{"as_of":"2026-08-21T14:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:791fa57c5d040c7e7cd115e281c3a5f6c5bc00c4e8c96e5b86870bd027a758da","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":26,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":26,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+00:00","state":"measured"},{"denominator":26,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":26,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T10:32:52.309122Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"pith","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":1445,"observed_at":"2026-08-05T02:28:24.338817Z","source":"pith"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2105.01601","last_updated":"2021-06-11T09:36:50Z","snapshot_observed_at":"2026-08-20T13:50:07.095032Z","submitted_at":"2021-05-04T16:17:21Z","title":"MLP-Mixer: An all-MLP Architecture for Vision","version":4},"cited_work":{"arxiv_id":"2105.01601","doi":"10.48550/arxiv.2105.01601","metadata_source":"pith","pith_arxiv_id":"2105.01601","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"CoRR, abs/2105.01601","venue":"cs.CV","work_id":"30cb7db2-723e-4ee0-9a0c-e83aa9a83061","year":2021},"citing_paper":{"arxiv_id":"2111.00396","last_updated":"2022-08-05T17:54:38Z","snapshot_observed_at":"2026-08-14T01:02:41.198730Z","submitted_at":"2021-10-31T03:32:18Z","title":"Efficiently Modeling Long Sequences with Structured State Spaces","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-11T10:41:55.618357Z"},"links":{"cited_paper":"/paper/2105.01601","citing_paper":"/paper/2111.00396"},"observation_digest":"sha256:3bd352cf6f39a0aa9926f5a5dcb2d9fd9475069c77a194de156231a5f1f6f129","observation_id":"118767e3-ce2a-4ce9-8a48-50bd3c354ec5","resolution":{"observed_at":"2026-05-11T10:41:55.808830Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2105.01601","last_updated":"2021-06-11T09:36:50Z","snapshot_observed_at":"2026-08-20T13:50:07.095032Z","submitted_at":"2021-05-04T16:17:21Z","title":"MLP-Mixer: An all-MLP Architecture for Vision","version":4},"cited_work":{"arxiv_id":"2105.01601","doi":"10.48550/arxiv.2105.01601","metadata_source":"pith","pith_arxiv_id":"2105.01601","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"CoRR, abs/2105.01601","venue":"cs.CV","work_id":"30cb7db2-723e-4ee0-9a0c-e83aa9a83061","year":2021},"citing_paper":{"arxiv_id":"2305.13048","last_updated":"2023-12-11T03:58:56Z","snapshot_observed_at":"2026-08-17T17:58:38.402665Z","submitted_at":"2023-05-22T13:57:41Z","title":"RWKV: Reinventing RNNs for the Transformer Era","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-13T10:53:42.020178Z"},"links":{"cited_paper":"/paper/2105.01601","citing_paper":"/paper/2305.13048"},"observation_digest":"sha256:f01c6d1b3f2d5dc17fa5c85f0cd7166dcdc32e7dc28a418b7770df3e3a432adc","observation_id":"9436486f-6b20-4dba-8496-366e33a11e65","resolution":{"observed_at":"2026-05-13T10:53:42.079952Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2105.01601","last_updated":"2021-06-11T09:36:50Z","snapshot_observed_at":"2026-08-20T13:50:07.095032Z","submitted_at":"2021-05-04T16:17:21Z","title":"MLP-Mixer: An all-MLP Architecture for Vision","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.01601","snapshot_observed_at":"2026-08-12T20:08:48.091541Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.10496","last_updated":"2024-11-15T06:54:25Z","snapshot_observed_at":"2026-08-19T14:44:39.245732Z","submitted_at":"2024-11-15T06:54:25Z","title":"Guided Learning: Lubricating End-to-End Modeling for Multi-stage