{"as_of":"2026-08-06T01:01:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:afc1ad18f5e0b88d143683e4b140d5c76fd76feeaf8fb3035812e12acfa0806b","coverage":[{"denominator":2,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-10T15:45:02.848369Z","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":"2026-08-05T06:32:48.257954+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-27T17:02:00.653422Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-07-03T00:47:30.426505Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2604.12887","last_updated":"2026-04-14T15:37:30Z","snapshot_observed_at":"2026-07-06T23:01:00.830207Z","submitted_at":"2026-04-14T15:37:30Z","title":"VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization","version":1},"cited_work":{"arxiv_id":"2604.12887","doi":null,"metadata_source":"pith","pith_arxiv_id":"2604.12887","snapshot_observed_at":"2026-07-03T00:47:30.426505Z","title":"VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization","venue":"cs.CV","work_id":"8bcf2f0a-8ea6-4b9d-8950-dc090f845ead","year":2026},"citing_paper":{"arxiv_id":"2606.09056","last_updated":"2026-06-08T05:46:01Z","snapshot_observed_at":"2026-07-06T23:48:26.076260Z","submitted_at":"2026-06-08T05:46:01Z","title":"MilliVid: Hierarchical Latents for Long-Range Consistency in Video Generation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-06-27T17:02:00.653422Z"},"links":{"cited_paper":"/paper/2604.12887","citing_paper":"/paper/2606.09056"},"observation_digest":"sha256:3c6f846a6a4430825b176906a1a81e3b03c0ebd8f9d606bb5aa4eba9fa77dcd7","observation_id":"074c408d-0a55-4863-96bd-d87011695396","resolution":{"observed_at":"2026-07-03T00:47:30.428152Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2604.12887/citation-record","integrity":"/paper/2604.12887/integrity","json":"/paper/2604.12887/citation-record.json","paper":"/paper/2604.12887"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2304.07193","last_updated":"2024-02-02T10:24:09Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-04-14T15:12:19Z","title":"DINOv2: Learning Robust Visual Features without Supervision","version":2},"cited_work":{"arxiv_id":"2304.07193","doi":"10.48550/arxiv.2304.07193","metadata_source":"pith","pith_arxiv_id":"2304.07193","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"DINOv2: Learning Robust Visual Features without Supervision","venue":"cs.CV","work_id":"26b304e5-b54a-4f26-be7e-83299eca52e4","year":2023},"citing_paper":{"arxiv_id":"2604.12887","last_updated":"2026-04-14T15:37:30Z","snapshot_observed_at":"2026-07-06T23:01:00.830207Z","submitted_at":"2026-04-14T15:37:30Z","title":"VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-10T15:45:02.848369Z"},"links":{"cited_paper":"/paper/2304.07193","citing_paper":"/paper/2604.12887"},"observation_digest":"sha256:de7afed8b5d140e7e6fb160cea20b6e7910cd06479d8a3166e2f94cdee3206be","observation_id":"2f928ea8-fd36-4197-9698-c4ba073f6a51","resolution":{"observed_at":"2026-05-11T09:56:01.919530Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2800.0206","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"d87e1ffb-fc1c-4d1c-ba94-18ea3eeec332","year":2025},"citing_paper":{"arxiv_id":"2604.12887","last_updated":"2026-04-14T15:37:30Z","snapshot_observed_at":"2026-07-06T23:01:00.830207Z","submitted_at":"2026-04-14T15:37:30Z","title":"VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-10T15:45:02.848369Z"},"links":{"citing_paper":"/paper/2604.12887"},"observation_digest":"sha256:caaa7ef369fab76a68a20b623c89eb93654150cee99246f3918b58eaa59b1382","observation_id":"c3b88d40-c09c-4e34-8a75-229a6a0aa527","resolution":{"observed_at":"2026-05-11T09:56:01.931585Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2604.12887","last_updated":"2026-04-14T15:37:30Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T23:01:00.830207Z","submitted_at":"2026-04-14T15:37:30Z","title":"VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization"},"reference_resolution":{"displayed":2,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":0,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":2},"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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 6 August 2026, this Paper Citation Record lists 2 of 2 outbound references and 1 inbound Pith citation observation for arXiv:2604.12887."}