{"as_of":"2026-08-17T00:24:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3952fb228e3f6a1edd11d718bd0b7c2af32f11a6018fd057f9cd7f810ed23b54","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":32,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":32,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":32,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":32,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T11:17:29.421987Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-03T17:28:44.977281Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":"2404.07904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-07-03T17:28:44.977281Z","title":"Hgrn2: Gated linear rnns with state expansion.ArXiv preprint, abs/2404.07904","venue":null,"work_id":"62f21939-fe4f-4159-bb1e-6a303fdc7b42","year":2024},"citing_paper":{"arxiv_id":"2312.06635","last_updated":"2024-08-27T01:27:29Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-11T18:51:59Z","title":"Gated Linear Attention Transformers with Hardware-Efficient Training","version":6},"reference_index":75,"source":"arxiv_source","source_observed_at":"2026-05-15T01:15:13.991219Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2312.06635"},"observation_digest":"sha256:efa6040e2e4ca78d5530e7c187687c8972e14b4c6c46ed8cc94f5692e3bfce5f","observation_id":"028141c2-506e-482e-9706-b95408296bc9","resolution":{"observed_at":"2026-05-15T01:15:14.178481Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":"2404.07904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-07-03T17:28:44.977281Z","title":"Hgrn2: Gated linear rnns with state expansion.ArXiv preprint, abs/2404.07904","venue":null,"work_id":"62f21939-fe4f-4159-bb1e-6a303fdc7b42","year":2024},"citing_paper":{"arxiv_id":"2405.21060","last_updated":"2024-05-31T17:50:01Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-05-31T17:50:01Z","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-05-11T12:16:25.390683Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2405.21060"},"observation_digest":"sha256:38353473dd40824a8fc4ba0f13e11f967d7b586a8626516c0a21ccd2f96aa32b","observation_id":"3180dd9b-e417-4b83-bb09-9c7aee3395a6","resolution":{"observed_at":"2026-05-11T12:16:25.924691Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-08-11T12:22:28.467675Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.14354","last_updated":"2025-04-22T17:44:39Z","snapshot_observed_at":"2026-08-15T22:46:43.733732Z","submitted_at":"2024-12-18T21:42:15Z","title":"State Space Models are Strong Text Rerankers","version":3},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-11T12:22:28.467675Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2412.14354"},"observation_digest":"sha256:a868c9c68ea6a34f12eb69cb95b9754b3e11008964af68729c78ad4e492eb240","observation_id":"cdfc1606-882b-4c46-9e3a-584d247c356c","resolution":{"observed_at":"2026-08-11T12:22:28.467675Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-08-10T22:52:33.568763Z","title":"Hgrn2: Gated linear rnns with state expansion","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.00658","last_updated":"2025-03-11T03:58:57Z","snapshot_observed_at":"2026-08-15T08:43:53.128548Z","submitted_at":"2024-12-31T22:06:39Z","title":"Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-10T22:52:33.568763Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2501.00658"},"observation_digest":"sha256:1d6f71d0987c4a3f00ce949dfe8bccd3e2cec544317861b7bee1d97a93de320f","observation_id":"bb9dc605-5b32-4362-95c2-dfc742b0af19","resolution":{"observed_at":"2026-08-10T22:52:33.568763Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-08-07T22:10:15.909661Z","title":"HGRN2: Gated linear RNNs with state expansion","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.09287","last_updated":"2025-02-13T13:01:46Z","snapshot_observed_at":"2026-08-15T05:31:38.119115Z","submitted_at":"2025-02-13T13:01:46Z","title":"An Uncertainty Principle for Linear Recurrent Neural