{"as_of":"2026-08-07T18:01:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5e5c0ae9f939eba7672edd74bc06febea2b645a94bd9ec2edb16618dfdba696a","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T21:41:51.372359Z","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":"2026-08-06T15:33:51.653731Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2411.16156","last_updated":"2025-03-18T08:15:28Z","snapshot_observed_at":"2026-07-06T19:56:21.333277Z","submitted_at":"2024-11-25T07:32:02Z","title":"VideoOrion: Tokenizing Object Dynamics in Videos","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.16156","snapshot_observed_at":"2026-08-06T21:41:51.372359Z","title":"Videoorion: Tokenizing object dynamics in videos.arXiv preprint arXiv:2411.16156, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.23639","last_updated":"2025-06-30T09:08:08Z","snapshot_observed_at":"2026-08-06T21:33:31.518732Z","submitted_at":"2025-06-30T09:08:08Z","title":"Unified Multimodal Understanding via Byte-Pair Visual Encoding","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T21:41:51.372359Z"},"links":{"cited_paper":"/paper/2411.16156","citing_paper":"/paper/2506.23639"},"observation_digest":"sha256:fa1830c5ae24079448969089b70128bb016f45c08640fc318f3ab7556ae25e81","observation_id":"a2c3ae77-95fe-4fe4-a46a-9825521193aa","resolution":{"observed_at":"2026-08-06T21:41:51.372359Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.16156","last_updated":"2025-03-18T08:15:28Z","snapshot_observed_at":"2026-07-06T19:56:21.333277Z","submitted_at":"2024-11-25T07:32:02Z","title":"VideoOrion: Tokenizing Object Dynamics in Videos","version":2},"cited_work":{"arxiv_id":"2411.16156","doi":null,"metadata_source":"pith","pith_arxiv_id":"2411.16156","snapshot_observed_at":"2026-08-06T15:33:51.653731Z","title":"VideoOrion: Tokenizing Object Dynamics in Videos","venue":"cs.CV","work_id":"3a2b9abd-e110-4484-bac3-2c95c835e65a","year":2024},"citing_paper":{"arxiv_id":"2507.15597","last_updated":"2025-07-21T13:19:09Z","snapshot_observed_at":"2026-08-06T15:25:42.125132Z","submitted_at":"2025-07-21T13:19:09Z","title":"Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T15:33:42.245773Z"},"links":{"cited_paper":"/paper/2411.16156","citing_paper":"/paper/2507.15597"},"observation_digest":"sha256:587379d7ed31c19e95bc7013b9886f52326e640a969958348bb7874873d00d85","observation_id":"dc1b8b98-c779-4bba-ba14-eacaaf7e8583","resolution":{"observed_at":"2026-08-06T15:33:51.694013Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2411.16156/citation-record","integrity":"/paper/2411.16156/integrity","json":"/paper/2411.16156/citation-record.json","paper":"/paper/2411.16156"},"outbound":[],"paper":{"arxiv_id":"2411.16156","last_updated":"2025-03-18T08:15:28Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T19:56:21.333277Z","submitted_at":"2024-11-25T07:32:02Z","title":"VideoOrion: Tokenizing Object Dynamics in Videos"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2411.16156."}