{"as_of":"2026-08-08T17:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:17b75f270ba37723fbdfc4b570c4cf970140216db87c9e60a5785a3cd6610b6b","coverage":[{"denominator":67,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":67,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T18:06:56.342744Z","state":"measured"},{"denominator":67,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":67,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2607.17419/citation-record","integrity":"/paper/2607.17419/integrity","json":"/paper/2607.17419/citation-record.json","paper":"/paper/2607.17419"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T18:06:48.618561Z","title":"Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) , pages =","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:48.618561Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:745aa1d2afed3d41fe61b68ebf12a81a5b4afc3cb79fabeaf5e6524120d1b055","observation_id":"1f243787-640d-4949-b53d-bbe6544ae9f7","resolution":{"observed_at":"2026-08-01T18:06:48.618561Z","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":"2026-08-01T18:06:48.683349Z","title":"Transformers are RNNs: fast autoregressive transformers with linear attention , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:48.683349Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:bfb33b12969e98e5fcb769239f980e680b8b0dae4d656d71615282b28f6de405","observation_id":"8561567c-1148-4b58-8b74-7905142eab7b","resolution":{"observed_at":"2026-08-01T18:06:48.683349Z","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":"2026-08-01T18:06:48.778220Z","title":"Advances in neural information processing systems , volume=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:48.778220Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:b60b3d6338bcdae4ea021414c855ac869ac687c3fe14ec566da10869fdb5296f","observation_id":"3bf73d91-3635-400a-acfe-bd3472daf7de","resolution":{"observed_at":"2026-08-01T18:06:48.778220Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.01032","last_updated":"2024-06-03T22:22:15Z","snapshot_observed_at":"2026-08-05T02:24:20.613110Z","submitted_at":"2024-02-01T21:44:11Z","title":"Repeat After Me: Transformers are Better than State Space Models at Copying","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.01032","snapshot_observed_at":"2026-08-01T18:06:48.827702Z","title":"arXiv preprint arXiv:2402.01032 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:48.827702Z"},"links":{"cited_paper":"/paper/2402.01032","citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:d1b9626eb3d1f0db3ca0d5117aaa81d725e54f66fe91ffab8d813fda0b2ba65a","observation_id":"86d98c18-52eb-4932-92da-eaadab7a7c71","resolution":{"observed_at":"2026-08-01T18:06:48.827702Z","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":"2026-08-01T18:06:48.911567Z","title":"arXiv preprint arXiv:2502.13685 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:48.911567Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:39f9b046c0abb8ba6ae0175d3534fe5aee52661b69ba9092133260b1846d83fa","observation_id":"df674fbe-a514-4f02-98a8-2e2d0c8aaf60","resolution":{"observed_at":"2026-08-01T18:06:48.911567Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.08621","last_updated":"2023-08-09T08:53:08Z","snapshot_observed_at":"2026-08-02T13:21:32.251959Z","submitted_at":"2023-07-17T16:40:01Z","title":"Retentive Network: A Successor to Transformer for Large Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.08621","snapshot_observed_at":"2026-08-01T18:06:49.038541Z","title":"arXiv preprint arXiv:2307.08621 , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:49.038541Z"},"links":{"cited_paper":"/paper/2307.08621","citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:6f670493e08cb33b49c79c0f20be0d9782253a46308d4f8d2fc682b71e789cff","observation_id":"a105e73d-5409-48ef-93d3-0e172810b052","resolution":{"observed_at":"2026-08-01T18:06:49.038541Z","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":"2026-08-01T18:06:49.151447Z","title":"International Conference on Learning Representations , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:49.151447Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:039779f6a8303881129db58257d9ba1551abebc30734833f2d8acb37219fa679","observation_id":"0d7376ba-0539-4024-aafb-acac5f8f53a9","resolution":{"observed_at":"2026-08-01T18:06:49.151447Z","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":"2026-08-01T18:06:49.273536Z","title":"Linear Transformers Are Secretly Fast Weight Programmers , booktitle =","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:49.273536Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:9668892716576c838435d61075632e07438c760ecb41ca3bce6cc77d82dfb902","observation_id":"5683e727-bf51-4783-9163-e745329bb6e0","resolution":{"observed_at":"2026-08-01T18:06:49.273536Z","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":"2026-08-01T18:06:49.423757Z","title":"International Conference on Learning Representations , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:49.423757Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:dce753e1e89d850b3f79dd8aace8136e3df75861bbecd3e05fead98cda17e508","observation_id":"22e4d873-59a4-4713-bf8c-0c708b73d4d1","resolution":{"observed_at":"2026-08-01T18:06:49.423757Z","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":"2026-08-01T18:06:49.592063Z","title":"Proceedings of the 41st International Conference on Machine Learning , articleno =","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:49.592063Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:b74fc5b5a15ec76ec35a189803948adca496655532911ae66105a0b516eda67f","observation_id":"1d819147-8faf-4ead-a132-95fcee381911","resolution":{"observed_at":"2026-08-01T18:06:49.592063Z","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":"2026-08-01T18:06:49.749443Z","title":"Proceedings of the 41st International Conference on Machine Learning , articleno =","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:49.749443Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:475b0c67efc031d93ae84c2b83c7e42f16e3c83308bb77f8c8dc979b840e10f6","observation_id":"99656b9e-84f9-414c-9f7c-39a503c42eea","resolution":{"observed_at":"2026-08-01T18:06:49.749443Z","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":"2026-08-01T18:06:49.929389Z","title":"Parallelizing Linear Transformers with the Delta Rule over Sequence Length , url =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:49.929389Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:e1429da9a38471d5efb076437cba9d11ea4036b219fc411f2ea7b4d4698bee74","observation_id":"93df1d03-2f50-4297-9a87-224210c23e8e","resolution":{"observed_at":"2026-08-01T18:06:49.929389Z","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":"2026-08-01T18:06:50.105547Z","title":"The Thirteenth International Conference on Learning Representations , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:50.105547Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:e0af84fa6f7d78e34dbcb41a56cdc6427d018942a0fb5d9201cd384315109a9d","observation_id":"7afa7047-622a-4878-a55c-03fc4dc33eef","resolution":{"observed_at":"2026-08-01T18:06:50.105547Z","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":"2026-08-01T18:06:50.343651Z","title":"SIAM Journal on Scientific and Statistical Computing , volume =","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:50.343651Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:96ad666183cb7136efc621b8dc4114ef4c98a03bda26e9ce883e51bbb95a811b","observation_id":"90fd81d2-a94f-4806-9a67-b59af8170f79","resolution":{"observed_at":"2026-08-01T18:06:50.343651Z","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":"2026-08-01T18:06:50.535931Z","title":"American Journal of Mathematics , volume =","venue":null,"work_id":null,"year":1957},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:50.535931Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:8fab913bbae3ecd1ba0ded9058c017b8df3a989515a840ea524285959fd48c8a","observation_id":"d2bea531-8d76-4a98-ae55-5a9ec3acb5f6","resolution":{"observed_at":"2026-08-01T18:06:50.535931Z","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":"2026-08-01T18:06:50.764388Z","title":null,"venue":null,"work_id":null,"year":1963},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:50.764388Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:9d9a017c2331187392d894577ae737645a22161a59db0088008e70866485e79a","observation_id":"a2f044aa-57d8-4571-b729-bed956f45b6f","resolution":{"observed_at":"2026-08-01T18:06:50.764388Z","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":"2026-08-01T18:06:50.925439Z","title":"Analysis on Symmetric Cones , series =","venue":null,"work_id":null,"year":1994},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:50.925439Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:401eb1373180461d5c3eaca0eeabbd0922931d0faafc1683a01046879ec50931","observation_id":"f3bb7302-eb9c-45fe-87d7-2970b825c95f","resolution":{"observed_at":"2026-08-01T18:06:50.925439Z","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":"2026-08-01T18:06:51.125014Z","title":"and Majumdar, Satya N","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:51.125014Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:9f1b04c27be5dce14a6a5239a6a75eb703b6d31e92d507f1630c2505f680559d","observation_id":"efdc987c-f1ce-4742-a6bf-f0a7bc158e3c","resolution":{"observed_at":"2026-08-01T18:06:51.125014Z","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":"2026-08-01T18:06:51.285276Z","title":"Israel