{"as_of":"2026-08-09T09:30:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c48d6a22d0fe8ccaa181bb8e0d288fd3142431e45b9d0eeb66112352b7c72cc9","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":14,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":14,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":14,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":14,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T13:18:19.340220Z","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":"2026-07-04T12:39:50.016990Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2103.02143","last_updated":"2021-03-19T21:24:06Z","snapshot_observed_at":"2026-08-04T23:37:38.910806Z","submitted_at":"2021-03-03T02:48:56Z","title":"Random Feature Attention","version":2},"cited_work":{"arxiv_id":"2103.02143","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.02143","snapshot_observed_at":"2026-07-04T12:39:50.016990Z","title":"Random feature attention.arXiv preprint arXiv:2103.02143","venue":null,"work_id":"1bd373e4-ab9a-4e64-8e88-1c304897525b","year":2021},"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":65,"source":"arxiv_source","source_observed_at":"2026-05-15T01:15:13.991219Z"},"links":{"cited_paper":"/paper/2103.02143","citing_paper":"/paper/2312.06635"},"observation_digest":"sha256:7f00b85dbb3e07d6434dbc1ae228da3db174d9554485d66769092eed5a0496c9","observation_id":"65595d49-61e1-4526-81a7-73094e8ddd77","resolution":{"observed_at":"2026-05-15T01:15:14.165236Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.02143","last_updated":"2021-03-19T21:24:06Z","snapshot_observed_at":"2026-08-04T23:37:38.910806Z","submitted_at":"2021-03-03T02:48:56Z","title":"Random Feature Attention","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.02143","snapshot_observed_at":"2026-08-08T13:18:19.340220Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.07277","last_updated":"2025-02-11T05:44:50Z","snapshot_observed_at":"2026-08-08T13:13:50.722462Z","submitted_at":"2025-02-11T05:44:50Z","title":"Enhancing Video Understanding: Deep Neural Networks for Spatiotemporal Analysis","version":1},"reference_index":103,"source":"pdf_text","source_observed_at":"2026-08-08T13:18:19.340220Z"},"links":{"cited_paper":"/paper/2103.02143","citing_paper":"/paper/2502.07277"},"observation_digest":"sha256:e82b2c576ad08a0fa5122d8f7b4ec7f39782b07f6bd22f7ac03ad75b8f89c232","observation_id":"70772b3d-ec89-43ad-b633-5dcc19d8b82c","resolution":{"observed_at":"2026-08-08T13:18:19.340220Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.02143","last_updated":"2021-03-19T21:24:06Z","snapshot_observed_at":"2026-08-04T23:37:38.910806Z","submitted_at":"2021-03-03T02:48:56Z","title":"Random Feature Attention","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.02143","snapshot_observed_at":"2026-08-07T10:30:13.820406Z","title":"Smith, and Lingpeng Kong","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.05233","last_updated":"2026-06-03T16:16:54Z","snapshot_observed_at":"2026-08-07T10:20:00.883360Z","submitted_at":"2025-06-05T16:50:23Z","title":"MesaNet: Sequence Modeling by Locally Optimal Test-Time Training","version":2},"reference_index":83,"source":"arxiv_source","source_observed_at":"2026-08-07T10:30:13.820406Z"},"links":{"cited_paper":"/paper/2103.02143","citing_paper":"/paper/2506.05233"},"observation_digest":"sha256:fa08e6ec11ed4a5d17372fe60c34d5a7da1107bfa01e2ec2468e102042a3acb3","observation_id":"34b5ac72-00e4-4aa2-abe9-2fe533452ac4","resolution":{"observed_at":"2026-08-07T10:30:13.820406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.02143","last_updated":"2021-03-19T21:24:06Z","snapshot_observed_at":"2026-08-04T23:37:38.910806Z","submitted_at":"2021-03-03T02:48:56Z","title":"Random Feature Attention","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.02143","snapshot_observed_at":"2026-08-06T18:19:59.085521Z","title":"Random feature attention","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.08637","last_updated":"2025-07-11T14:40:40Z","snapshot_observed_at":"2026-08-06T18:11:30.264997Z","submitted_at":"2025-07-11T14:40:40Z","title":"Scaling