{"as_of":"2026-08-22T15:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2d2f504e973769e62474b0cc55d486d6466e402f7b4dbd4f34a642c2a12091dc","coverage":[{"denominator":38,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":38,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T10:32:48.105394Z","state":"measured"},{"denominator":38,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":38,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+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/2510.09379/citation-record","integrity":"/paper/2510.09379/integrity","json":"/paper/2510.09379/citation-record.json","paper":"/paper/2510.09379"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:32:47.887507Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:47.887507Z"},"links":{"citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:cb74d05739200f0aae7dc7e1ff7d9598e5e0ad9bdad7084232ef8a933da648d7","observation_id":"179a2f3d-82d9-4829-ad36-40f8dbf248cd","resolution":{"observed_at":"2026-08-04T10:32:47.887507Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.04927","last_updated":"2023-12-08T09:44:25Z","snapshot_observed_at":"2026-08-16T14:36:34.764352Z","submitted_at":"2023-12-08T09:44:25Z","title":"Zoology: Measuring and Improving Recall in Efficient Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.04927","snapshot_observed_at":"2026-08-04T10:32:47.894083Z","title":"Zoology: Measuring and Improving Recall in Efficient Language Models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:47.894083Z"},"links":{"cited_paper":"/paper/2312.04927","citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:bdf60063ec9030c4fff3b139603ba3293def3407b39b04be3f60feac12904560","observation_id":"8330e56d-fb73-40ad-abb7-df3daa077a62","resolution":{"observed_at":"2026-08-04T10:32:47.894083Z","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":"2026-08-04T10:32:47.900572Z","title":"Self-attention networks localize when qk-eigenspectrum concentrates","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:47.900572Z"},"links":{"citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:42242d26f915a9506887999b80268ec565865dacb9dac1e5ef3eeb62137f77d0","observation_id":"9e23560c-79f8-410c-81bd-e18b3a0c35d9","resolution":{"observed_at":"2026-08-04T10:32:47.900572Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.04517","last_updated":"2024-12-06T15:42:07Z","snapshot_observed_at":"2026-08-16T13:54:34.627474Z","submitted_at":"2024-05-07T17:50:21Z","title":"xLSTM: Extended Long Short-Term Memory","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.04517","snapshot_observed_at":"2026-08-04T10:32:47.907460Z","title":"xLSTM: Extended Long Short-Term Memory","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:47.907460Z"},"links":{"cited_paper":"/paper/2405.04517","citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:593d60fab94851c71a3bce47e8b67e7a2a291d0e748ac0bcb486273f619ba60c","observation_id":"1a375ff7-dc69-496d-9aea-80c10113872c","resolution":{"observed_at":"2026-08-04T10:32:47.907460Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.08823","last_updated":"2021-06-16T14:38:42Z","snapshot_observed_at":"2026-08-20T02:56:57.383317Z","submitted_at":"2021-06-16T14:38:42Z","title":"Eigen Analysis of Self-Attention and its Reconstruction from Partial Computation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.08823","snapshot_observed_at":"2026-08-04T10:32:47.914053Z","title":"Eigen analysis of self-attention and its reconstruction from partial computation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:47.914053Z"},"links":{"cited_paper":"/paper/2106.08823","citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:360bb548a7d6e51f887edb80d6b59640008645e597f8f849303f779534352871","observation_id":"a3f4b9a9-1be7-4907-b09d-c2bb70815bda","resolution":{"observed_at":"2026-08-04T10:32:47.914053Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.07258","last_updated":"2022-07-12T23:45:14Z","snapshot_observed_at":"2026-08-02T09:20:40.804790Z","submitted_at":"2021-08-16T17:50:08Z","title":"On the Opportunities and Risks of Foundation Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.07258","snapshot_observed_at":"2026-08-04T10:32:47.921142Z","title":"On the opportunities and risks of foundation models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:47.921142Z"},"links":{"cited_paper":"/paper/2108.07258","citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:1bd3874cacbaa1fb4f007d4b39bb4440a06fc0c838f59f8012637f200c740db0","observation_id":"db8f6074-1de8-4fae-a314-e1f4bb77773e","resolution":{"observed_at":"2026-08-04T10:32:47.921142Z","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":"2026-08-04T10:32:47.926577Z","title":"Language