Journal of Mathematics , volume =","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:51.285276Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:d7195475f3100644d675f56d18aef00700cd372fdfaa3f9b9026dd9ba8e10fed","observation_id":"5b014494-c39b-4291-8b39-aa4126742201","resolution":{"observed_at":"2026-08-01T18:06:51.285276Z","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":"2026-08-01T18:06:51.389288Z","title":"Hopfield Networks Is All You Need , booktitle =","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:51.389288Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:9d8b8496a8a5d9516c42799a2ee3aeacd339e588382cb8862eae1efd7f31f520","observation_id":"993372cf-07e4-4088-86b5-d31b9b73ed02","resolution":{"observed_at":"2026-08-01T18:06:51.389288Z","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":"2026-08-01T18:06:51.527129Z","title":", title =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:51.527129Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:a38ef44fa9cdceff8b76b7c216c062375e024ce4b437dfe2852b0f933abfe318","observation_id":"839db26a-4311-4cdc-92ca-ca2501ed38bb","resolution":{"observed_at":"2026-08-01T18:06:51.527129Z","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":"2026-08-01T18:06:51.641135Z","title":"On a Model of Associative Memory with Huge Storage Capacity , journal =","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:51.641135Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:78782b208a8268ac49eb9c63419591a929d8be587ba88d4cc8d94b6d8bb74705","observation_id":"7cae7320-66c8-46f0-95da-fd8b646a451a","resolution":{"observed_at":"2026-08-01T18:06:51.641135Z","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":"2026-08-01T18:06:51.738201Z","title":"First Conference on Language Modeling (","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:51.738201Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:e106905b451ece05ea44884ead4fa1576fe8dceb16128100bc627fec43183ef1","observation_id":"f54ea753-a79b-4721-90c9-ab9c0e0a2d88","resolution":{"observed_at":"2026-08-01T18:06:51.738201Z","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":"2026-08-01T18:06:51.818884Z","title":"Findings of the Association for Computational Linguistics:","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:51.818884Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:b4c3464157dfc64c87f4cf6512b4db4297338994b8d98e57babaf089c3f8ab8b","observation_id":"579e1025-61d7-40cf-a056-0032bbf7d3a9","resolution":{"observed_at":"2026-08-01T18:06:51.818884Z","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":"2026-08-01T18:06:51.929037Z","title":"and Kong, Lingpeng , title =","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:51.929037Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:dd5e36f1116ac32355418f445ff7e4aabfd0a95cfebf9981c7ffcacd09e27299","observation_id":"f2d1598d-99be-4603-b1e7-77f6745e6fe9","resolution":{"observed_at":"2026-08-01T18:06:51.929037Z","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":"2026-08-01T18:06:52.014154Z","title":"The Tenth International Conference on Learning Representations (","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:52.014154Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:b579fbb76832ebdfca77004b076c60fda7a169d4ffb44c53cf481880d6a6e1e7","observation_id":"2237979d-7cff-42c2-8038-6902b1201aad","resolution":{"observed_at":"2026-08-01T18:06:52.014154Z","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":"2026-08-01T18:06:52.122311Z","title":"Transformer Circuits Thread , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:52.122311Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:4c4c49291b66d0ecb55a464e5ad93968bcdee39f71500a08b8632193a80783dc","observation_id":"df390231-abcb-4d22-ac83-8e152c14974b","resolution":{"observed_at":"2026-08-01T18:06:52.122311Z","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":"2026-08-01T18:06:52.232528Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:52.232528Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:65cc16e8ea3a680d79eeec49f7a99c5f2291261c8298c1c97d4d5cc6ce3e7282","observation_id":"866056da-88a2-4898-9c64-fcb3b4d6f22e","resolution":{"observed_at":"2026-08-01T18:06:52.232528Z","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":"2026-08-01T18:06:52.317416Z","title":", title =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:52.317416Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:18b52d49e5bd9753dca069f31b346e8d012f20797ddff5f30e3b9f7c067bb424","observation_id":"40b13eaf-b4db-41fd-812f-aabf1e054584","resolution":{"observed_at":"2026-08-01T18:06:52.317416Z","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":"2026-08-01T18:06:52.377740Z","title":", title =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:52.377740Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:eaebe85bd942d575f88ab7a1300ca5adb1dc7a31db612affae008ae9682f3db9","observation_id":"60f6c8f3-3d7d-4c49-acab-34fae7611585","resolution":{"observed_at":"2026-08-01T18:06:52.377740Z","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":"2026-08-01T18:06:52.442993Z","title":", title =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:52.442993Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:4e0748f8b2b0b0c66698febd09eb7489c4e07fd8d848df9c64f58b4083340539","observation_id":"742fb5cf-0969-4d8d-afe5-f2fc0d02ccaf","resolution":{"observed_at":"2026-08-01T18:06:52.442993Z","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":"2026-08-01T18:06:52.495010Z","title":", title =","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:52.495010Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:a6000271ba6131bd7e200acb13aded62ec40b8f89ed30df47f05a10dac2fd469","observation_id":"b57aca37-303e-47ba-bb31-2263a2a427e8","resolution":{"observed_at":"2026-08-01T18:06:52.495010Z","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":"2026-08-01T18:06:52.537212Z","title":"2023 , eprint=","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:52.537212Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:4e3a5465b3167eec0c080e93331868cd64e47f91709e5c4370e3fff433f43d7e","observation_id":"db4ea769-0503-4da2-8433-aaed46616ad8","resolution":{"observed_at":"2026-08-01T18:06:52.537212Z","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":"2026-08-01T18:06:52.626996Z","title":"2025 , eprint=","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:52.626996Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:2746efab49e5f417a15e7b21ca1fe9d154e34185f271369fb981b28b146894da","observation_id":"29ea9a28-8101-4065-a007-7b9516d5cee2","resolution":{"observed_at":"2026-08-01T18:06:52.626996Z","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":"2026-08-01T18:06:52.712400Z","title":"Advances in Neural Information Processing Systems (NeurIPS) , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:52.712400Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:ce761ecfef1b08c9a0e9ea1e625858c1679a7016d847c434a363dfef0568d2ff","observation_id":"a5e45b83-f51d-477f-a082-c1a1c9799930","resolution":{"observed_at":"2026-08-01T18:06:52.712400Z","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":"2026-08-01T18:06:52.793129Z","title":"2024 , eprint =","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:52.793129Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:571656c2f97a96b31ae1e33e123ea9ef73aab69bb7b6a435068e65c5aae4dc35","observation_id":"30db7f6d-37c1-48b8-8c43-396adf83397d","resolution":{"observed_at":"2026-08-01T18:06:52.793129Z","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":"2026-08-01T18:06:52.875789Z","title":"2024 , eprint =","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:52.875789Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:ac7962b33059988f653597ed4c9262b1f6695d9fd704851115ce6c383a18a766","observation_id":"083ab70e-bdda-40b3-b9ea-07764fe13bf9","resolution":{"observed_at":"2026-08-01T18:06:52.875789Z","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":"2026-08-01T18:06:52.928157Z","title":"arXiv preprint arXiv:2505.23666 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:52.928157Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:2a6c98e07a4f61dd9a2673d5847b519c5c7b57c4dcfb2bc3078a687f13b89b32","observation_id":"c0deb284-9fd2-494c-b53f-eb56c33abbc2","resolution":{"observed_at":"2026-08-01T18:06:52.928157Z","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":"2026-08-01T18:06:53.000682Z","title":"2025 , eprint=","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:53.000682Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:c03f8fa3dba2e6cb2fcf589bdc98fdb93015757101dc5e2ce979b2154f8aeaed","observation_id":"45e90589-eb4f-4c15-937b-48941207c534","resolution":{"observed_at":"2026-08-01T18:06:53.000682Z","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":"2026-08-01T18:06:53.047330Z","title":"arXiv preprint arXiv:2510.01450 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:53.047330Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:ee50e56c33052c30e54dd88fcb8915fac989b8b795766df3a9e449156e5beec3","observation_id":"f991e379-4849-4a2c-b418-3d77cc2a657f","resolution":{"observed_at":"2026-08-01T18:06:53.047330Z","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":"2026-08-01T18:06:53.126299Z","title":"Annals of Physics , volume =","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:53.126299Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:1727fab7803de0c73c730cd622239e81a5e43d6b8100ba2db4ae1ccad8132253","observation_id":"dcd6c85e-7039-4e3f-8195-9aad8580147f","resolution":{"observed_at":"2026-08-01T18:06:53.126299Z","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":"2026-08-01T18:06:53.214353Z","title":"Algorithmica , volume =","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:53.214353Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:74ce7bd5b0f0a24bcbe10c7fa3ed8cb7324edab679bd268cc857f2cc7a060ade","observation_id":"2454b2ad-9134-48f2-a8fb-49708ebd909f","resolution":{"observed_at":"2026-08-01T18:06:53.214353Z","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":"2026-08-01T18:06:53.314652Z","title":"Journal of Complexity , volume =","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:53.314652Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:9e9627ddd9c6d5def05828cf6249e6c4247ea429d65f5d3a4bb37a963d3401a9","observation_id":"83bbeb46-4588-4e9f-b44d-09962ed95e5f","resolution":{"observed_at":"2026-08-01T18:06:53.314652Z","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":"2026-08-01T18:06:53.399722Z","title":"2024 , url =","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:53.399722Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:db59c35f1e9e304b346ed8c96b7b629476afe49752f6d6caff18a94f8263809e","observation_id":"da153f5f-c4df-45cc-950e-c2fb3c9bb4f2","resolution":{"observed_at":"2026-08-01T18:06:53.399722Z","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":"2026-08-01T18:06:53.459263Z","title":"Proceedings of the 39th International Conference on Machine Learning (","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:53.459263Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:f006067da3c89dd8e0e047c523545ab13c7194c1c5933c762e2bdb903ab12b51","observation_id":"89b98638-f75a-4fdd-818e-817e75c60638","resolution":{"observed_at":"2026-08-01T18:06:53.459263Z","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":"2026-08-01T18:06:53.599165Z","title":"2025 , eprint=","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:53.599165Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:aab24612c4d235e68395ebbb7a58680f067db12b608907efa9a66dc8db4aa91c","observation_id":"e5f4f255-026c-4e03-b9ce-d24e33baa975","resolution":{"observed_at":"2026-08-01T18:06:53.599165Z","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":"2026-08-01T18:06:53.827495Z","title":"2025 , eprint=","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:53.827495Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:e0c9f35d112929ee1497297c98d33b907dc49230e23b6246b271cf2daf32aa86","observation_id":"65bc154a-0a18-4053-a210-f7a817e66eee","resolution":{"observed_at":"2026-08-01T18:06:53.827495Z","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":"2026-08-01T18:06:54.053143Z","title":"2026 , eprint=","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:54.053143Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:4e111a6cfbf62fddfcb0f00a02ef1bd0426475d8fc1b88e86c8abb79c19936d8","observation_id":"429795ac-459b-4eea-953f-3ce05fe8f68a","resolution":{"observed_at":"2026-08-01T18:06:54.053143Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.05258","last_updated":"2025-04-07T12:04:28Z","snapshot_observed_at":"2026-08-03T16:01:59.392774Z","submitted_at":"2024-10-07T17:57:38Z","title":"Differential Transformer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.05258","snapshot_observed_at":"2026-08-01T18:06:54.224936Z","title":"arXiv preprint arXiv:2410.05258 , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:54.224936Z"},"links":{"cited_paper":"/paper/2410.05258","citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:04fb1da363b74afd0b6810736f5792f6aa89b1b22f91baf5b12ae2d63be9b2f3","observation_id":"875d758a-f54b-447f-a6c6-ac08efe1a7f3","resolution":{"observed_at":"2026-08-01T18:06:54.224936Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.04625","last_updated":"2023-10-06T23:37:24Z","snapshot_observed_at":"2026-07-06T16:29:03.404736Z","submitted_at":"2023-10-06T23:37:24Z","title":"Copy Suppression: Comprehensively Understanding an Attention Head","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.04625","snapshot_observed_at":"2026-08-01T18:06:54.358789Z","title":"arXiv preprint arXiv:2310.04625 , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:54.358789Z"},"links":{"cited_paper":"/paper/2310.04625","citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:c6b0ebef4eba0c6dd8deadfc320233014ee8e628a20d853b20b0683960ab3d14","observation_id":"dd125648-1291-4896-b8a0-bec78cb275bc","resolution":{"observed_at":"2026-08-01T18:06:54.358789Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.02703","last_updated":"2025-04-24T02:44:54Z","snapshot_observed_at":"2026-08-08T11:47:02.508198Z","submitted_at":"2024-10-03T17:27:30Z","title":"Selective