Decision-making","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-12T20:08:48.091541Z"},"links":{"cited_paper":"/paper/2105.01601","citing_paper":"/paper/2411.10496"},"observation_digest":"sha256:e9cb2f25203ef119b921f95f8fdb7ff86138fa91fdfffc3b15d62891e13dd204","observation_id":"aecdae05-5999-4a21-ae6d-72d63d8560ea","resolution":{"observed_at":"2026-08-12T20:08:48.091541Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.01601","last_updated":"2021-06-11T09:36:50Z","snapshot_observed_at":"2026-08-20T13:50:07.095032Z","submitted_at":"2021-05-04T16:17:21Z","title":"MLP-Mixer: An all-MLP Architecture for Vision","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.01601","snapshot_observed_at":"2026-08-12T17:36:34.084916Z","title":"MLP-Mixer: An all-MLP Architecture for Vision,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.12431","last_updated":"2024-11-19T11:41:22Z","snapshot_observed_at":"2026-08-20T22:22:49.402920Z","submitted_at":"2024-11-19T11:41:22Z","title":"CV-Cities: Advancing Cross-View Geo-Localization in Global Cities","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T17:36:34.084916Z"},"links":{"cited_paper":"/paper/2105.01601","citing_paper":"/paper/2411.12431"},"observation_digest":"sha256:0b3ded3a3a79905078f647cdc019c14bbf83d49f30f9774ccc63c16f90ad0576","observation_id":"e05ef0ac-1274-4421-8a77-801e2b43a443","resolution":{"observed_at":"2026-08-12T17:36:34.084916Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.01601","last_updated":"2021-06-11T09:36:50Z","snapshot_observed_at":"2026-08-20T13:50:07.095032Z","submitted_at":"2021-05-04T16:17:21Z","title":"MLP-Mixer: An all-MLP Architecture for Vision","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.01601","snapshot_observed_at":"2026-08-12T12:12:45.385963Z","title":"Mlp-mixer: An all-mlp ar- chitecture for vision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.17390","last_updated":"2024-11-26T12:48:47Z","snapshot_observed_at":"2026-08-18T07:08:33.729629Z","submitted_at":"2024-11-26T12:48:47Z","title":"Dual-Representation Interaction Driven Image Quality Assessment with Restoration Assistance","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-12T12:12:45.385963Z"},"links":{"cited_paper":"/paper/2105.01601","citing_paper":"/paper/2411.17390"},"observation_digest":"sha256:aef2925476529e1f29a17a703ab4fac65cb60ce7c7e6e4688a28d6b70858551e","observation_id":"8a3c28e8-d1b0-4420-a206-8fbbe184f929","resolution":{"observed_at":"2026-08-12T12:12:45.385963Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.01601","last_updated":"2021-06-11T09:36:50Z","snapshot_observed_at":"2026-08-20T13:50:07.095032Z","submitted_at":"2021-05-04T16:17:21Z","title":"MLP-Mixer: An all-MLP Architecture for Vision","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.01601","snapshot_observed_at":"2026-08-11T17:59:15.744703Z","title":"Mlp-mixer: An all-mlp architecture for vision","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.744703Z"},"links":{"cited_paper":"/paper/2105.01601","citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:1236b6de4f31dfef2ba281ec8c2d53178367199349aa08b85f7b8e9d86a4e71b","observation_id":"cefcc746-cada-43a7-b3c0-6257b017d033","resolution":{"observed_at":"2026-08-11T17:59:15.744703Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.01601","last_updated":"2021-06-11T09:36:50Z","snapshot_observed_at":"2026-08-20T13:50:07.095032Z","submitted_at":"2021-05-04T16:17:21Z","title":"MLP-Mixer: An all-MLP Architecture for Vision","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.01601","snapshot_observed_at":"2026-08-11T00:15:11.858137Z","title":"Mlp-mixer: An all-mlp architecture for