13:26:47.003353Z","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":"2026-08-08T13:26:47.008197Z","title":"Identifying non- linear dynamical systems with multiple time scales and long-range dependencies","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.008197Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:7be34f42f7c4e103f0dbcb2bc30e7ff399bc25526ea455c3f2589d29f00dbc18","observation_id":"fed7b871-3f78-4a3c-bcd4-fa48c72964bd","resolution":{"observed_at":"2026-08-08T13:26:47.008197Z","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":"2026-08-08T13:26:48.075169Z","title":"Identifying nonlinear dy- namical systems via generative recurrent neural networks with applications to fmri","venue":null,"work_id":"2a67e0e4-e9bc-4ed4-ab78-348f47de114d","year":2019},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.012948Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:2f1c403e49e5fba58e59bb1b428cd0887bfe78aef21706082ad88e297e2360b6","observation_id":"9083d54c-bf59-4e1d-925a-47be22dae2ef","resolution":{"observed_at":"2026-08-08T13:26:48.080613Z","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":"2026-08-08T13:26:47.017471Z","title":"The role of population structure in computations through neural dynamics","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.017471Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:b0fe19c34780cfdbd503f20c5086ba2051f0a4c325945750afe7d14c478eff3a","observation_id":"546e4444-cf21-46b5-b166-c4004298cdb3","resolution":{"observed_at":"2026-08-08T13:26:47.017471Z","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":"2026-08-08T13:26:47.022194Z","title":"Task representations in neural networks trained to perform many cognitive tasks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.022194Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:b012b702097fe12d6f77f8878b15eaa7ce883cd82c3c03b70747b7f7a82d4aa1","observation_id":"4365ea98-e125-49c0-b5dd-75dfc350581e","resolution":{"observed_at":"2026-08-08T13:26:47.022194Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.17561","last_updated":"2023-10-26T16:49:44Z","snapshot_observed_at":"2026-08-03T13:16:43.728045Z","submitted_at":"2023-10-26T16:49:44Z","title":"Bifurcations and loss jumps in RNN training","version":1},"cited_work":{"arxiv_id":"2310.17561","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.17561","snapshot_observed_at":"2026-08-08T13:26:47.373318Z","title":"Bifurcations and loss jumps in RNN training","venue":"cs.LG","work_id":"050c5e50-4a71-41db-aea0-42b5b07f127a","year":2023},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.027072Z"},"links":{"cited_paper":"/paper/2310.17561","citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:a143ad18a4decb933efae2bd30d54104c6d558dbeda9c11ce87aceb08661f0df","observation_id":"5e0bbff9-eb1c-4784-9c5e-f0fe015665fc","resolution":{"observed_at":"2026-08-08T13:26:47.378900Z","resolver_source":"local_arxiv","status":"verified_exact"},"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":"2306.07125","last_updated":"2023-06-12T14:01:30Z","snapshot_observed_at":"2026-08-05T19:38:01.306018Z","submitted_at":"2023-06-12T14:01:30Z","title":"On the Dynamics of Learning Time-Aware Behavior with Recurrent Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.07125","snapshot_observed_at":"2026-08-08T13:26:47.032432Z","title":"On the dynamics of learning time- aware behavior with recurrent neural networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.032432Z"},"links":{"cited_paper":"/paper/2306.07125","citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:4b14fa55a09d0e91405e648b5245a7338c6ad4293720951d63989a4b261ecf85","observation_id":"7cd0cf58-a310-4330-be56-1d591ea47c32","resolution":{"observed_at":"2026-08-08T13:26:47.032432Z","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":"2026-08-08T13:26:47.037842Z","title":"Monfared and