{"as_of":"2026-08-12T04:54:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7db718ea7944453fcc7167b354b062432c84637e902705750dd30e8310cac873","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T12:44:18.700607Z","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":"2026-05-11T01:40:52.062182Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2401.02957","last_updated":"2024-07-22T09:07:27Z","snapshot_observed_at":"2026-08-10T19:06:52.473039Z","submitted_at":"2024-01-05T18:59:52Z","title":"Denoising Vision Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.02957","snapshot_observed_at":"2026-08-11T12:44:18.700607Z","title":"De- noising vision transformers,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.13916","last_updated":"2024-12-18T14:56:03Z","snapshot_observed_at":"2026-08-11T12:37:35.451412Z","submitted_at":"2024-12-18T14:56:03Z","title":"Retrieval Augmented Image Harmonization","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T12:44:18.700607Z"},"links":{"cited_paper":"/paper/2401.02957","citing_paper":"/paper/2412.13916"},"observation_digest":"sha256:c1398f3e7302899be586144837f2ffef4accb60e00a636a170ef327ee9b5d099","observation_id":"aa69e7fb-c00a-4641-b9f4-831a8d05ddce","resolution":{"observed_at":"2026-08-11T12:44:18.700607Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.02957","last_updated":"2024-07-22T09:07:27Z","snapshot_observed_at":"2026-08-10T19:06:52.473039Z","submitted_at":"2024-01-05T18:59:52Z","title":"Denoising Vision Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.02957","snapshot_observed_at":"2026-08-11T12:28:54.658445Z","title":"Denoising vision transformers,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.14145","last_updated":"2024-12-18T18:43:21Z","snapshot_observed_at":"2026-08-11T12:23:56.755925Z","submitted_at":"2024-12-18T18:43:21Z","title":"Incorporating Feature Pyramid Tokenization and Open Vocabulary Semantic Segmentation","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T12:28:54.658445Z"},"links":{"cited_paper":"/paper/2401.02957","citing_paper":"/paper/2412.14145"},"observation_digest":"sha256:c7fc226ca5b7de96066d313397ea81b5de5639bc9f9e16207b4ebb78d05c708e","observation_id":"0f38c679-ce8a-41a5-9dbd-e37c28aced91","resolution":{"observed_at":"2026-08-11T12:28:54.658445Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.02957","last_updated":"2024-07-22T09:07:27Z","snapshot_observed_at":"2026-08-10T19:06:52.473039Z","submitted_at":"2024-01-05T18:59:52Z","title":"Denoising Vision Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.02957","snapshot_observed_at":"2026-08-10T15:06:59.564819Z","title":"Denoising vision transformers,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.14535","last_updated":"2025-01-24T14:41:30Z","snapshot_observed_at":"2026-08-11T13:48:31.664409Z","submitted_at":"2025-01-24T14:41:30Z","title":"Rethinking Encoder-Decoder Flow Through Shared Structures","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T15:06:59.564819Z"},"links":{"cited_paper":"/paper/2401.02957","citing_paper":"/paper/2501.14535"},"observation_digest":"sha256:cfbd4379d993e0ac757886513df1c7b83185e8b2f65a0cf97527b1eb2d5397ea","observation_id":"14cdf7e4-2780-454a-a415-fefcdba6bcf5","resolution":{"observed_at":"2026-08-10T15:06:59.564819Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.02957","last_updated":"2024-07-22T09:07:27Z","snapshot_observed_at":"2026-08-10T19:06:52.473039Z","submitted_at":"2024-01-05T18:59:52Z","title":"Denoising Vision Transformers","version":2},"cited_work":{"arxiv_id":"2401.02957","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2401.02957","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Guibas, Dilip Krishnan, Kilian Q Weinberger, Yonglong Tian, and Yue Wang","venue":null,"work_id":"8c02c00f-1e9a-4962-bad8-8182ccca3f3f","year":2024},"citing_paper":{"arxiv_id":"2605.06809","last_updated":"2026-05-07T18:08:31Z","snapshot_observed_at":"2026-08-03T23:33:44.795399Z","submitted_at":"2026-05-07T18:08:31Z","title":"LookWhen? Fast Video Recognition by Learning When, Where, and What to Compute","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-11T01:36:50.406353Z"},"links":{"cited_paper":"/paper/2401.02957","citing_paper":"/paper/2605.06809"},"observation_digest":"sha256:ad2064181884ed1542fd470b088a2c2b26f5b83956c9df076e6342806ed462cc","observation_id":"f1a8e71a-e0ff-4bc3-8e55-dbab86f0623c","resolution":{"observed_at":"2026-05-11T01:40:52.064300Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2401.02957/citation-record","integrity":"/paper/2401.02957/integrity","json":"/paper/2401.02957/citation-record.json","paper":"/paper/2401.02957"},"outbound":[],"paper":{"arxiv_id":"2401.02957","last_updated":"2024-07-22T09:07:27Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-10T19:06:52.473039Z","submitted_at":"2024-01-05T18:59:52Z","title":"Denoising 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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2401.02957."}