vision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-15T13:10:54.452810Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.858137Z"},"links":{"cited_paper":"/paper/2105.01601","citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:b8d06d75d412f4e3131c9e433e90d481773f09d93a1cfc37d4f026ee915ddee7","observation_id":"03a491d0-fdb0-4e89-9e8f-aa29dff04439","resolution":{"observed_at":"2026-08-11T00:15:11.858137Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.01601","last_updated":"2021-06-11T09:36:50Z","snapshot_observed_at":"2026-08-20T13:50:07.095032Z","submitted_at":"2021-05-04T16:17:21Z","title":"MLP-Mixer: An all-MLP Architecture for Vision","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.01601","snapshot_observed_at":"2026-08-10T15:20:09.965791Z","title":"MLP-Mixer: An all-MLP Architecture for Vision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.14322","last_updated":"2025-01-24T08:34:22Z","snapshot_observed_at":"2026-08-18T06:00:57.162021Z","submitted_at":"2025-01-24T08:34:22Z","title":"Relative Layer-Wise Relevance Propagation: a more Robust Neural Networks eXplaination","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T15:20:09.965791Z"},"links":{"cited_paper":"/paper/2105.01601","citing_paper":"/paper/2501.14322"},"observation_digest":"sha256:4dd78543c674822b1d5db1e6a9c327208a4cb7ceb7b0cfcf7881394065ac8981","observation_id":"fc07db14-ae42-420c-96e5-09893689eb72","resolution":{"observed_at":"2026-08-10T15:20:09.965791Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.01601","last_updated":"2021-06-11T09:36:50Z","snapshot_observed_at":"2026-08-20T13:50:07.095032Z","submitted_at":"2021-05-04T16:17:21Z","title":"MLP-Mixer: An all-MLP Architecture for Vision","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.01601","snapshot_observed_at":"2026-08-16T10:32:52.309122Z","title":"MLP - Mixer : An all- MLP Architecture for Vision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.18600","last_updated":"2025-04-24T18:47:22Z","snapshot_observed_at":"2026-08-19T23:18:33.376295Z","submitted_at":"2025-04-24T18:47:22Z","title":"QuantBench: Benchmarking AI Methods for Quantitative Investment","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-16T10:32:52.309122Z"},"links":{"cited_paper":"/paper/2105.01601","citing_paper":"/paper/2504.18600"},"observation_digest":"sha256:68741073aa360d1df194103daa4648c57e8c14f5f49d7f7a5fffc0affeeda80b","observation_id":"974178f5-6108-4571-a00c-db671ef4042b","resolution":{"observed_at":"2026-08-16T10:32:52.309122Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.01601","last_updated":"2021-06-11T09:36:50Z","snapshot_observed_at":"2026-08-20T13:50:07.095032Z","submitted_at":"2021-05-04T16:17:21Z","title":"MLP-Mixer: An all-MLP Architecture for Vision","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.01601","snapshot_observed_at":"2026-08-16T06:05:05.528423Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.19227","last_updated":"2025-04-27T13:09:14Z","snapshot_observed_at":"2026-08-16T05:56:05.905844Z","submitted_at":"2025-04-27T13:09:14Z","title":"Unsupervised 2D-3D lifting of non-rigid objects using local constraints","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-16T06:05:05.528423Z"},"links":{"cited_paper":"/paper/2105.01601","citing_paper":"/paper/2504.19227"},"observation_digest":"sha256:222b5e2963d12c30200bcbe3cd4a01788b54f42114e6d3f7cdecd5d0e4194279","observation_id":"56723980-c304-46d2-8959-20c18b51060a","resolution":{"observed_at":"2026-08-16T06:05:05.528423Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.01601","last_updated":"2021-06-11T09:36:50Z","snapshot_observed_at":"2026-08-20T13:50:07.095032Z","submitted_at":"2021-05-04T16:17:21Z","title":"MLP-Mixer: An all-MLP Architecture for