Models are Few-Shot Learners","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:47.926577Z"},"links":{"citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:62125cee6964b44aae293c09b63d14a46b7098b5ac3938c9da86a27d5299fdd7","observation_id":"261001d6-4c64-4df6-aff3-479583984fa2","resolution":{"observed_at":"2026-08-04T10:32:47.926577Z","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":"2026-08-04T10:32:47.931761Z","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms with Structured State Space Duality","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:47.931761Z"},"links":{"citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:a85737b2eba746ad94fdd5862a97cb953f0c1259d24a68281de29755deb77df5","observation_id":"f4b3a1eb-2910-4684-a513-b2c340307273","resolution":{"observed_at":"2026-08-04T10:32:47.931761Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.14052","last_updated":"2023-04-29T03:18:40Z","snapshot_observed_at":"2026-08-18T19:17:21.619873Z","submitted_at":"2022-12-28T17:56:03Z","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.14052","snapshot_observed_at":"2026-08-04T10:32:47.936254Z","title":"Fu, Tri Dao, Khaled K","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:47.936254Z"},"links":{"cited_paper":"/paper/2212.14052","citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:d8513605575f9fc6d4a9ea8eb52b7a07a3740961b01d580f61f2c90a9c2195be","observation_id":"1600c0ae-ea55-4f6c-929c-fe189e12c0f9","resolution":{"observed_at":"2026-08-04T10:32:47.936254Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.12537","last_updated":"2025-03-18T13:13:18Z","snapshot_observed_at":"2026-08-19T18:11:10.921042Z","submitted_at":"2024-11-19T14:35:38Z","title":"Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.12537","snapshot_observed_at":"2026-08-04T10:32:47.941368Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:47.941368Z"},"links":{"cited_paper":"/paper/2411.12537","citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:63828f734dffb8fc8de3c13865fe4143bf7d8d9447745fabe3ea2a906e7a10df","observation_id":"4ec16b14-5325-4723-b86b-9855bd7a7c2f","resolution":{"observed_at":"2026-08-04T10:32:47.941368Z","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":"2026-08-04T10:32:47.946813Z","title":"HiPPO: Recurrent Memory with Optimal Polynomial Projections","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:47.946813Z"},"links":{"citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:3a5018427f6d4630acf0158701a1bc6174b979007167bd7c393f6e1d6333dca6","observation_id":"030efb75-ada4-4e87-baa1-16455307534f","resolution":{"observed_at":"2026-08-04T10:32:47.946813Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.00396","last_updated":"2022-08-05T17:54:38Z","snapshot_observed_at":"2026-08-14T01:02:41.198730Z","submitted_at":"2021-10-31T03:32:18Z","title":"Efficiently Modeling Long Sequences with Structured State Spaces","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.00396","snapshot_observed_at":"2026-08-04T10:32:47.952013Z","title":"Efficiently modeling long sequences with structured state spaces","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:47.952013Z"},"links":{"cited_paper":"/paper/2111.00396","citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:a7d2514a422305a6e39d9d08c8c7995a9216f85c0872eff94ac30419bad9b320","observation_id":"6eed4298-d30d-49af-b650-4e9013d256e9","resolution":{"observed_at":"2026-08-04T10:32:47.952013Z","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":"2026-08-04T10:32:47.957574Z","title":"Efficiently Modeling Long Sequences with Structured State Spaces","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:47.957574Z"},"links":{"citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:dd627fd8dc72ddcb625710e8ef19fa622adc07dbedfffb4bdff63264db18dd31","observation_id":"c1b6dedf-cf8a-47f3-a1e3-21129bfdee93","resolution":{"observed_at":"2026-08-04T10:32:47.957574Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.07964","last_updated":"2019-11-18T21:28:02Z","snapshot_observed_at":"2026-08-13T12:25:46.847869Z","submitted_at":"2019-11-18T21:28:02Z","title":"Eigenvalue Normalized Recurrent Neural Networks for Short Term Memory","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.07964","snapshot_observed_at":"2026-08-04T10:32:47.962886Z","title":"Eigenvalue normalized recurrent neural networks for short term