D","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.037842Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:0f3147726f708b4d12c992dd775627931119669855a03081ac057ba0bf8c88c3","observation_id":"fb94ff8a-7de8-402c-bf55-b298f0bf66d0","resolution":{"observed_at":"2026-08-08T13:26:47.037842Z","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":"2026-08-08T13:26:47.043119Z","title":null,"venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.043119Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:30ddfe46ce1f2f617eb9cf1f959a210c8fce5edc193164ab714c5fd9b7a75a2f","observation_id":"8c997f28-777d-4090-b81b-39380cfeee7d","resolution":{"observed_at":"2026-08-08T13:26:47.043119Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.04406","last_updated":"2023-10-27T09:30:19Z","snapshot_observed_at":"2026-08-09T09:18:07.596557Z","submitted_at":"2023-06-07T13:04:34Z","title":"Generalized Teacher Forcing for Learning Chaotic Dynamics","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.04406","snapshot_observed_at":"2026-08-08T13:26:47.049830Z","title":"Generalized teacher forcing for learn- ing chaotic dynamics","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.049830Z"},"links":{"cited_paper":"/paper/2306.04406","citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:43a99d50fa5ccd7c30f8f1a458fb3e9ac05545afde8b6a631599076764f1f8a3","observation_id":"70ac294b-add0-4806-80f5-f02302101633","resolution":{"observed_at":"2026-08-08T13:26:47.049830Z","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":"2026-08-08T13:26:48.015675Z","title":"Nonlinear dynamics and chaos: With applications to physics, biology, chemistry, and engineer- ing","venue":null,"work_id":"22794f75-154b-4dec-a21f-e3e2e19ccc59","year":2018},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.055246Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:5bb8f956591f1b90cd8a19e6c7ad288205d0ab5f87afd7d24dcc6d49462896c6","observation_id":"719aa72d-cfef-408e-a0f6-ed04fbfabb28","resolution":{"observed_at":"2026-08-08T13:26:48.020712Z","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":"2026-08-08T13:26:47.999480Z","title":"Preventing gradient explosions in gated recur- rent units","venue":null,"work_id":"4f51732d-fd2a-4eb4-842a-e01165504642","year":2017},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.060153Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:7a3ac3a70bdead34dc75082d548a130e50abe6796219077cf75c310c672f87f1","observation_id":"1058c0cc-5f08-4fcf-8239-0f0527925e70","resolution":{"observed_at":"2026-08-08T13:26:48.004698Z","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":"2026-08-08T13:26:47.065019Z","title":"The effect of the forget gate on bifurcation boundaries and dynamics in re- current neural networks and its implications for gradient- based optimization","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.065019Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:f14ae9ffa7cea64a4678fb0caf80fdce24632805853b93fca423de77ba75a571","observation_id":"105ffc7e-7c38-4d1e-af0e-33cdfb00fce1","resolution":{"observed_at":"2026-08-08T13:26:47.065019Z","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":"2026-08-08T13:26:47.972053Z","title":"Ribeiro, Koen Tiels, Luis A","venue":null,"work_id":"0aa07cf9-69c7-421c-a8ce-b2cea0433037","year":2020},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.069548Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:e2eaca2a08a5e91ea0d75ae015d0d2f30f2b5f1b1be687d7a001d4f05e2866be","observation_id":"8f630904-7078-40f5-9d0d-0f26a0ff8f82","resolution":{"observed_at":"2026-08-08T13:26:47.976983Z","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":"2026-08-08T13:26:47.956210Z","title":"Chaos in random neural networks","venue":null,"work_id":"511f8957-cbff-44a4-a568-3cb5703e8e8d","year":1988},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.074457Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:c1eff8226c1a797aab58e3463356a136619e84803ff29fc33bea54d31cc88884","observation_id":"c06d6703-98f4-4a9f-85c5-e279971ebcba","resolution":{"observed_at":"2026-08-08T13:26:47.960963Z","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":"2026-08-08T13:26:47.939476Z","title":"Real-time computing without stable states: A new framework for neural computation based on