Attention Improves Transformer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.02703","snapshot_observed_at":"2026-08-01T18:06:54.522323Z","title":"arXiv preprint arXiv:2410.02703 , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:54.522323Z"},"links":{"cited_paper":"/paper/2410.02703","citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:b4e78268e1d8488c61f87cff444b7d83f11af342e482febe60056fccc15e8b4c","observation_id":"9d0894d7-d7f6-4bd8-9b9b-d9c088546a0d","resolution":{"observed_at":"2026-08-01T18:06:54.522323Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.07176","last_updated":"2025-01-30T18:17:13Z","snapshot_observed_at":"2026-07-06T19:48:36.508447Z","submitted_at":"2024-11-11T17:56:28Z","title":"More Expressive Attention with Negative Weights","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.07176","snapshot_observed_at":"2026-08-01T18:06:54.696636Z","title":"arXiv preprint arXiv:2411.07176 , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:54.696636Z"},"links":{"cited_paper":"/paper/2411.07176","citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:490f6cb0540c10ef1df5f7fae5b1573b9319a1cc27b456a9f30f3dcb4ffa2e74","observation_id":"ff0e3634-e639-437f-975f-0f6ea85dcbd6","resolution":{"observed_at":"2026-08-01T18:06:54.696636Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.17453","last_updated":"2024-04-07T00:56:53Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-09-29T17:59:56Z","title":"Efficient Streaming Language Models with Attention Sinks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.17453","snapshot_observed_at":"2026-08-01T18:06:54.835682Z","title":"arXiv preprint arXiv:2309.17453 , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:54.835682Z"},"links":{"cited_paper":"/paper/2309.17453","citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:47367be6d574234209b805f63903dc5eab4279e66ee9b28017b3b3c6b5c4296f","observation_id":"1cc921e6-66f5-4dda-a535-8bfa71653758","resolution":{"observed_at":"2026-08-01T18:06:54.835682Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.03404","last_updated":"2023-08-01T14:27:08Z","snapshot_observed_at":"2026-08-05T14:55:30.595810Z","submitted_at":"2021-03-05T00:39:05Z","title":"Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.03404","snapshot_observed_at":"2026-08-01T18:06:54.962658Z","title":"arXiv preprint arXiv:2103.03404 , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:54.962658Z"},"links":{"cited_paper":"/paper/2103.03404","citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:ba037df5b5573a3be9162c0df66f484c79a44ae212819ed7cfccd0be6ab74ed5","observation_id":"822ff1e7-3b2e-4886-8d99-4a2f91d58481","resolution":{"observed_at":"2026-08-01T18:06:54.962658Z","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":"2026-08-01T18:06:55.112994Z","title":"First Conference on Language Modeling , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:55.112994Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:97651b6dc0fa2a001995be8b0b1f47e29e72e71fdd070c01c7560faf1b166f8b","observation_id":"6aae4ba4-0cf4-4087-adca-d5c9f8721e2f","resolution":{"observed_at":"2026-08-01T18:06:55.112994Z","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":"2026-08-01T18:06:55.185689Z","title":"2023 , howpublished=","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:55.185689Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:7640b007f2d5419781eef3e30b39797c077f1c33046867ac9565886f75c2826c","observation_id":"7c298b26-34bb-40fe-9ade-e23b8acdb5b3","resolution":{"observed_at":"2026-08-01T18:06:55.185689Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.02385","last_updated":"2024-06-04T02:05:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-01-04T17:54:59Z","title":"TinyLlama: An Open-Source Small Language Model","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.02385","snapshot_observed_at":"2026-08-01T18:06:55.271436Z","title":"2401.02385 , archivePrefix=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:55.271436Z"},"links":{"cited_paper":"/paper/2401.02385","citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:ed688b222661848d54248d36dbc575ce9ab710a6ab4a8efc23a667544d2ba573","observation_id":"bc11385f-1a5c-4f94-9b06-9cd462ba9d62","resolution":{"observed_at":"2026-08-01T18:06:55.271436Z","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":"2026-08-01T18:06:55.371466Z","title":"2016 , eprint =","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:55.371466Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:e18cd4c9e5fc9b66fb6f95be3ee909b6b2dfb2b6bff15f6fbe6cba8adf9e678e","observation_id":"ccf54976-ad2a-432e-81aa-844e83e1f765","resolution":{"observed_at":"2026-08-01T18:06:55.371466Z","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":"10.1016/0893-6080(93)90014-n","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"1993 , issn =","venue":"Neural Networks","work_id":"29de3cd6-c446-40a5-b5fb-780cfcd3e685","year":1993},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:55.528144Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:20cd51f67c0094074ef60032255eb110f0cce1dc60f82023b774100e1788e365","observation_id":"d980b704-111a-4c47-b459-53866248109f","resolution":{"observed_at":"2026-08-01T18:08:25.330842Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-01T18:06:55.639072Z","title":"Physical Review Letters , volume =","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:55.639072Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:d998c4f675457609591893feed668ffbc6f08e73ccb977fac2ce04f2e38a4ecb","observation_id":"407319d9-a453-4a3f-98c1-e8eae492fda1","resolution":{"observed_at":"2026-08-01T18:06:55.639072Z","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":"2026-08-01T18:06:55.728064Z","title":"2026 , eprint =","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:55.728064Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:5593dd153c458ca7991dafab00ab391c1d5025329eb4f27b160fde5453ed891e","observation_id":"e9666520-d856-4334-9e4a-f9b4c294938b","resolution":{"observed_at":"2026-08-01T18:06:55.728064Z","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":"2026-08-01T18:06:55.840416Z","title":"and Lindenstrauss, Joram , title =","venue":null,"work_id":null,"year":1984},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:55.840416Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:365e93ca9b362c014459f21db055b696d7b95591386f8a1d1aa4d781e60e01b5","observation_id":"170521ef-5649-4364-bc8c-08f7b7eb98ff","resolution":{"observed_at":"2026-08-01T18:06:55.840416Z","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":"2026-08-01T18:06:55.988053Z","title":"Journal of Computer and System Sciences , volume =","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:55.988053Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:6ef1c8beda0b9184ef736df137a41efa9c97e4613d5b442c566e94bb950a81d1","observation_id":"178fb62d-6981-47eb-957a-2835c080c40f","resolution":{"observed_at":"2026-08-01T18:06:55.988053Z","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":"2026-08-01T18:06:56.062522Z","title":"Combinatorics, Probability and Computing , volume =","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:56.062522Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:13d279f566874adac6d16d57cd39e363689e8222e61f80e7fe5a8fe5ad52d44b","observation_id":"a29d6b50-d049-4c11-8816-9be5bd4e87e9","resolution":{"observed_at":"2026-08-01T18:06:56.062522Z","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":"2026-08-01T18:06:56.121665Z","title":"and Elad, Michael , title =","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:56.121665Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:091a4bb8f3ca8cc4d7fe439009a8285d8c6f4a53e7d0a866f66b0afa6226bb51","observation_id":"02582b04-9665-4a71-99b4-626511c535ac","resolution":{"observed_at":"2026-08-01T18:06:56.121665Z","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":"2026-08-01T18:06:56.232421Z","title":"2025 , eprint=","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:56.232421Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:bacd673db13b35e135a5d527ffaafd62d7a8e7900829ae9da79e67a2589bfd06","observation_id":"bf6b149d-75c0-4cd4-be5d-8a77ebcc2222","resolution":{"observed_at":"2026-08-01T18:06:56.232421Z","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":"2026-08-01T18:06:56.342744Z","title":"2023 , eprint=","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones","version":1},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-08-01T18:06:56.342744Z"},"links":{"citing_paper":"/paper/2607.17419"},"observation_digest":"sha256:1640da2169f9a6af3e8c363a2d12a04f1770e8b4721f1290fcc244ee31d1a2c5","observation_id":"b9978a0a-6b71-4930-b568-2b7e9acb5510","resolution":{"observed_at":"2026-08-01T18:06:56.342744Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.17419","last_updated":"2026-07-19T21:46:09Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-05T15:40:44.010247Z","submitted_at":"2026-07-19T21:46:09Z","title":"Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones"},"reference_resolution":{"displayed":67,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":66,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":67},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 67 of 67 outbound references and 0 inbound Pith citation observations for arXiv:2607.17419."}