memory, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:47.962886Z"},"links":{"cited_paper":"/paper/1911.07964","citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:bc34593ed09cd030535c78c159e9f918b613f16856f2ecefccfe9a389dd9e3d4","observation_id":"9400816f-373d-49fa-9e16-2f89e8c98c4b","resolution":{"observed_at":"2026-08-04T10:32:47.962886Z","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":"10.1007/s11571-022-09802-5","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Different eigenvalue distributions encode the same temporal tasks in recurrent neural networks","venue":"Cognitive Neurodynamics","work_id":"965d7119-841a-4c19-878b-0932b85ee5c8","year":2022},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:47.967054Z"},"links":{"citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:f02def35068142789c8612b8a491a552099a2c7b690f986ff0038aead7d0d2de","observation_id":"fc504304-7314-4cbb-9ee0-e9f6424f5780","resolution":{"observed_at":"2026-08-04T10:34:04.728254Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-04T10:32:47.971971Z","title":"Linear systems, volume 156","venue":null,"work_id":null,"year":1980},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:47.971971Z"},"links":{"citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:e47c28d8cb7daeea1b480e3ec50efcf31d9be7abb8983bb1b200cfe10618aa61","observation_id":"d4d5c56e-df53-4375-8f59-86126c2e66fa","resolution":{"observed_at":"2026-08-04T10:32:47.971971Z","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":"2026-08-04T10:32:47.977452Z","title":"Transformers are RNN s: fast autoregressive transformers with linear attention","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:47.977452Z"},"links":{"citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:3e602caa3a7c5ace11544d03d25f8d5a9df3d616331f652e720acf35c4593c57","observation_id":"6322d436-a5fe-4ad6-be0d-1ec3cfbf56b3","resolution":{"observed_at":"2026-08-04T10:32:47.977452Z","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":"2026-08-04T10:32:47.981927Z","title":"Decoupled Weight Decay Regularization","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:47.981927Z"},"links":{"citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:11ace419630b33ea6ac81ae3e0983e512409d2a3a694bf7f74ec54348f8ddf0f","observation_id":"6af73e3c-89f0-48f4-a401-b4e218c4e965","resolution":{"observed_at":"2026-08-04T10:32:47.981927Z","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":"2026-08-04T10:32:47.987405Z","title":"Pointer sentinel mixture models, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:47.987405Z"},"links":{"citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:d50cc0fc7ec504f4918c1f8c64ae6bd77dd118a12a786d309b42819c079b0e28","observation_id":"0d9c491d-b24a-4f27-b17b-7d94acd8df13","resolution":{"observed_at":"2026-08-04T10:32:47.987405Z","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":"2026-08-04T10:32:47.992307Z","title":"When recalling in-context, transformers are not ssms","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:47.992307Z"},"links":{"citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:add0619b236112a7d28bd74d72ae714c2c298646098c6c052fab762aa5b5cdc3","observation_id":"75d412a3-e8e5-42ab-b71b-613390008c31","resolution":{"observed_at":"2026-08-04T10:32:47.992307Z","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":"2026-08-04T10:32:47.996922Z","title":"Signals & systems","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:47.996922Z"},"links":{"citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:db4cf475820c53d824bebb2605e775f8dd02279b321e90338c692dd05b2cf698","observation_id":"4eff4e1a-791f-4463-aecd-ffd0b47072ed","resolution":{"observed_at":"2026-08-04T10:32:47.996922Z","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":"2026-08-04T10:32:48.002185Z","title":"Resurrecting recurrent neural networks for long sequences","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:48.002185Z"},"links":{"citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:6c954721f2641166759798cd8d3ae1cfd0d2a01450f21035210ccbd163be42c4","observation_id":"4df8e25b-4c75-479e-81c4-9891617643be","resolution":{"observed_at":"2026-08-04T10:32:48.002185Z","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":"2026-08-04T10:32:48.008282Z","title":"Resurrecting Recurrent Neural Networks for Long Sequences","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:48.008282Z"},"links":{"citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:184cbc03f3a493237634fedbbd82a454fd379ec560c267f2f5909453feaac927","observation_id":"8c0a26fc-077f-43d7-a6af-5f68b217d058","resolution":{"observed_at":"2026-08-04T10:32:48.008282Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1512.08756","last_updated":"2016-09-20T05:02:22Z","snapshot_observed_at":"2026-08-14T22:16:38.014280Z","submitted_at":"2015-12-29T19:03:43Z","title":"Feed-Forward