per- turbations","venue":null,"work_id":"427590fb-4254-4f0d-b93e-8d3c63c5b67a","year":2002},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.079919Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:83ff4609361027914352bd417378647196ef4cabefcb045c2741de1859f812a8","observation_id":"431b9f5d-ca3c-4ac6-b756-a51b7fa5aa7a","resolution":{"observed_at":"2026-08-08T13:26:47.944684Z","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":"2026-08-08T13:26:47.922602Z","title":"Harnessing nonlinear- ity: Predicting chaotic systems and saving energy in wire- less communication","venue":null,"work_id":"a3e13960-fd62-49d5-9b71-85e7e240dc96","year":2004},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.085359Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:1bf4664dd223ce44aee01a62f40c08775468ecee3356b2012647579657509789","observation_id":"46f70cb7-ee84-446c-b544-9c79623ade00","resolution":{"observed_at":"2026-08-08T13:26:47.927960Z","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":"2026-08-08T13:26:47.090425Z","title":"Generating coherent patterns of activity from chaotic neural networks","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.090425Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:e007089925c1cda6164afda1c5dc059c69c66a55a8ff7daa0ba60f90e16f4b70","observation_id":"3a736cd7-a603-4f0e-9d3a-796d40120404","resolution":{"observed_at":"2026-08-08T13:26:47.090425Z","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":"2026-08-08T13:26:47.891631Z","title":"full-force: A target- based method for training recurrent networks","venue":null,"work_id":"55a141e9-c19f-494d-8d48-2a4f0fd90c49","year":2018},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.095262Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:15097c887495de4aee13f208a2fcaa86d8d3a3e17873de2ce67331985a68b533","observation_id":"dc795479-871e-423c-9d6b-4759fedfb5a2","resolution":{"observed_at":"2026-08-08T13:26:47.897520Z","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":"2501.02378","last_updated":"2026-04-15T05:10:03Z","snapshot_observed_at":"2026-07-31T16:53:57.321287Z","submitted_at":"2025-01-04T20:49:20Z","title":"A ghost mechanism: An analytical model of abrupt learning in recurrent networks","version":2},"cited_work":{"arxiv_id":"2501.02378","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.02378","snapshot_observed_at":"2026-08-08T13:26:47.313893Z","title":"A ghost mechanism: An analytical model of abrupt learning in recurrent networks","venue":"cs.LG","work_id":"6b012613-eb5f-4deb-b538-b776ca29867b","year":2025},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.101053Z"},"links":{"cited_paper":"/paper/2501.02378","citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:e0a4c929ed19d7be12f2d47dd18f074952a8863b8a59c8e38b39956d41d5fbc9","observation_id":"f922ace7-fe49-4507-91e6-4c40ec5ed2f7","resolution":{"observed_at":"2026-08-08T13:26:47.321434Z","resolver_source":"local_arxiv","status":"verified_exact"},"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":"2026-08-08T13:26:47.872347Z","title":"A line attractor encoding a persistent internal state requires neuropeptide signal- ing","venue":null,"work_id":"9bbef190-ab34-4aee-8dd2-a51589e6d96b","year":2024},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.106435Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:4d183032c99f06a17210d2695c7a19036c82ba869f0ada0b3253c29e401aeca1","observation_id":"c2f58777-83d1-4c79-8944-f0cf439ef22c","resolution":{"observed_at":"2026-08-08T13:26:47.877834Z","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":"2026-08-08T13:26:47.856017Z","title":"Ring attractor dynamics in the drosophila central brain","venue":null,"work_id":"222be8af-3dbe-40e3-b1c3-f5dbc8c7de67","year":2017},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.112116Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:6247595624475e2431cafac325007f51b7a5df217966f8ee29633eeca5208645","observation_id":"5cc2371b-8584-4155-bd47-248665a0e748","resolution":{"observed_at":"2026-08-08T13:26:47.861290Z","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":"2026-08-08T13:26:47.839508Z","title":"Toroidal topology of population activity in grid