Networks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T22:10:15.909661Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2502.09287"},"observation_digest":"sha256:6f44aba4c35d695382a479031314e358ea47d872c36328df7e6664990a477888","observation_id":"1bd148f1-0b79-4d3e-b370-2b16168f3bca","resolution":{"observed_at":"2026-08-07T22:10:15.909661Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-08-08T10:59:50.623523Z","title":"HGRN2 : Gated Linear RNNs with State Expansion , April 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2503.18002","last_updated":"2025-03-25T12:05:26Z","snapshot_observed_at":"2026-08-09T03:28:52.903250Z","submitted_at":"2025-02-12T02:40:44Z","title":"Neuromorphic Principles for Efficient Large Language Models on Intel Loihi 2","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-08T10:59:50.623523Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2503.18002"},"observation_digest":"sha256:5f9fb297963277dec0bbcd3499b552b32a5b24f65bc5337001ebcb438ad868dc","observation_id":"53e3cf3f-bd85-4455-9a3e-65a41694f548","resolution":{"observed_at":"2026-08-08T10:59:50.623523Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-08-16T11:17:29.421987Z","title":"Hgrn2: Gated linear rnns with state expansion, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.18574","last_updated":"2025-06-11T11:06:08Z","snapshot_observed_at":"2026-08-16T13:43:24.279224Z","submitted_at":"2025-04-22T16:15:19Z","title":"Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-16T11:17:29.421987Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2504.18574"},"observation_digest":"sha256:a1ff04c05fb517caab79d30b234bf721d673bf631a29b3d051e5cfce4dd1bdb6","observation_id":"4d21a790-bd48-41cf-b027-ef278a9b576c","resolution":{"observed_at":"2026-08-16T11:17:29.421987Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-08-15T22:12:58.798549Z","title":"Hgrn2: Gated linear rnns with state expansion, 2024 b","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07793","last_updated":"2025-09-08T20:57:22Z","snapshot_observed_at":"2026-08-15T22:05:45.876584Z","submitted_at":"2025-05-12T17:45:05Z","title":"Overflow Prevention Enhances Long-Context Recurrent LLMs","version":2},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-15T22:12:58.798549Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2505.07793"},"observation_digest":"sha256:e0213e13d489af50337cf49611edc585a9a436eb80f0390223c95217e425ee9e","observation_id":"7842a8f4-3636-4956-99e9-e157b6e0d9e1","resolution":{"observed_at":"2026-08-15T22:12:58.798549Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-08-06T20:53:49.949048Z","title":"Hgrn2: Gated linear rnns with state expansion.arXiv preprint arXiv:2404.07904,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.01652","last_updated":"2025-07-02T12:27:06Z","snapshot_observed_at":"2026-08-14T15:07:04.185058Z","submitted_at":"2025-07-02T12:27:06Z","title":"Autoregressive Image Generation with Linear Complexity: A Spatial-Aware Decay Perspective","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T20:53:49.949048Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2507.01652"},"observation_digest":"sha256:5f9546ac4da3e17a4f455798f75e74e0f28604b371230f4a1166a1f78ef73a16","observation_id":"573992a7-f2eb-43aa-b04e-c85c2dff66dd","resolution":{"observed_at":"2026-08-06T20:53:49.949048Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-08-06T19:14:29.778788Z","title":"Hgrn2: Gated linear rnns with state expansion","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.06203","last_updated":"2025-07-10T16:43:36Z","snapshot_observed_at":"2026-08-07T04:57:37.201438Z","submitted_at":"2025-07-08T17:29:07Z","title":"A Survey on Latent Reasoning","version":2},"reference_index":80,"source":"arxiv_source","source_observed_at":"2026-08-06T19:14:29.778788Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2507.06203"},"observation_digest":"sha256:f411edbc874d9fe638a5680cc90121fb0da1477eac7908dd548fa29c45f1e976","observation_id":"cd664a8c-0092-49a1-b441-3ec3454ef6ee","resolution":{"observed_at":"2026-08-06T19:14:29.778788Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-08-05T05:29:21.596988Z","title":"Hgrn2: Gated linear rnns with state expansion","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.05282","last_updated":"2025-09-05T17:48:26Z","snapshot_observed_at":"2026-08-14T20:35:20.665795Z","submitted_at":"2025-09-05T17:48:26Z","title":"Elucidating the Design Space of Decay in Linear Attention","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-05T05:29:21.596988Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2509.05282"},"observation_digest":"sha256:de5ea8c8f04285b41531aae3d725e63eddbaa1f000da72f5fde28c1d952c2ffd","observation_id":"6f9b6f7c-42b2-4d19-9f4f-fb6d6cc589ad","resolution":{"observed_at":"2026-08-05T05:29:21.596988Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":"2404.07904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-07-03T17:28:44.977281Z","title":"Hgrn2: Gated linear rnns with state expansion.ArXiv preprint, abs/2404.07904","venue":null,"work_id":"62f21939-fe4f-4159-bb1e-6a303fdc7b42","year":2024},"citing_paper":{"arxiv_id":"2510.26083","last_updated":"2026-04-08T13:55:00Z","snapshot_observed_at":"2026-08-16T04:39:06.555557Z","submitted_at":"2025-10-30T02:41:54Z","title":"Nirvana: A Specialized Generalist Model With Task-Aware Memory Mechanism","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-18T03:05:06.069642Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2510.26083"},"observation_digest":"sha256:c8b4ba3e0c6ddfa5c97a8ecd7478b6bb08c6519f84939aef99f3d8dcc6ba1ec0","observation_id":"4b894af1-4bf3-4a35-8a49-af66b2722404","resolution":{"observed_at":"2026-05-18T03:05:48.046309Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":"2404.07904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-07-03T17:28:44.977281Z","title":"Hgrn2: Gated linear rnns with state expansion.ArXiv preprint, abs/2404.07904","venue":null,"work_id":"62f21939-fe4f-4159-bb1e-6a303fdc7b42","year":2024},"citing_paper":{"arxiv_id":"2510.26692","last_updated":"2025-11-01T12:05:18Z","snapshot_observed_at":"2026-08-07T19:30:34.681869Z","submitted_at":"2025-10-30T16:59:43Z","title":"Kimi Linear: An Expressive, Efficient Attention Architecture","version":2},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-05-13T23:49:10.555255Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2510.26692"},"observation_digest":"sha256:2e6766d631d14abec5415a49d5a1448a96efb2601644228931edbb495ec549c7","observation_id":"2fc4299c-e2db-4779-aba3-9f49db45f35f","resolution":{"observed_at":"2026-05-13T23:49:10.756376Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":"2404.07904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-07-03T17:28:44.977281Z","title":"Hgrn2: Gated linear rnns with state expansion.ArXiv preprint, abs/2404.07904","venue":null,"work_id":"62f21939-fe4f-4159-bb1e-6a303fdc7b42","year":2024},"citing_paper":{"arxiv_id":"2511.17388","last_updated":"2026-06-23T17:12:17Z","snapshot_observed_at":"2026-08-15T03:11:50.414827Z","submitted_at":"2025-11-21T16:50:00Z","title":"Selective Rotary Position Embedding","version":2},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-05-17T20:36:49.650895Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2511.17388"},"observation_digest":"sha256:000642e9d8b81a304c4580b4a54bb06700ac68fef812b675095a9b04907869ae","observation_id":"4fbf30cf-0485-4cbc-ab7b-b2ff3e879222","resolution":{"observed_at":"2026-05-17T20:40:14.876027Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-08-03T21:03:22.534290Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2511.17388","last_updated":"2026-06-23T17:12:17Z","snapshot_observed_at":"2026-08-15T03:11:50.414827Z","submitted_at":"2025-11-21T16:50:00Z","title":"Selective Rotary Position