{"as_of":"2026-08-17T17:33:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b54c26cb02905216689bfce5493e9f78cc0861cdbc3ce50952f6fc51553a68ff","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T00:22:07.598422Z","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":"2026-05-11T07:35:58.995229Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2106.02689","last_updated":"2022-03-31T03:20:15Z","snapshot_observed_at":"2026-08-16T23:24:52.536891Z","submitted_at":"2021-06-04T19:57:11Z","title":"RegionViT: Regional-to-Local Attention for Vision Transformers","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.02689","snapshot_observed_at":"2026-08-15T23:26:13.516424Z","title":"RegionViT: Regional -to-local attention for vision transformers,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.04740","last_updated":"2025-05-07T19:13:17Z","snapshot_observed_at":"2026-08-17T15:14:40.590417Z","submitted_at":"2025-05-07T19:13:17Z","title":"Hyb-KAN ViT: Hybrid Kolmogorov-Arnold Networks Augmented Vision Transformer","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T23:26:13.516424Z"},"links":{"cited_paper":"/paper/2106.02689","citing_paper":"/paper/2505.04740"},"observation_digest":"sha256:2e48416149d146c5e3bd1458de18a3e14324481516f69c54c360c64c564ba7b3","observation_id":"a4f82b0c-15cc-41c3-a87f-6af24ce66153","resolution":{"observed_at":"2026-08-15T23:26:13.516424Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.02689","last_updated":"2022-03-31T03:20:15Z","snapshot_observed_at":"2026-08-16T23:24:52.536891Z","submitted_at":"2021-06-04T19:57:11Z","title":"RegionViT: Regional-to-Local Attention for Vision Transformers","version":3},"cited_work":{"arxiv_id":"2106.02689","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2106.02689","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Re- gionvit: Regional-to-local attention for vision transformers","venue":null,"work_id":"3ddbfcb9-c5a9-4253-9ff1-3fc94f606c1c","year":2021},"citing_paper":{"arxiv_id":"2604.07994","last_updated":"2026-04-10T03:37:09Z","snapshot_observed_at":"2026-08-17T14:45:05.894868Z","submitted_at":"2026-04-09T09:02:58Z","title":"SAT: Selective Aggregation Transformer for Image Super-Resolution","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-10T17:05:40.713918Z"},"links":{"cited_paper":"/paper/2106.02689","citing_paper":"/paper/2604.07994"},"observation_digest":"sha256:28181ff2cfe2e5261bf7e6555b41f2a19655a1e3b5f248a165f496bd9a05acba","observation_id":"7e0f7f57-9056-43c5-85d6-b3818937fdb5","resolution":{"observed_at":"2026-05-11T07:35:59.001111Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.02689","last_updated":"2022-03-31T03:20:15Z","snapshot_observed_at":"2026-08-16T23:24:52.536891Z","submitted_at":"2021-06-04T19:57:11Z","title":"RegionViT: Regional-to-Local Attention for Vision Transformers","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.02689","snapshot_observed_at":"2026-08-16T00:22:07.598422Z","title":"doi:10.48550/arXiv.2106.02689 , urldate =","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.12084","last_updated":"2026-08-12T14:07:09Z","snapshot_observed_at":"2026-08-16T00:50:45.268717Z","submitted_at":"2026-08-12T14:07:09Z","title":"NAE: Normalizing AutoEncoder","version":1},"reference_index":77,"source":"arxiv_source","source_observed_at":"2026-08-16T00:22:07.598422Z"},"links":{"cited_paper":"/paper/2106.02689","citing_paper":"/paper/2608.12084"},"observation_digest":"sha256:f28b3546cf56426702ab044c5d02531b93e60ea9cc2dd1614842c37f9af11519","observation_id":"c253ba82-f804-484f-91f1-f7ebd378814c","resolution":{"observed_at":"2026-08-16T00:22:07.598422Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2106.02689/citation-record","integrity":"/paper/2106.02689/integrity","json":"/paper/2106.02689/citation-record.json","paper":"/paper/2106.02689"},"outbound":[],"paper":{"arxiv_id":"2106.02689","last_updated":"2022-03-31T03:20:15Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T23:24:52.536891Z","submitted_at":"2021-06-04T19:57:11Z","title":"RegionViT: Regional-to-Local Attention for Vision Transformers"},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2106.02689."}