cells","venue":null,"work_id":"4170ef06-6c8c-429a-88aa-6ec48cd7f6f7","year":2022},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.116959Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:44c2831a2ffca1a04db83f490e8b1fcedd1713188a52d4b94f48c6df686a39fa","observation_id":"1b203649-a927-4d7f-8378-354628d380cc","resolution":{"observed_at":"2026-08-08T13:26:47.844785Z","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":"2026-08-08T13:26:47.822459Z","title":"Generalized teacher forcing for learning chaotic dynamics","venue":null,"work_id":"7d6c1377-9433-402a-bf1f-f4a036f9ecd7","year":2023},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.121802Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:81a4657c389a131271d14e10a4290c9d34336847f8a479dca35efd1ae62c4583","observation_id":"2cd6c1e7-2cc1-4208-abbf-e7ec286bd1d2","resolution":{"observed_at":"2026-08-08T13:26:47.827772Z","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":"2026-08-08T13:26:47.804552Z","title":"Beyond exploding and vanishing gradi- ents: analysing rnn training using attractors and smooth- ness","venue":null,"work_id":"74aaee0d-93a8-4afd-862b-1026039c6f6c","year":2020},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.126412Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:c647bc86ee98a884cdd88370b5d05c120a2cd75a92d294363ae2ec25225f1838","observation_id":"b87834bf-e680-4d52-bbb0-70d8ede23f60","resolution":{"observed_at":"2026-08-08T13:26:47.810199Z","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":"2026-08-08T13:26:47.131366Z","title":"Fixedpointfinder: A tensorflow toolbox for identifying and characterizing fixed points in recurrent neural networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.131366Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:57029b387a5a341ea17a99d96cb79c74e440897e818df0f69c64bb786f88e51c","observation_id":"5c3c2b3f-0800-4634-9ff5-58d9ef6d24e1","resolution":{"observed_at":"2026-08-08T13:26:47.131366Z","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":"2026-08-08T13:26:47.774269Z","title":"Automatic differentiation in pytorch","venue":null,"work_id":"a18924e8-a7bd-4879-bf12-15282a7c2fe2","year":2017},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.136140Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:813d9cf92174eea0fd349f456ed05528c8039506f185d77716801cb026139087","observation_id":"85a5f104-956f-46e9-bb6d-e33b0a239936","resolution":{"observed_at":"2026-08-08T13:26:47.779563Z","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":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-08T13:26:47.140810Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.140810Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:6522dfbf3db2dca456d62ebae633a798082f3feb9b90750938f60e4595278e66","observation_id":"1aa2a6c6-979b-41bc-a0c3-886d052439e0","resolution":{"observed_at":"2026-08-08T13:26:47.140810Z","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":"2026-08-08T13:26:47.756475Z","title":"Low- dimensional dynamics for working memory and time en- coding","venue":null,"work_id":"e1e8abe4-8755-42b0-a979-f6c6e2d0aca1","year":2020},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.146092Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:f60621a84b085619d1067f9de3e256dfffa5dc54bee2a01dd3966b4970750390","observation_id":"6d2609e3-203a-488e-9d79-ef760dd5e288","resolution":{"observed_at":"2026-08-08T13:26:47.762493Z","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":"2026-08-08T13:26:47.739702Z","title":"Ramping activity is a cor- tical mechanism of temporal control of action","venue":null,"work_id":"977a2616-c130-4f05-b6d1-6258f58d9796","year":2016},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.151080Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:9ffec10a6c715ccdc0491cd0ad3222994731fe8de9e4e1958b9cb03504d2ebea","observation_id":"b571c9d6-44eb-47c0-a509-845562c5437f","resolution":{"observed_at":"2026-08-08T13:26:47.744816Z","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":"2026-08-08T13:26:47.156045Z","title":"Cornn: Convex optimization of recurrent neural networks for rapid inference of neural