Embedding","version":3},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-03T21:03:22.534290Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2511.17388"},"observation_digest":"sha256:d62f6a3bc2e480b51cffe9d9e968338befb953fa71dbb88102bf908bcbd251dd","observation_id":"57230f3d-9378-40cb-8c2f-cebced81accd","resolution":{"observed_at":"2026-08-03T21:03:22.534290Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":"2404.07904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-07-03T17:28:44.977281Z","title":"Hgrn2: Gated linear rnns with state expansion.ArXiv preprint, abs/2404.07904","venue":null,"work_id":"62f21939-fe4f-4159-bb1e-6a303fdc7b42","year":2024},"citing_paper":{"arxiv_id":"2602.21204","last_updated":"2026-05-12T22:37:21Z","snapshot_observed_at":"2026-08-11T13:53:26.662684Z","submitted_at":"2026-02-24T18:59:30Z","title":"Test-Time Training with KV Binding Is Secretly Linear Attention","version":4},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-15T19:40:35.854519Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2602.21204"},"observation_digest":"sha256:9197a3d18876fa1de06f20b64c83ff6b294a85fc235606db03c744c2c05c5a2a","observation_id":"2462ea1a-cdd9-4d42-aa05-ab26cce44ba9","resolution":{"observed_at":"2026-05-15T19:41:32.655604Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":"2404.07904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-07-03T17:28:44.977281Z","title":"Hgrn2: Gated linear rnns with state expansion.ArXiv preprint, abs/2404.07904","venue":null,"work_id":"62f21939-fe4f-4159-bb1e-6a303fdc7b42","year":2024},"citing_paper":{"arxiv_id":"2603.15031","last_updated":"2026-03-16T09:32:21Z","snapshot_observed_at":"2026-08-16T13:30:40.009888Z","submitted_at":"2026-03-16T09:32:21Z","title":"Attention Residuals","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-21T06:39:04.312270Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2603.15031"},"observation_digest":"sha256:987f4aeeed6c386e3090371ef3d274b802b1a3449e83cb4ac256fbb3a391395a","observation_id":"256821c7-39ac-4d26-bc67-d7e1a707ad25","resolution":{"observed_at":"2026-05-21T06:39:04.421192Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":"2404.07904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-07-03T17:28:44.977281Z","title":"Hgrn2: Gated linear rnns with state expansion.ArXiv preprint, abs/2404.07904","venue":null,"work_id":"62f21939-fe4f-4159-bb1e-6a303fdc7b42","year":2024},"citing_paper":{"arxiv_id":"2604.19021","last_updated":"2026-05-03T07:41:57Z","snapshot_observed_at":"2026-08-15T02:31:57.597372Z","submitted_at":"2026-04-21T03:15:28Z","title":"FG$^2$-GDN: Enhancing Long-Context Gated Delta Networks with Doubly Fine-Grained Control","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-10T02:27:18.261984Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2604.19021"},"observation_digest":"sha256:c99bd3a6b0bc87a4bd0c478eff0f5955399716c4c93c321051d6455dceba951f","observation_id":"f09d6923-58ed-4883-a640-16d130ffb17e","resolution":{"observed_at":"2026-05-11T13:01:23.745730Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":"2404.07904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-07-03T17:28:44.977281Z","title":"Hgrn2: Gated linear rnns with state expansion.ArXiv preprint, abs/2404.07904","venue":null,"work_id":"62f21939-fe4f-4159-bb1e-6a303fdc7b42","year":2024},"citing_paper":{"arxiv_id":"2605.05066","last_updated":"2026-08-06T14:35:06Z","snapshot_observed_at":"2026-08-14T15:21:39.185474Z","submitted_at":"2026-05-06T16:01:43Z","title":"The Impossibility Triangle of Long-Context Modeling","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-08T17:17:44.033300Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2605.05066"},"observation_digest":"sha256:f8a95bd285abecef7942509ad3297775f897fde7e5c5cad65326d44d649e9ed5","observation_id":"09aa5059-09a1-4359-aefd-d3ac460fc2ea","resolution":{"observed_at":"2026-05-11T17:41:08.965747Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":"2404.07904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-07-03T17:28:44.977281Z","title":"Hgrn2: Gated linear rnns with state expansion.ArXiv