Networks with Attention Can Solve Some Long-Term Memory Problems","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1512.08756","snapshot_observed_at":"2026-08-04T10:32:48.014055Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:48.014055Z"},"links":{"cited_paper":"/paper/1512.08756","citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:49e85ebf9bdf9f64980174d2e7be6580564df479fbba14821ab4e74417d46a0e","observation_id":"a0d19bd0-f5a1-4ad7-82bc-d94af129466e","resolution":{"observed_at":"2026-08-04T10:32:48.014055Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.14332","last_updated":"2024-08-26T15:01:04Z","snapshot_observed_at":"2026-08-16T13:23:47.304952Z","submitted_at":"2024-08-26T15:01:04Z","title":"One-layer transformers fail to solve the induction heads task","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.14332","snapshot_observed_at":"2026-08-04T10:32:48.018937Z","title":"One-layer transformers fail to solve the induction heads task","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:48.018937Z"},"links":{"cited_paper":"/paper/2408.14332","citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:e0b7e93218e54bba8c8f06842032c6ad48d6e098e3fb27ed4d9b66286f69323c","observation_id":"4647ff50-7a71-4574-9641-bbe341e61d6b","resolution":{"observed_at":"2026-08-04T10:32:48.018937Z","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":"2026-08-04T10:32:48.028207Z","title":"Linear transformers are secretly fast weight programmers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:48.028207Z"},"links":{"citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:8e3fc898f5839bbb4e093a2fbbbdeec66ccb4908dcae0cfac623e10116ce14ae","observation_id":"57b8f759-81e1-4d3e-aa21-be274d9c4d64","resolution":{"observed_at":"2026-08-04T10:32:48.028207Z","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":"2026-08-04T10:32:48.032483Z","title":"Understanding the differences in foundation models: Attention, state space models, and recurrent neural networks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:48.032483Z"},"links":{"citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:74eb0b611dc824d95994cff82bde716434c9ad4989221e5f2426e5e62fe4f4c0","observation_id":"378bb126-f7e8-447c-ab39-b171b5285743","resolution":{"observed_at":"2026-08-04T10:32:48.032483Z","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":"2026-08-04T10:32:48.037953Z","title":"Smith, Andrew Warrington, and Scott Linderman","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:48.037953Z"},"links":{"citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:50c054e87f80c4e6a62afd9fab65b8a2a419fa205ef2b2dcd1eb70c6e3947cd8","observation_id":"d827d9b2-5c6f-4a26-be35-deef67ebcedc","resolution":{"observed_at":"2026-08-04T10:32:48.037953Z","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":"10.1016/j.neucom.2019.04.044","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":null,"venue":"Neurocomputing","work_id":"cb3a45e9-3b39-409c-a942-34fa265a41fa","year":2019},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:48.043534Z"},"links":{"citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:d110b8c04a72f93f6b4f9fc74972c39a49beae7b18bcded21e7efce48cb20f0e","observation_id":"9b937e7e-8338-474f-9dad-8011d9982efb","resolution":{"observed_at":"2026-08-04T10:34:04.422668Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1907.01470","last_updated":"2019-07-02T15:56:20Z","snapshot_observed_at":"2026-08-18T22:25:47.140517Z","submitted_at":"2019-07-02T15:56:20Z","title":"Augmenting Self-attention with Persistent Memory","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.01470","snapshot_observed_at":"2026-08-04T10:32:48.048417Z","title":"Augmenting self-attention with persistent memory, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:48.048417Z"},"links":{"cited_paper":"/paper/1907.01470","citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:fb5553f2e3991281ee01ad1336e6074ea17ffad9502f8c0e38d01ac1ebdea89f","observation_id":"29254109-44fc-481c-8ed1-d112791d795e","resolution":{"observed_at":"2026-08-04T10:32:48.048417Z","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":"2026-08-04T10:32:48.058653Z","title":"Long Range Arena : A Benchmark for Efficient