Attention to Very Long Sequences in Linear Time with Wavelet-Enhanced Random Spectral Attention (WERSA)","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T18:19:59.085521Z"},"links":{"cited_paper":"/paper/2103.02143","citing_paper":"/paper/2507.08637"},"observation_digest":"sha256:ea14a228b70c03133b51c8152c2e9ab63f8dbc5e999bfe4eef5886ae3296a50f","observation_id":"892858da-22bc-4cfa-b2b6-4f01e6cb0adf","resolution":{"observed_at":"2026-08-06T18:19:59.085521Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.02143","last_updated":"2021-03-19T21:24:06Z","snapshot_observed_at":"2026-08-04T23:37:38.910806Z","submitted_at":"2021-03-03T02:48:56Z","title":"Random Feature Attention","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.02143","snapshot_observed_at":"2026-08-05T05:29:21.517415Z","title":"Random feature attention","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.05282","last_updated":"2025-09-05T17:48:26Z","snapshot_observed_at":"2026-08-08T13:14:59.554723Z","submitted_at":"2025-09-05T17:48:26Z","title":"Elucidating the Design Space of Decay in Linear Attention","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-05T05:29:21.517415Z"},"links":{"cited_paper":"/paper/2103.02143","citing_paper":"/paper/2509.05282"},"observation_digest":"sha256:fe2c00a77e8e8c8fcb0c355110f6a4e871ef2684b77d260965288fa8fe6b72b2","observation_id":"d30f7494-0234-4161-bc89-1c7483ff83a8","resolution":{"observed_at":"2026-08-05T05:29:21.517415Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.02143","last_updated":"2021-03-19T21:24:06Z","snapshot_observed_at":"2026-08-04T23:37:38.910806Z","submitted_at":"2021-03-03T02:48:56Z","title":"Random Feature Attention","version":2},"cited_work":{"arxiv_id":"2103.02143","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.02143","snapshot_observed_at":"2026-07-04T12:39:50.016990Z","title":"Random feature attention.arXiv preprint arXiv:2103.02143","venue":null,"work_id":"1bd373e4-ab9a-4e64-8e88-1c304897525b","year":2021},"citing_paper":{"arxiv_id":"2510.27258","last_updated":"2026-05-14T15:35:59Z","snapshot_observed_at":"2026-08-08T14:18:17.260680Z","submitted_at":"2025-10-31T07:54:37Z","title":"Higher-order Linear Attention","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-18T03:05:35.823369Z"},"links":{"cited_paper":"/paper/2103.02143","citing_paper":"/paper/2510.27258"},"observation_digest":"sha256:b1396292e325157513f80525e457748e63a025c884d951809679ecef839f8ea5","observation_id":"1865fa0f-edf9-42f0-b85e-c746f26b013c","resolution":{"observed_at":"2026-05-18T03:05:47.388067Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.02143","last_updated":"2021-03-19T21:24:06Z","snapshot_observed_at":"2026-08-04T23:37:38.910806Z","submitted_at":"2021-03-03T02:48:56Z","title":"Random Feature Attention","version":2},"cited_work":{"arxiv_id":"2103.02143","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.02143","snapshot_observed_at":"2026-07-04T12:39:50.016990Z","title":"Random feature attention.arXiv preprint arXiv:2103.02143","venue":null,"work_id":"1bd373e4-ab9a-4e64-8e88-1c304897525b","year":2021},"citing_paper":{"arxiv_id":"2603.14360","last_updated":"2026-05-13T23:29:01Z","snapshot_observed_at":"2026-08-01T09:38:25.349230Z","submitted_at":"2026-03-15T12:53:09Z","title":"M$^2$RNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language Modeling","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-15T11:35:43.088803Z"},"links":{"cited_paper":"/paper/2103.02143","citing_paper":"/paper/2603.14360"},"observation_digest":"sha256:f5cd76f3d5349513f66784674f64881c7148ff4da75b6661095e67f68aa9e75e","observation_id":"1709028a-4e5e-4697-a44f-96e5c5909aa8","resolution":{"observed_at":"2026-05-15T11:39:59.259044Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.02143","last_updated":"2021-03-19T21:24:06Z","snapshot_observed_at":"2026-08-04T23:37:38.910806Z","submitted_at":"2021-03-03T02:48:56Z","title":"Random Feature Attention","version":2},"cited_work":{"arxiv_id":"2103.02143","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.02143","snapshot_observed_at":"2026-07-04T12:39:50.016990Z","title":"Random