Vision","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.01601","snapshot_observed_at":"2026-08-07T14:15:46.972275Z","title":"Mlp-mixer: An all-mlp architecture for vision,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.19535","last_updated":"2025-05-26T05:47:09Z","snapshot_observed_at":"2026-08-18T07:06:21.546171Z","submitted_at":"2025-05-26T05:47:09Z","title":"TDVE-Assessor: Benchmarking and Evaluating the Quality of Text-Driven Video Editing with LMMs","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T14:15:46.972275Z"},"links":{"cited_paper":"/paper/2105.01601","citing_paper":"/paper/2505.19535"},"observation_digest":"sha256:b1e0340ed924d5a6e9c249a7c9725c175091c90e40e89117251595526ca0d551","observation_id":"2a2ac725-4e2f-4ca5-9db3-93e2c7a3cef6","resolution":{"observed_at":"2026-08-07T14:15:46.972275Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.01601","last_updated":"2021-06-11T09:36:50Z","snapshot_observed_at":"2026-08-20T13:50:07.095032Z","submitted_at":"2021-05-04T16:17:21Z","title":"MLP-Mixer: An all-MLP Architecture for Vision","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.01601","snapshot_observed_at":"2026-08-07T13:01:33.436568Z","title":"Mlp- mixer: An all-mlp architecture for vision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.22985","last_updated":"2025-05-29T01:48:36Z","snapshot_observed_at":"2026-08-18T19:22:16.156881Z","submitted_at":"2025-05-29T01:48:36Z","title":"Knowledge Distillation for Reservoir-based Classifier: Human Activity Recognition","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T13:01:33.436568Z"},"links":{"cited_paper":"/paper/2105.01601","citing_paper":"/paper/2505.22985"},"observation_digest":"sha256:165088af047ddb28805773cc42d36e7f3e80bb9e0bb1a9f5056710cae19bbfa1","observation_id":"ea28c7a0-18af-4086-bfbc-242b9042ad46","resolution":{"observed_at":"2026-08-07T13:01:33.436568Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.01601","last_updated":"2021-06-11T09:36:50Z","snapshot_observed_at":"2026-08-20T13:50:07.095032Z","submitted_at":"2021-05-04T16:17:21Z","title":"MLP-Mixer: An all-MLP Architecture for Vision","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.01601","snapshot_observed_at":"2026-08-07T05:42:15.846285Z","title":"Tolstikhin, Neil Houlsby, Alexander Kolesnikov, Lu- cas Beyer, Xiaohua Zhai, Thomas Unterthiner, Jessica Yung, Daniel Keysers, Jakob Uszkoreit, Mario Lucic, and Alexey Dosovitskiy","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.07310","last_updated":"2025-08-01T18:44:17Z","snapshot_observed_at":"2026-08-20T21:57:43.862054Z","submitted_at":"2025-06-08T22:55:06Z","title":"AllTracker: Efficient Dense Point Tracking at High Resolution","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:15.846285Z"},"links":{"cited_paper":"/paper/2105.01601","citing_paper":"/paper/2506.07310"},"observation_digest":"sha256:74a552f23517afbc817d1922474fd6c049a3195931408be6821e1ef31f9340cc","observation_id":"3dfdcaae-078a-49e3-af05-5a8ca0f587e5","resolution":{"observed_at":"2026-08-07T05:42:15.846285Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.01601","last_updated":"2021-06-11T09:36:50Z","snapshot_observed_at":"2026-08-20T13:50:07.095032Z","submitted_at":"2021-05-04T16:17:21Z","title":"MLP-Mixer: An all-MLP Architecture for Vision","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.01601","snapshot_observed_at":"2026-08-06T21:25:52.324196Z","title":"Tolstikhin, N","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.00182","last_updated":"2025-07-02T17:15:08Z","snapshot_observed_at":"2026-08-19T19:57:15.018502Z","submitted_at":"2025-06-30T18:44:27Z","title":"Graph-Based Deep Learning for Component Segmentation of Maize