dynam- ics","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.156045Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:e2426b332bdcbfff963ae9ab7c191a5eb85f35c4a4b07d0546ecda1ea4d73990","observation_id":"2721e742-758a-434a-8361-972509fd71a4","resolution":{"observed_at":"2026-08-08T13:26:47.156045Z","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":"2026-08-08T13:26:47.161523Z","title":"Neural networks and physical systems with emergent collective computational abilities","venue":null,"work_id":null,"year":1982},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.161523Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:025b659bd6d2effaeac3402e47f610be59a9c31e64af06063a355f688a97ac6a","observation_id":"2234883e-900f-4d84-b5c8-2c2371c903a4","resolution":{"observed_at":"2026-08-08T13:26:47.161523Z","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":"2026-08-08T13:26:47.699011Z","title":"Domain adaptive video segmentation via temporal consistency regularization, 2021","venue":null,"work_id":"c849aa6c-e8ec-43e2-82e5-6ce2c32bd00c","year":2021},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.166700Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:71f690bd46455f895c57dd0ecf186d114aa1c8cd8241ad1f45e8ce35fc52c083","observation_id":"15cc679e-df77-4e23-8775-15950e7326be","resolution":{"observed_at":"2026-08-08T13:26:47.704302Z","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":"2026-08-08T13:26:47.680838Z","title":"Preserving semantic and temporal consistency for unpaired video- to-video translation","venue":null,"work_id":"906182b7-64fa-468b-8b8b-d7e335bad3b5","year":2019},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.171469Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:458d44594d29bd13cbdacc80c0165bbd2d587441c85f2c6e6a1511dc9f9b5b6a","observation_id":"9109d34f-3111-4cc5-bd57-ec3e252ce42b","resolution":{"observed_at":"2026-08-08T13:26:47.686683Z","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":"2026-08-08T13:26:47.661697Z","title":"Coherent online video style transfer, 2017","venue":null,"work_id":"7581ea8d-4d6d-4987-80d0-c86dcde5e97c","year":2017},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.176149Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:c434cac5e1cc441b1138d6ba685a4dded00b8f9009ccda7d712c477628bc0475","observation_id":"df2a72a9-8cc3-4096-b7bb-011174a1c66a","resolution":{"observed_at":"2026-08-08T13:26:47.666619Z","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":"2026-08-08T13:26:47.644213Z","title":"Real- time neural style transfer for videos","venue":null,"work_id":"bf11c30e-ef54-4a6a-8472-6eea76db3172","year":2017},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.180901Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:1ac7e1e6a9a76c1d4b82bb31ee24ecc828cc47b26729a708cfa5ad7a2d8d57e2","observation_id":"db085e67-52d4-47cc-b1f1-94cc9e22fe63","resolution":{"observed_at":"2026-08-08T13:26:47.649955Z","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":"2026-08-08T13:26:47.627409Z","title":"Artistic style transfer for videos","venue":null,"work_id":"178f5bd1-e6e5-491e-99a0-4c74696eeec2","year":2016},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.185413Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:9866de7f7cced18eec62b65efaa01c893a76dc4ad8ce79392c38140dbbe2e9f3","observation_id":"1acf87e9-5cd4-4794-bf73-add3bb41aca3","resolution":{"observed_at":"2026-08-08T13:26:47.632424Z","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":"2026-08-08T13:26:48.543107Z","title":"Finally, most relevantly, [3] has utilized a penalty term that regularized the first-order dynamics in RNNs to incentivize RNNs to find simpler final solutions","venue":null,"work_id":"51403c8e-fb16-415b-9702-e0c1957133e6","year":null},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:46.836343Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:de52279c8d4bf7840cd903ac65485f82332549873e0c57d75dde45b8072d848e","observation_id":"c08f6037-da03-4c88-95ff-0daec465b293","resolution":{"observed_at":"2026-08-08T13:26:48.547637Z","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":"2026-08-08T13:26:47.611469Z","title":"Learning