feature attention.arXiv preprint arXiv:2103.02143","venue":null,"work_id":"1bd373e4-ab9a-4e64-8e88-1c304897525b","year":2021},"citing_paper":{"arxiv_id":"2604.14191","last_updated":"2026-04-01T09:23:08Z","snapshot_observed_at":"2026-07-06T23:02:00.082783Z","submitted_at":"2026-04-01T09:23:08Z","title":"Attention to Mamba: A Recipe for Cross-Architecture Distillation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-13T23:07:41.022051Z"},"links":{"cited_paper":"/paper/2103.02143","citing_paper":"/paper/2604.14191"},"observation_digest":"sha256:cc020ad997d8f1f6c3e6bc3678b345d2be0e6cf02726e7a08b4368ef4983a9be","observation_id":"e6d84347-504f-4770-8481-2c82ada2edb6","resolution":{"observed_at":"2026-05-13T23:08:24.880040Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.02143","last_updated":"2021-03-19T21:24:06Z","snapshot_observed_at":"2026-08-04T23:37:38.910806Z","submitted_at":"2021-03-03T02:48:56Z","title":"Random Feature Attention","version":2},"cited_work":{"arxiv_id":"2103.02143","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.02143","snapshot_observed_at":"2026-07-04T12:39:50.016990Z","title":"Random feature attention.arXiv preprint arXiv:2103.02143","venue":null,"work_id":"1bd373e4-ab9a-4e64-8e88-1c304897525b","year":2021},"citing_paper":{"arxiv_id":"2605.09905","last_updated":"2026-05-11T02:48:06Z","snapshot_observed_at":"2026-07-06T23:21:54.140120Z","submitted_at":"2026-05-11T02:48:06Z","title":"Rethinking Random Transformers as Adaptive Sequence Smoothers for Sleep Staging","version":1},"reference_index":81,"source":"arxiv_source","source_observed_at":"2026-05-12T04:41:48.085125Z"},"links":{"cited_paper":"/paper/2103.02143","citing_paper":"/paper/2605.09905"},"observation_digest":"sha256:fad8e5018f92960a7222b24f3a4f9ca0853051dc7c94e9b810555035c7392ab7","observation_id":"ac6a2fc1-9c13-4536-92f9-ce5530d52002","resolution":{"observed_at":"2026-05-12T06:01:24.149112Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.02143","last_updated":"2021-03-19T21:24:06Z","snapshot_observed_at":"2026-08-04T23:37:38.910806Z","submitted_at":"2021-03-03T02:48:56Z","title":"Random Feature Attention","version":2},"cited_work":{"arxiv_id":"2103.02143","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.02143","snapshot_observed_at":"2026-07-04T12:39:50.016990Z","title":"Random feature attention.arXiv preprint arXiv:2103.02143","venue":null,"work_id":"1bd373e4-ab9a-4e64-8e88-1c304897525b","year":2021},"citing_paper":{"arxiv_id":"2605.12491","last_updated":"2026-05-12T17:59:26Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-05-12T17:59:26Z","title":"Elastic Attention Cores for Scalable Vision Transformers","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-05-13T06:02:40.158866Z"},"links":{"cited_paper":"/paper/2103.02143","citing_paper":"/paper/2605.12491"},"observation_digest":"sha256:42838ef57bf6fb5cc7baa8e5d6acfe3dc876c0eca484c92df948e1805ffefd20","observation_id":"f5259d0a-2e5f-4856-8263-eefee22d8af7","resolution":{"observed_at":"2026-05-13T06:07:22.876757Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.02143","last_updated":"2021-03-19T21:24:06Z","snapshot_observed_at":"2026-08-04T23:37:38.910806Z","submitted_at":"2021-03-03T02:48:56Z","title":"Random Feature Attention","version":2},"cited_work":{"arxiv_id":"2103.02143","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.02143","snapshot_observed_at":"2026-07-04T12:39:50.016990Z","title":"Random feature attention.arXiv preprint arXiv:2103.02143","venue":null,"work_id":"1bd373e4-ab9a-4e64-8e88-1c304897525b","year":2021},"citing_paper":{"arxiv_id":"2605.28769","last_updated":"2026-05-27T17:26:09Z","snapshot_observed_at":"2026-07-06T23:38:19.096349Z","submitted_at":"2026-05-27T17:26:09Z","title":"Multi-Mixer Models: Flexible Sequence Modeling with Shared