Plants","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T21:25:52.324196Z"},"links":{"cited_paper":"/paper/2105.01601","citing_paper":"/paper/2507.00182"},"observation_digest":"sha256:3c240460bb424573117269842caafe6f78fdc00ecec9df92ad643fb8de5bc202","observation_id":"709b67a1-b440-4e7f-b7b2-17337238a707","resolution":{"observed_at":"2026-08-06T21:25:52.324196Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.01601","last_updated":"2021-06-11T09:36:50Z","snapshot_observed_at":"2026-08-20T13:50:07.095032Z","submitted_at":"2021-05-04T16:17:21Z","title":"MLP-Mixer: An all-MLP Architecture for Vision","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.01601","snapshot_observed_at":"2026-08-05T14:41:43.820076Z","title":"Tolstikhin, N","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.21040","last_updated":"2025-08-28T17:44:52Z","snapshot_observed_at":"2026-08-14T03:56:10.020328Z","submitted_at":"2025-08-28T17:44:52Z","title":"FW-GAN: Frequency-Driven Handwriting Synthesis with Wave-Modulated MLP Generator","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-05T14:41:43.820076Z"},"links":{"cited_paper":"/paper/2105.01601","citing_paper":"/paper/2508.21040"},"observation_digest":"sha256:0c0637e7f6ed41e67af94b2f5ef5054bbec20bfdc708c42f081a66d9ab09cb0a","observation_id":"64edded1-bd3c-49d7-bdd3-84dc1a0354dd","resolution":{"observed_at":"2026-08-05T14:41:43.820076Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.01601","last_updated":"2021-06-11T09:36:50Z","snapshot_observed_at":"2026-08-20T13:50:07.095032Z","submitted_at":"2021-05-04T16:17:21Z","title":"MLP-Mixer: An all-MLP Architecture for Vision","version":4},"cited_work":{"arxiv_id":"2105.01601","doi":"10.48550/arxiv.2105.01601","metadata_source":"pith","pith_arxiv_id":"2105.01601","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"CoRR, abs/2105.01601","venue":"cs.CV","work_id":"30cb7db2-723e-4ee0-9a0c-e83aa9a83061","year":2021},"citing_paper":{"arxiv_id":"2604.20934","last_updated":"2026-04-22T11:52:43Z","snapshot_observed_at":"2026-07-06T23:07:36.996629Z","submitted_at":"2026-04-22T11:52:43Z","title":"SDNGuardStack: An Explainable Ensemble Learning Framework for High-Accuracy Intrusion Detection in Software-Defined Networks","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-10T00:13:15.180285Z"},"links":{"cited_paper":"/paper/2105.01601","citing_paper":"/paper/2604.20934"},"observation_digest":"sha256:a6c79c948472cc109e9172106def26a65e5c04a8c0db2757d3eb6413177c6066","observation_id":"ce65e83b-2686-4df4-b7ee-c9e96e3c4a8d","resolution":{"observed_at":"2026-05-10T00:14:46.480950Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2105.01601","last_updated":"2021-06-11T09:36:50Z","snapshot_observed_at":"2026-08-20T13:50:07.095032Z","submitted_at":"2021-05-04T16:17:21Z","title":"MLP-Mixer: An all-MLP Architecture for Vision","version":4},"cited_work":{"arxiv_id":"2105.01601","doi":"10.48550/arxiv.2105.01601","metadata_source":"pith","pith_arxiv_id":"2105.01601","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"CoRR, abs/2105.01601","venue":"cs.CV","work_id":"30cb7db2-723e-4ee0-9a0c-e83aa9a83061","year":2021},"citing_paper":{"arxiv_id":"2605.06683","last_updated":"2026-04-24T20:37:21Z","snapshot_observed_at":"2026-08-13T08:20:06.063888Z","submitted_at":"2026-04-24T20:37:21Z","title":"Toeplitz MLP Mixers are Low Complexity, Information-Rich Sequence