differential equations that are easy to solve","venue":null,"work_id":"606b1758-5803-46d8-b3c8-7f84d9361f89","year":2020},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.190205Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:51f557106124637fdf4e0c8d2cd4d7a100fc443a625384d9b47b981153d75001","observation_id":"6547da30-3d3a-4066-a646-be7c84ec64f0","resolution":{"observed_at":"2026-08-08T13:26:47.617169Z","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":"2026-08-08T13:26:47.595056Z","title":"Understanding the difficulty of training deep feedforward neural networks","venue":null,"work_id":"cdb86aa4-9bbe-4529-afd2-931400f7810d","year":2010},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.195021Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:3a4832557335b23d8bbf5f83869ff49eb75c4e5123087743732f88ce2502db81","observation_id":"0a1a2d03-2cf1-49b7-952d-9bbb8d8f12d3","resolution":{"observed_at":"2026-08-08T13:26:47.600891Z","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":"2026-08-08T13:26:47.579185Z","title":"Chaotic recurrent neural networks for brain modelling: A review","venue":null,"work_id":"a1253eb3-2c17-488f-bcfa-a8a649d6d7f1","year":2024},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.200084Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:f78cdb9b62333a0f5c702331d4837fb269eae42368010c292ee1df037feab9df","observation_id":"a9a98aaa-7ece-4bf0-bf13-add4ae9382f1","resolution":{"observed_at":"2026-08-08T13:26:47.584417Z","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":"2026-08-08T13:26:47.562658Z","title":"Robust timing and motor patterns by taming chaos in recurrent neural networks","venue":null,"work_id":"e7e411e2-14c7-476c-89b1-72d6a29fa0d6","year":2013},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.204791Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:1cfc0185c98328247733d60fff66d8b07a543f49d88f596c0c707725926545b6","observation_id":"bc8d2dae-7969-4785-a591-c4ce8a01d598","resolution":{"observed_at":"2026-08-08T13:26:47.568090Z","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":"2026-08-08T13:26:47.546263Z","title":"PLRNN dynamical systems equa- tion is as follows","venue":null,"work_id":"6a174265-406d-4191-85c9-f8ee24962d54","year":null},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.209489Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:95e3542267e4a7e722907404840840469522ec98a5de52cbe9271d6803d9f248","observation_id":"192d8d6c-3a2d-4e7b-bee5-944e904a4d28","resolution":{"observed_at":"2026-08-08T13:26:47.551589Z","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":"2026-08-08T13:26:47.530319Z","title":"Input to each trial, U = {(u1 1, u2 1), (u1 2, u2 2), ...,(u1 T , u2 T )}, has the shape of T × 2, where T is the trial length","venue":null,"work_id":"e2ba9adc-6951-448b-805d-e542c0b1e4d6","year":null},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.214336Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:bfe2f2a8da01684897044ac6734675305ef4cabe442a4017eae8209976bdc724","observation_id":"e2667903-30ad-4fb9-8abb-0dc98164019b","resolution":{"observed_at":"2026-08-08T13:26:47.535903Z","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":"2026-08-08T13:26:47.513591Z","title":null,"venue":null,"work_id":"90788b55-fe2d-4abb-a891-3ed10004c937","year":null},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.219451Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:ada5c39418143da7985c2133b67ec00ac0c29a983586dd7e7a2c15c2277d5847","observation_id":"11d6ec65-0927-47e3-88fe-c16763ce7021","resolution":{"observed_at":"2026-08-08T13:26:47.519296Z","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":"2026-08-08T13:26:47.494178Z","title":"We first picked a data batch with 100 trials from the test set","venue":null,"work_id":"b63622c6-f8fc-47bf-b1e3-1ae3c61bd35b","year":null},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.224410Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:8f0ed85693be5e309b9c25892bc7c323a6f3cd8935d4c9dea5e26101b944a844","observation_id":"d12fcfbe-e6e1-4f70-a564-695e560e2f92","resolution":{"observed_at":"2026-08-08T13:26:47.501474Z","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":"2026-08-08T13:26:47.476821Z","title":"To