Representations","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-29T14:24:54.942194Z"},"links":{"cited_paper":"/paper/2103.02143","citing_paper":"/paper/2605.28769"},"observation_digest":"sha256:e947ad21f7e91a654ce6596989dd57528c0145c780450463dd07402365d6d113","observation_id":"9d20a8b4-375d-4971-9044-4084fc837fc2","resolution":{"observed_at":"2026-06-29T14:33:30.785124Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.02143","last_updated":"2021-03-19T21:24:06Z","snapshot_observed_at":"2026-08-04T23:37:38.910806Z","submitted_at":"2021-03-03T02:48:56Z","title":"Random Feature Attention","version":2},"cited_work":{"arxiv_id":"2103.02143","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.02143","snapshot_observed_at":"2026-07-04T12:39:50.016990Z","title":"Random feature attention.arXiv preprint arXiv:2103.02143","venue":null,"work_id":"1bd373e4-ab9a-4e64-8e88-1c304897525b","year":2021},"citing_paper":{"arxiv_id":"2606.00746","last_updated":"2026-05-30T14:29:43Z","snapshot_observed_at":"2026-07-06T23:41:24.911421Z","submitted_at":"2026-05-30T14:29:43Z","title":"Scaling Parallel Sequence Models to Foundation-Scale Vision Encoders","version":1},"reference_index":107,"source":"arxiv_source","source_observed_at":"2026-06-28T19:23:08.100056Z"},"links":{"cited_paper":"/paper/2103.02143","citing_paper":"/paper/2606.00746"},"observation_digest":"sha256:4a3f6edce9d56ae3132f49ddabb5438ef36fd5ff6b483d5b6a2cfac6dc3b3678","observation_id":"dd0430b4-0fe0-4cdc-bc21-683598987f09","resolution":{"observed_at":"2026-06-28T19:32:35.233826Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.02143","last_updated":"2021-03-19T21:24:06Z","snapshot_observed_at":"2026-08-04T23:37:38.910806Z","submitted_at":"2021-03-03T02:48:56Z","title":"Random Feature Attention","version":2},"cited_work":{"arxiv_id":"2103.02143","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.02143","snapshot_observed_at":"2026-07-04T12:39:50.016990Z","title":"Random feature attention.arXiv preprint arXiv:2103.02143","venue":null,"work_id":"1bd373e4-ab9a-4e64-8e88-1c304897525b","year":2021},"citing_paper":{"arxiv_id":"2606.09862","last_updated":"2026-05-31T17:43:06Z","snapshot_observed_at":"2026-08-03T01:37:13.983372Z","submitted_at":"2026-05-31T17:43:06Z","title":"Blurry Window Attention","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-06-28T17:43:34.429061Z"},"links":{"cited_paper":"/paper/2103.02143","citing_paper":"/paper/2606.09862"},"observation_digest":"sha256:b2668549f475865fa74d4dca43aee9d26010d7ee935f5443bbe0188e7aaafacc","observation_id":"fca26131-b39e-4f38-a51e-e9c5487e29f5","resolution":{"observed_at":"2026-07-01T20:46:14.012497Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.02143","last_updated":"2021-03-19T21:24:06Z","snapshot_observed_at":"2026-08-04T23:37:38.910806Z","submitted_at":"2021-03-03T02:48:56Z","title":"Random Feature Attention","version":2},"cited_work":{"arxiv_id":"2103.02143","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.02143","snapshot_observed_at":"2026-07-04T12:39:50.016990Z","title":"Random feature attention.arXiv preprint arXiv:2103.02143","venue":null,"work_id":"1bd373e4-ab9a-4e64-8e88-1c304897525b","year":2021},"citing_paper":{"arxiv_id":"2606.23159","last_updated":"2026-06-22T11:02:40Z","snapshot_observed_at":"2026-08-08T04:12:43.051678Z","submitted_at":"2026-06-22T11:02:40Z","title":"General-Purpose Nonlinear Function Approximation via Linear Integrated Photonics","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-06-26T06:12:43.253235Z"},"links":{"cited_paper":"/paper/2103.02143","citing_paper":"/paper/2606.23159"},"observation_digest":"sha256:6f8a0e93dcf588239aa20b3b7c3a7be82a4b7750e485043de707d0b561ddd159","observation_id":"d4a862c6-363d-44a5-a5a0-db551698921f","resolution":{"observed_at":"2026-07-04T12:39:50.018405Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2103.02143/citation-record","integrity":"/paper/2103.02143/integrity","json":"/paper/2103.02143/citation-record.json","paper":"/paper/2103.02143"},"outbound":[],"paper":{"arxiv_id":"2103.02143","last_updated":"2021-03-19T21:24:06Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-04T23:37:38.910806Z","submitted_at":"2021-03-03T02:48:56Z","title":"Random Feature Attention"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 14 inbound Pith citation observations for arXiv:2103.02143."}