{"as_of":"2026-08-19T21:05:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1711bd45cf214a3e99460266318c256455482a92bd7d54d4f4a1afba79faf5b1","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":"2026-08-19T06:32:44.657259+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":"2026-08-15T21:41:18.953335Z","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":"2026-05-21T05:09:38.779237Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2101.11986","last_updated":"2021-11-30T12:30:01Z","snapshot_observed_at":"2026-08-19T16:23:59.139526Z","submitted_at":"2021-01-28T13:25:28Z","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","version":3},"cited_work":{"arxiv_id":"2101.11986","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2101.11986","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Tokens- to-token vit: Training vision transformers from scratch on imagenet","venue":null,"work_id":"89fa0521-fcf1-47a7-acc2-b8c0360b0b5e","year":2021},"citing_paper":{"arxiv_id":"2103.14030","last_updated":"2021-08-17T16:41:34Z","snapshot_observed_at":"2026-08-13T19:24:14.214828Z","submitted_at":"2021-03-25T17:59:31Z","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","version":2},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-05-15T19:27:56.785857Z"},"links":{"cited_paper":"/paper/2101.11986","citing_paper":"/paper/2103.14030"},"observation_digest":"sha256:c5ff0944ef93c4b584a82c6b116aa887c11471933a554b715337101602bfed29","observation_id":"218f96ad-106e-4865-a80e-b36e26a2955c","resolution":{"observed_at":"2026-05-15T19:27:56.864167Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2101.11986","last_updated":"2021-11-30T12:30:01Z","snapshot_observed_at":"2026-08-19T16:23:59.139526Z","submitted_at":"2021-01-28T13:25:28Z","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.11986","snapshot_observed_at":"2026-08-15T21:41:18.953335Z","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.09168","last_updated":"2025-05-14T06:03:53Z","snapshot_observed_at":"2026-08-17T12:53:39.894742Z","submitted_at":"2025-05-14T06:03:53Z","title":"DRRNet: Macro-Micro Feature Fusion and Dual Reverse Refinement for Camouflaged Object Detection","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T21:41:18.953335Z"},"links":{"cited_paper":"/paper/2101.11986","citing_paper":"/paper/2505.09168"},"observation_digest":"sha256:18cc7d13f19ab49d32ba738365ba7fe0a08d7232d260019aeabcb2fdc2e8988c","observation_id":"47d3589c-2079-428c-a30d-e7b82a390d01","resolution":{"observed_at":"2026-08-15T21:41:18.953335Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.11986","last_updated":"2021-11-30T12:30:01Z","snapshot_observed_at":"2026-08-19T16:23:59.139526Z","submitted_at":"2021-01-28T13:25:28Z","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","version":3},"cited_work":{"arxiv_id":"2101.11986","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2101.11986","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Tokens- to-token vit: Training vision transformers from scratch on imagenet","venue":null,"work_id":"89fa0521-fcf1-47a7-acc2-b8c0360b0b5e","year":2021},"citing_paper":{"arxiv_id":"2605.20732","last_updated":"2026-05-20T05:35:45Z","snapshot_observed_at":"2026-08-15T17:09:09.655327Z","submitted_at":"2026-05-20T05:35:45Z","title":"Deep Attention Reweighting: Post-Hoc Attention-Based Feature Aggregation in CNNs for Disentangling Core and Spurious Features under Spurious Correlations","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-05-21T05:04:59.177437Z"},"links":{"cited_paper":"/paper/2101.11986","citing_paper":"/paper/2605.20732"},"observation_digest":"sha256:ab23f70e31cf24b8896275b34fd44e500b6d0acea57796bffc81256c6bce114c","observation_id":"a693005f-2040-484f-9e6b-e44f16f35afe","resolution":{"observed_at":"2026-05-21T05:09:38.781237Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2101.11986/citation-record","integrity":"/paper/2101.11986/integrity","json":"/paper/2101.11986/citation-record.json","paper":"/paper/2101.11986"},"outbound":[],"paper":{"arxiv_id":"2101.11986","last_updated":"2021-11-30T12:30:01Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-19T16:23:59.139526Z","submitted_at":"2021-01-28T13:25:28Z","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet"},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2101.11986."}