preprint, abs/2404.07904","venue":null,"work_id":"62f21939-fe4f-4159-bb1e-6a303fdc7b42","year":2024},"citing_paper":{"arxiv_id":"2605.06501","last_updated":"2026-05-19T06:54:59Z","snapshot_observed_at":"2026-08-02T05:36:24.593005Z","submitted_at":"2026-05-07T16:18:55Z","title":"Cubit: Token Mixer with Kernel Ridge Regression","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-05-08T12:38:19.925573Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2605.06501"},"observation_digest":"sha256:d11e8996c103c3b70c884381a4351e641b5b94b6b6ddd20c87c3e6147196864a","observation_id":"3d723a27-c177-4a9d-bf34-390fced108ca","resolution":{"observed_at":"2026-05-11T19:06:10.811375Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":"2404.07904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-07-03T17:28:44.977281Z","title":"Hgrn2: Gated linear rnns with state expansion.ArXiv preprint, abs/2404.07904","venue":null,"work_id":"62f21939-fe4f-4159-bb1e-6a303fdc7b42","year":2024},"citing_paper":{"arxiv_id":"2605.06501","last_updated":"2026-05-19T06:54:59Z","snapshot_observed_at":"2026-08-02T05:36:24.593005Z","submitted_at":"2026-05-07T16:18:55Z","title":"Cubit: Token Mixer with Kernel Ridge Regression","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-05-20T22:34:36.108826Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2605.06501"},"observation_digest":"sha256:23f517e8336fd8616e10191a09e3dc3cdf7c7806138821255080760c446398b5","observation_id":"c8242dce-7d6d-41ea-ac26-ad571e9917a8","resolution":{"observed_at":"2026-05-20T22:39:11.022749Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":"2404.07904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-07-03T17:28:44.977281Z","title":"Hgrn2: Gated linear rnns with state expansion.ArXiv preprint, abs/2404.07904","venue":null,"work_id":"62f21939-fe4f-4159-bb1e-6a303fdc7b42","year":2024},"citing_paper":{"arxiv_id":"2605.12491","last_updated":"2026-05-12T17:59:26Z","snapshot_observed_at":"2026-08-11T07:31:36.341334Z","submitted_at":"2026-05-12T17:59:26Z","title":"Elastic Attention Cores for Scalable Vision Transformers","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-05-13T06:02:40.158866Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2605.12491"},"observation_digest":"sha256:6e7c7dd9fe50e99c5f0238d8db491fee968146dba7a96f1f5b6c78cc28f15c29","observation_id":"286fdac0-1d10-48d5-83b3-abbc37c78f17","resolution":{"observed_at":"2026-05-13T06:07:22.515060Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":"2404.07904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-07-03T17:28:44.977281Z","title":"Hgrn2: Gated linear rnns with state expansion.ArXiv preprint, abs/2404.07904","venue":null,"work_id":"62f21939-fe4f-4159-bb1e-6a303fdc7b42","year":2024},"citing_paper":{"arxiv_id":"2605.12992","last_updated":"2026-05-13T04:45:35Z","snapshot_observed_at":"2026-08-14T01:07:03.852554Z","submitted_at":"2026-05-13T04:45:35Z","title":"SpikeProphecy: A Large-Scale Benchmark for Autoregressive Neural Population Forecasting","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-05-14T02:17:34.631149Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2605.12992"},"observation_digest":"sha256:a0c937d92ae34856fefca061f69cac4bc4bd0bc2138f7291faf7fdf21bffa4ae","observation_id":"11cc2d6a-49c9-4f2f-95bf-a83671a01053","resolution":{"observed_at":"2026-05-14T02:18:37.510692Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":"2404.07904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-07-03T17:28:44.977281Z","title":"Hgrn2: Gated linear rnns with state expansion.ArXiv preprint, abs/2404.07904","venue":null,"work_id":"62f21939-fe4f-4159-bb1e-6a303fdc7b42","year":2024},"citing_paper":{"arxiv_id":"2605.20670","last_updated":"2026-05-22T21:41:56Z","snapshot_observed_at":"2026-08-13T10:55:41.115489Z","submitted_at":"2026-05-20T03:36:44Z","title":"LT2: Linear-Time Looped