Transformers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:48.058653Z"},"links":{"citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:53ada24a4389e51ecbe90faa9c86cd170f7b38e52d06b430f4bdc7892fe5de3a","observation_id":"1a0a2ee6-4398-415d-8370-a9801f3c7b2c","resolution":{"observed_at":"2026-08-04T10:32:48.058653Z","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":"2026-08-04T10:32:48.067347Z","title":"Attention is All you Need","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:48.067347Z"},"links":{"citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:30292513afe67b108620ba35a171b0d494fa8dd24f4995dd28d4fd3232f14431","observation_id":"bef33b6d-58be-4986-af00-99eddbea50d5","resolution":{"observed_at":"2026-08-04T10:32:48.067347Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.14495","last_updated":"2024-06-05T05:15:16Z","snapshot_observed_at":"2026-08-17T15:42:07.928550Z","submitted_at":"2023-11-24T14:08:31Z","title":"StableSSM: Alleviating the Curse of Memory in State-space Models through Stable Reparameterization","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.14495","snapshot_observed_at":"2026-08-04T10:32:48.073170Z","title":"Stablessm: Alleviating the curse of memory in state-space models through stable reparameterization, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:48.073170Z"},"links":{"cited_paper":"/paper/2311.14495","citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:24938e0d088bfb891aaa8288444005e2f2eb0ec1d297763908d8a9119afe3c8e","observation_id":"39065917-a490-4b10-b97c-2a387590bf30","resolution":{"observed_at":"2026-08-04T10:32:48.073170Z","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":"2026-08-04T10:32:48.081414Z","title":"State-space models with layer-wise nonlinearity are universal approximators with exponential decaying memory","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:48.081414Z"},"links":{"citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:493eee36932f86d32dc2b48487ecff74d2ba596737caa9067f07c9e013b12a24","observation_id":"0e9b8921-3193-4f11-a806-acedf5fb794b","resolution":{"observed_at":"2026-08-04T10:32:48.081414Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.06464","last_updated":"2025-03-06T06:57:34Z","snapshot_observed_at":"2026-08-14T21:08:22.323819Z","submitted_at":"2024-12-09T13:09:04Z","title":"Gated Delta Networks: Improving Mamba2 with Delta Rule","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.06464","snapshot_observed_at":"2026-08-04T10:32:48.089866Z","title":"Gated delta networks: Improving mamba2 with delta rule","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:48.089866Z"},"links":{"cited_paper":"/paper/2412.06464","citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:2cb1ea3123485934c34a5eff0a982b6e31358d36b48585b70cae8e46929628f3","observation_id":"97e96b56-24aa-4ef8-bf7b-0c702238cf3d","resolution":{"observed_at":"2026-08-04T10:32:48.089866Z","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":"2026-08-04T10:32:48.094940Z","title":"@esa (Ref","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:48.094940Z"},"links":{"citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:3d8e478b5d0ea4d49464e28f181a068b88ef068de6dcb97dd2593989e6da40c3","observation_id":"3243d888-5868-420b-89db-4719a3e24c94","resolution":{"observed_at":"2026-08-04T10:32:48.094940Z","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":"2026-08-04T10:32:48.100671Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:48.100671Z"},"links":{"citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:2c9bed8de30375b8c4df0cf723ba2f27eaf347dbb7214008adec17a725417d09","observation_id":"581ba0cf-170f-4f40-aca5-9382ff23df18","resolution":{"observed_at":"2026-08-04T10:32:48.100671Z","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":"2026-08-04T10:32:48.105394Z","title":"ks V s Xi o/ θ e ]` moÁ, \\1= 7vd ; ;7 z6'e ߷DvB |_ E?/ u z + 3R G Y_>2(/ B.6ɶe,Mm `q c? gĊ=t ?mZ ds@K B5޾","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-04T10:32:48.105394Z"},"links":{"citing_paper":"/paper/2510.09379"},"observation_digest":"sha256:bed7d9fbe167380c0fa489dd240106561e0dc08f1a628b583ca476cf6d647bd6","observation_id":"a6ce35a6-9f83-469a-b6cc-b5e1e70faa5f","resolution":{"observed_at":"2026-08-04T10:32:48.105394Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2510.09379","last_updated":"2026-08-01T07:50:34Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T15:22:45.434514Z","submitted_at":"2025-10-10T13:35:21Z","title":"Eigenvalues as a Metric for Memory Dynamics in Sequence Models"},"reference_resolution":{"displayed":38,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":36,"verified_exact":2,"verified_fuzzy":0},"total_outbound_references":38},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2510.09379."}