Models","version":1},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-05-11T01:07:33.756985Z"},"links":{"cited_paper":"/paper/2105.01601","citing_paper":"/paper/2605.06683"},"observation_digest":"sha256:21bbf56e0df34874a71a103042fe3c387eae426964022b1c6c7b3e0b2cef1e66","observation_id":"0ede220e-7df3-4f68-a3ed-135e7f591143","resolution":{"observed_at":"2026-05-11T04:45:56.262520Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2105.01601","last_updated":"2021-06-11T09:36:50Z","snapshot_observed_at":"2026-08-20T13:50:07.095032Z","submitted_at":"2021-05-04T16:17:21Z","title":"MLP-Mixer: An all-MLP Architecture for Vision","version":4},"cited_work":{"arxiv_id":"2105.01601","doi":"10.48550/arxiv.2105.01601","metadata_source":"pith","pith_arxiv_id":"2105.01601","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"CoRR, abs/2105.01601","venue":"cs.CV","work_id":"30cb7db2-723e-4ee0-9a0c-e83aa9a83061","year":2021},"citing_paper":{"arxiv_id":"2605.08168","last_updated":"2026-05-04T18:01:15Z","snapshot_observed_at":"2026-08-11T08:33:06.194053Z","submitted_at":"2026-05-04T18:01:15Z","title":"Understanding Asynchronous Inference Methods for Vision-Language-Action Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-12T01:44:13.931529Z"},"links":{"cited_paper":"/paper/2105.01601","citing_paper":"/paper/2605.08168"},"observation_digest":"sha256:2df77e2e17df55ed6846607436af1c9cec3d4c9ccec04436d9e0724a0a939c48","observation_id":"70ed285c-a411-4d90-8934-145363dd5746","resolution":{"observed_at":"2026-05-12T01:46:13.801618Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2105.01601","last_updated":"2021-06-11T09:36:50Z","snapshot_observed_at":"2026-08-20T13:50:07.095032Z","submitted_at":"2021-05-04T16:17:21Z","title":"MLP-Mixer: An all-MLP Architecture for Vision","version":4},"cited_work":{"arxiv_id":"2105.01601","doi":"10.48550/arxiv.2105.01601","metadata_source":"pith","pith_arxiv_id":"2105.01601","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"CoRR, abs/2105.01601","venue":"cs.CV","work_id":"30cb7db2-723e-4ee0-9a0c-e83aa9a83061","year":2021},"citing_paper":{"arxiv_id":"2606.19329","last_updated":"2026-06-17T17:54:52Z","snapshot_observed_at":"2026-08-03T08:49:27.118171Z","submitted_at":"2026-06-17T17:54:52Z","title":"The Chandra-Gaia Catalog of Counterparts: Resolving ambiguous Gaia matches to X-ray sources in the Chandra Source Catalog using Machine Learning","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-06-26T18:55:03.636902Z"},"links":{"cited_paper":"/paper/2105.01601","citing_paper":"/paper/2606.19329"},"observation_digest":"sha256:5aed11ef779ebb565e898b8b08cc6e72ce50c4b38c14051c65f7bd3281757fe1","observation_id":"3446ebc4-7b4c-4587-b6be-88d0ec3d18b2","resolution":{"observed_at":"2026-06-26T18:59:43.602552Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2105.01601","last_updated":"2021-06-11T09:36:50Z","snapshot_observed_at":"2026-08-20T13:50:07.095032Z","submitted_at":"2021-05-04T16:17:21Z","title":"MLP-Mixer: An all-MLP Architecture for Vision","version":4},"cited_work":{"arxiv_id":"2105.01601","doi":"10.48550/arxiv.2105.01601","metadata_source":"pith","pith_arxiv_id":"2105.01601","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"CoRR, abs/2105.01601","venue":"cs.CV","work_id":"30cb7db2-723e-4ee0-9a0c-e83aa9a83061","year":2021},"citing_paper":{"arxiv_id":"2606.25010","last_updated":"2026-06-23T17:51:10Z","snapshot_observed_at":"2026-08-13T11:45:58.173978Z","submitted_at":"2026-06-23T17:51:10Z","title":"Emergent Capabilities Arise Randomly from Learning Sparse Attention Patterns","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-06-25T23:43:20.900414Z"},"links":{"cited_paper":"/paper/2105.01601","citing_paper":"/paper/2606.25010"},"observation_digest":"sha256:87f19cd2c9c646f96047ac0352b121d0cc7cf73aa69481852bff5222601ad86f","observation_id":"dee163ee-d986-46a2-b822-f3a172581466","resolution":{"observed_at":"2026-07-04T17:29:59.843603Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2105.01601","last_updated":"2021-06-11T09:36:50Z","snapshot_observed_at":"2026-08-20T13:50:07.095032Z","submitted_at":"2021-05-04T16:17:21Z","title":"MLP-Mixer: An all-MLP Architecture for Vision","version":4},"cited_work":{"arxiv_id":"2105.01601","doi":"10.48550/arxiv.2105.01601","metadata_source":"pith","pith_arxiv_id":"2105.01601","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"CoRR, abs/2105.01601","venue":"cs.CV","work_id":"30cb7db2-723e-4ee0-9a0c-e83aa9a83061","year":2021},"citing_paper":{"arxiv_id":"2606.28529","last_updated":"2026-06-30T06:26:23Z","snapshot_observed_at":"2026-07-07T00:02:38.226622Z","submitted_at":"2026-06-26T18:28:52Z","title":"The Speedup Paradox: Rethinking Inference Speed-Quality Trade-off in Embodied Tasks","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-06-30T01:10:12.636354Z"},"links":{"cited_paper":"/paper/2105.01601","citing_paper":"/paper/2606.28529"},"observation_digest":"sha256:6324a35a4faaa1fdb7cc9283fb6e7577564ca6128a0b5d124556a6092cd4f345","observation_id":"64b51f20-1ebf-4d50-8fde-ae58f86f0d72","resolution":{"observed_at":"2026-07-01T15:45:48.384837Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2105.01601","last_updated":"2021-06-11T09:36:50Z","snapshot_observed_at":"2026-08-20T13:50:07.095032Z","submitted_at":"2021-05-04T16:17:21Z","title":"MLP-Mixer: An all-MLP Architecture for Vision","version":4},"cited_work":{"arxiv_id":"2105.01601","doi":"10.48550/arxiv.2105.01601","metadata_source":"pith","pith_arxiv_id":"2105.01601","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"CoRR, abs/2105.01601","venue":"cs.CV","work_id":"30cb7db2-723e-4ee0-9a0c-e83aa9a83061","year":2021},"citing_paper":{"arxiv_id":"2606.28529","last_updated":"2026-06-30T06:26:23Z","snapshot_observed_at":"2026-07-07T00:02:38.226622Z","submitted_at":"2026-06-26T18:28:52Z","title":"The Speedup Paradox: Rethinking Inference Speed-Quality Trade-off in Embodied Tasks","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-07-01T06:27:54.229184Z"},"links":{"cited_paper":"/paper/2105.01601","citing_paper":"/paper/2606.28529"},"observation_digest":"sha256:0f53d32f953c6ebf60ee7c5bbe86ff2f1e5b0eea9c1add28f8fd9e86433090c7","observation_id":"65d79a19-00dc-4f3d-8067-70480e2b0d25","resolution":{"observed_at":"2026-07-01T09:35:40.089589Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2105.01601","last_updated":"2021-06-11T09:36:50Z","snapshot_observed_at":"2026-08-20T13:50:07.095032Z","submitted_at":"2021-05-04T16:17:21Z","title":"MLP-Mixer: An all-MLP Architecture for Vision","version":4},"cited_work":{"arxiv_id":"2105.01601","doi":"10.48550/arxiv.2105.01601","metadata_source":"pith","pith_arxiv_id":"2105.01601","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"CoRR, abs/2105.01601","venue":"cs.CV","work_id":"30cb7db2-723e-4ee0-9a0c-e83aa9a83061","year":2021},"citing_paper":{"arxiv_id":"2607.08175","last_updated":"2026-07-09T07:21:11Z","snapshot_observed_at":"2026-08-18T07:54:33.547854Z","submitted_at":"2026-07-09T07:21:11Z","title":"Transformer-based machine learning using low-level calorimeter signals for collimated photon identification at collider experiments","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-07-10T11:52:41.218796Z"},"links":{"cited_paper":"/paper/2105.01601","citing_paper":"/paper/2607.08175"},"observation_digest":"sha256:98243b46409626b56ca466bf6556ff9aa24cc38feaf9cbcd94750806db20c2a9","observation_id":"efe04ea0-27e4-4299-b4e3-7036eae6b03b","resolution":{"observed_at":"2026-07-10T11:57:03.319850Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2105.01601","last_updated":"2021-06-11T09:36:50Z","snapshot_observed_at":"2026-08-20T13:50:07.095032Z","submitted_at":"2021-05-04T16:17:21Z","title":"MLP-Mixer: An all-MLP Architecture for Vision","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.01601","snapshot_observed_at":"2026-08-01T06:46:58.439106Z","title":"URL https://arxiv.org/abs/2105.01601","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.27501","last_updated":"2026-07-29T22:35:13Z","snapshot_observed_at":"2026-08-19T22:51:27.862088Z","submitted_at":"2026-07-29T22:35:13Z","title":"A Lightweight Foundation Model for Collider Physics with Multi-Domain Adaptation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T06:46:58.439106Z"},"links":{"cited_paper":"/paper/2105.01601","citing_paper":"/paper/2607.27501"},"observation_digest":"sha256:5640ffd068b2a0d6ad3b785a70847ba76614de5804b6e9c61c6b8e694e0538fb","observation_id":"dc51db23-523f-4cc2-ac72-2ef627b9917f","resolution":{"observed_at":"2026-08-01T06:46:58.439106Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.01601","last_updated":"2021-06-11T09:36:50Z","snapshot_observed_at":"2026-08-20T13:50:07.095032Z","submitted_at":"2021-05-04T16:17:21Z","title":"MLP-Mixer: An all-MLP Architecture for Vision","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.01601","snapshot_observed_at":"2026-08-03T16:12:10.026048Z","title":"MLP-Mixer: An all-mlp architecture for vision,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.28978","last_updated":"2026-07-31T03:06:07Z","snapshot_observed_at":"2026-08-18T04:50:41.830932Z","submitted_at":"2026-07-31T03:06:07Z","title":"Classification of COVID-19 cases from chest CT volumes using hybrid model of 3D CNN and 3D MLP-Mixer","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-03T16:12:10.026048Z"},"links":{"cited_paper":"/paper/2105.01601","citing_paper":"/paper/2607.28978"},"observation_digest":"sha256:624b5d145af207c5e9f0b08930e6e0fffe067c9998ddaae6da76071bcbd0cfd2","observation_id":"564e44f8-64bf-498c-9061-3d99d7112d25","resolution":{"observed_at":"2026-08-03T16:12:10.026048Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.01601","last_updated":"2021-06-11T09:36:50Z","snapshot_observed_at":"2026-08-20T13:50:07.095032Z","submitted_at":"2021-05-04T16:17:21Z","title":"MLP-Mixer: An all-MLP Architecture for Vision","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.01601","snapshot_observed_at":"2026-08-14T10:39:58.871054Z","title":"et al.: MLP-Mixer: An all-MLP Architecture for Vision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.13455","last_updated":"2026-08-13T16:40:26Z","snapshot_observed_at":"2026-08-16T23:12:59.111777Z","submitted_at":"2026-08-13T16:40:26Z","title":"Evaluation of Clinically Steerable Retinal Image Generation from Foundation Model Latent Spaces","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T10:39:58.871054Z"},"links":{"cited_paper":"/paper/2105.01601","citing_paper":"/paper/2608.13455"},"observation_digest":"sha256:3b2d2d9db1768ebd5876fbf5980fb58658ae7edfb4b371268aa5bd58e12041f0","observation_id":"51df6c22-dd1b-43ca-bb17-dd707ba67634","resolution":{"observed_at":"2026-08-14T10:39:58.871054Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2105.01601/citation-record","integrity":"/paper/2105.01601/integrity","json":"/paper/2105.01601/citation-record.json","paper":"/paper/2105.01601"},"outbound":[],"paper":{"arxiv_id":"2105.01601","last_updated":"2021-06-11T09:36:50Z","latest_version":4,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-20T13:50:07.095032Z","submitted_at":"2021-05-04T16:17:21Z","title":"MLP-Mixer: An all-MLP Architecture for Vision"},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 26 inbound Pith citation observations for arXiv:2105.01601."}