Transformers","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-05-21T06:11:19.104464Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2605.20670"},"observation_digest":"sha256:2653b1ad39aa41890bdd5a37f448cec14613f1b0a51d6ae7b8479f177339b609","observation_id":"2a073cd0-b19c-4d8e-9003-5973ba72f6e0","resolution":{"observed_at":"2026-05-21T06:13:59.615527Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":"2404.07904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-07-03T17:28:44.977281Z","title":"Hgrn2: Gated linear rnns with state expansion.ArXiv preprint, abs/2404.07904","venue":null,"work_id":"62f21939-fe4f-4159-bb1e-6a303fdc7b42","year":2024},"citing_paper":{"arxiv_id":"2605.20670","last_updated":"2026-05-22T21:41:56Z","snapshot_observed_at":"2026-08-13T10:55:41.115489Z","submitted_at":"2026-05-20T03:36:44Z","title":"LT2: Linear-Time Looped Transformers","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-06-30T17:52:25.401671Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2605.20670"},"observation_digest":"sha256:a0d6c2cba84c23ea83a19c16ace621d00ccae6abd91ed1cace7839f1d3e5a571","observation_id":"7fada328-71dc-4991-8818-72c4914f5af7","resolution":{"observed_at":"2026-06-30T17:54:57.816696Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":"2404.07904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-07-03T17:28:44.977281Z","title":"Hgrn2: Gated linear rnns with state expansion.ArXiv preprint, abs/2404.07904","venue":null,"work_id":"62f21939-fe4f-4159-bb1e-6a303fdc7b42","year":2024},"citing_paper":{"arxiv_id":"2605.22791","last_updated":"2026-05-21T17:44:57Z","snapshot_observed_at":"2026-08-14T13:35:02.404505Z","submitted_at":"2026-05-21T17:44:57Z","title":"Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-22T04:53:24.400091Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2605.22791"},"observation_digest":"sha256:9b2babb0eeb08505bf3b5a48240709a73869a78e1f747de79b4b51d02f33be5c","observation_id":"2af5326e-6c1c-4c7a-8052-81474fca269d","resolution":{"observed_at":"2026-05-22T04:54:36.620527Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":"2404.07904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-07-03T17:28:44.977281Z","title":"Hgrn2: Gated linear rnns with state expansion.ArXiv preprint, abs/2404.07904","venue":null,"work_id":"62f21939-fe4f-4159-bb1e-6a303fdc7b42","year":2024},"citing_paper":{"arxiv_id":"2605.28507","last_updated":"2026-06-11T11:39:46Z","snapshot_observed_at":"2026-07-06T23:38:04.621658Z","submitted_at":"2026-05-27T14:10:41Z","title":"Universal Time Series Generation with Neural Controlled Differential Equations","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-06-29T14:10:38.078991Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2605.28507"},"observation_digest":"sha256:a34f00c9b69169962af18b5e1db0a7d4d8df1ad93e3d725cd9eff658af377aed","observation_id":"7bf3a3f5-a8fe-4aaa-8b4e-07f072b5ffef","resolution":{"observed_at":"2026-06-29T14:13:30.017761Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":"2404.07904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-07-03T17:28:44.977281Z","title":"Hgrn2: Gated linear rnns with state expansion.ArXiv preprint, abs/2404.07904","venue":null,"work_id":"62f21939-fe4f-4159-bb1e-6a303fdc7b42","year":2024},"citing_paper":{"arxiv_id":"2605.31163","last_updated":"2026-08-09T14:33:02Z","snapshot_observed_at":"2026-08-13T23:28:18.289669Z","submitted_at":"2026-05-29T11:13:00Z","title":"Memory by Design: Probabilistic Sequence Layers","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-06-28T21:07:31.407554Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2605.31163"},"observation_digest":"sha256:b4bb58468b43e68f870bbcad963ad2340d29868e0fd030c68ceed424fdbbe656","observation_id":"06e63161-e187-4f3d-b004-5d4da99d1b39","resolution":{"observed_at":"2026-07-01T20:26:12.859084Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":"2404.07904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-07-03T17:28:44.977281Z","title":"Hgrn2: Gated linear rnns with state expansion.ArXiv