fit the data to PCA, we first fed 100 trials from the test set to the fully- trained PLRNN and obtained the corresponding activa- tions x[t]s","venue":null,"work_id":"280e0b12-83da-4a72-ada2-bec196297a7b","year":null},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.229214Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:bb38d6ce4537646f11f66a3d70ddc40c061804e64a15aefcdaf44f4c7191d7dc","observation_id":"aa59240a-f1d0-417f-9552-51f175ad9ca2","resolution":{"observed_at":"2026-08-08T13:26:47.482217Z","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":"2026-08-08T13:26:47.459097Z","title":null,"venue":null,"work_id":"a53b93e2-0a83-44e1-9ec7-0f7d02b09f21","year":null},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.235033Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:1de57b381eee7a54e6b379bdcf1bdba94e61a6d1a0973a8d702d13c066e27f89","observation_id":"b900bdec-2050-4a7e-99c8-084b84d1f0d1","resolution":{"observed_at":"2026-08-08T13:26:47.464284Z","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":"2026-08-08T13:26:47.440895Z","title":"We picked 10 unregularized PLRNNs and 10 PLRNNs trained with MAR and MAI for the delayed addition task from the networks shown in Fig","venue":null,"work_id":"1e6f3bd0-3b4e-462b-94d7-b726654c5c4e","year":null},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.240381Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:b59b456c2c4b29a68b46314c39c12e7e71a64caecede3f661916606d621d7f24","observation_id":"45dc88ed-424b-4ff3-ac99-a323abef8b16","resolution":{"observed_at":"2026-08-08T13:26:47.446718Z","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":"2026-08-08T13:26:47.425049Z","title":"To conduct this analysis, we selected 3 representative networks from Fig","venue":null,"work_id":"ed32bb04-43b3-423a-af22-17cefab2d268","year":null},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.245171Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:86e23edc741f6ba766c4a99dd82a7a012ad0a4a923b477cef8bbcb90f6da237d","observation_id":"00afce8d-afcd-41c2-93df-8354981453b5","resolution":{"observed_at":"2026-08-08T13:26:47.430164Z","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":"2026-08-08T13:26:47.407961Z","title":"epoch b is computed based on the stalling points in the loss function during training","venue":null,"work_id":"b437d705-2345-4b3d-a8d5-1719adccf28d","year":null},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.249969Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:10ac9e0cb7c6069fbeb9e01ccf6082969a82643c286128801ce9ef3ce3750ee6","observation_id":"018cdf5b-a797-40c9-a84f-1ba08affd7cb","resolution":{"observed_at":"2026-08-08T13:26:47.412973Z","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":"2026-08-08T13:26:47.391264Z","title":"(S11) Here, ri is the activity or firing rate of neuron i and zi is the total input current to neuron i","venue":null,"work_id":"0c3915e9-0cc0-4894-8f67-a3a866846ebb","year":2000},"citing_paper":{"arxiv_id":"2502.07256","last_updated":"2025-02-11T04:51:27Z","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-08T13:26:47.255305Z"},"links":{"citing_paper":"/paper/2502.07256"},"observation_digest":"sha256:781425d122f4b872d50ac5be1621725f43b2639c0efbcc4dfa22208905e17e23","observation_id":"36219841-20af-433b-b1eb-dbfdd26c3f57","resolution":{"observed_at":"2026-08-08T13:26:47.396975Z","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":"2502.07256","last_updated":"2025-02-11T04:51:27Z","latest_version":1,"primary_category":"q-bio.NC","snapshot_observed_at":"2026-08-09T09:18:43.701283Z","submitted_at":"2025-02-11T04:51:27Z","title":"Understanding and controlling the geometry of memory organization in RNNs"},"reference_resolution":{"displayed":79,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":22,"verified_exact":2,"verified_fuzzy":55},"total_outbound_references":79},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 79 of 79 outbound references and 0 inbound Pith citation observations for arXiv:2502.07256."}