preprint, abs/2404.07904","venue":null,"work_id":"62f21939-fe4f-4159-bb1e-6a303fdc7b42","year":2024},"citing_paper":{"arxiv_id":"2606.03825","last_updated":"2026-06-02T16:07:55Z","snapshot_observed_at":"2026-08-15T00:44:29.353819Z","submitted_at":"2026-06-02T16:07:55Z","title":"Dynamic Short Convolutions Improve Transformers","version":1},"reference_index":174,"source":"arxiv_source","source_observed_at":"2026-06-28T10:48:50.103004Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2606.03825"},"observation_digest":"sha256:7cc9a0ea11c98b04c034e720da1c82579c43fe4339b490849520533f6130771f","observation_id":"c413e580-7b36-4bea-888e-fe0e4cf2d629","resolution":{"observed_at":"2026-07-02T02:36:27.001391Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":"2404.07904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-07-03T17:28:44.977281Z","title":"Hgrn2: Gated linear rnns with state expansion.ArXiv preprint, abs/2404.07904","venue":null,"work_id":"62f21939-fe4f-4159-bb1e-6a303fdc7b42","year":2024},"citing_paper":{"arxiv_id":"2606.11634","last_updated":"2026-06-10T03:56:03Z","snapshot_observed_at":"2026-08-12T13:36:16.324487Z","submitted_at":"2026-06-10T03:56:03Z","title":"Architecture-Aware Reinforcement Learning Makes Sliding-Window Attention Competitive in Math Reasoning","version":1},"reference_index":76,"source":"arxiv_source","source_observed_at":"2026-06-27T10:18:54.163862Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2606.11634"},"observation_digest":"sha256:6c0d4c55e6c6674ca8950b10a4dd865f84de701fd3528951687a29dd5e9c2897","observation_id":"a1d64929-c85f-4d00-a050-bcb460179fa0","resolution":{"observed_at":"2026-07-03T09:47:59.839072Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":"2404.07904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-07-03T17:28:44.977281Z","title":"Hgrn2: Gated linear rnns with state expansion.ArXiv preprint, abs/2404.07904","venue":null,"work_id":"62f21939-fe4f-4159-bb1e-6a303fdc7b42","year":2024},"citing_paper":{"arxiv_id":"2606.16533","last_updated":"2026-07-03T04:30:36Z","snapshot_observed_at":"2026-07-12T13:47:19.539499Z","submitted_at":"2026-06-15T10:37:42Z","title":"Kairos: A Regret-Aware Native World-Action Model Stack for Physical AI","version":2},"reference_index":185,"source":"pdf_text","source_observed_at":"2026-06-27T04:02:53.110012Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2606.16533"},"observation_digest":"sha256:86f1528526b08f2a94817c7d75c4e3ecb843aa859326a13e820b791606c33754","observation_id":"4f22a659-6728-4a2c-a2ea-e049194f67f6","resolution":{"observed_at":"2026-07-03T17:28:44.978700Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion","version":2},"cited_work":{"arxiv_id":"2404.07904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.07904","snapshot_observed_at":"2026-07-03T17:28:44.977281Z","title":"Hgrn2: Gated linear rnns with state expansion.ArXiv preprint, abs/2404.07904","venue":null,"work_id":"62f21939-fe4f-4159-bb1e-6a303fdc7b42","year":2024},"citing_paper":{"arxiv_id":"2606.30562","last_updated":"2026-06-29T17:02:34Z","snapshot_observed_at":"2026-08-14T09:50:47.227901Z","submitted_at":"2026-06-29T17:02:34Z","title":"Morphing into Hybrid Attention Models","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-06-30T05:56:51.447893Z"},"links":{"cited_paper":"/paper/2404.07904","citing_paper":"/paper/2606.30562"},"observation_digest":"sha256:0b8e518c3486ab084b49d643bf570377411f52f0f599b91769118cfe992c32f3","observation_id":"7d24fd88-1556-4edf-a88b-f2fd67fe5c67","resolution":{"observed_at":"2026-06-30T08:44:28.077887Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2404.07904/citation-record","integrity":"/paper/2404.07904/integrity","json":"/paper/2404.07904/citation-record.json","paper":"/paper/2404.07904"},"outbound":[],"paper":{"arxiv_id":"2404.07904","last_updated":"2024-08-19T17:16:55Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T14:01:40.481918Z","submitted_at":"2024-04-11T16:43:03Z","title":"HGRN2: Gated Linear RNNs with State Expansion"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 32 inbound Pith citation observations for arXiv:2404.07904."}