{"as_of":"2026-08-08T09:13:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:09254889b3b5d3083f50aa1b7923726363faef0e264cc6f2bc559e12e4150131","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":"2026-08-08T06:32:00.761636+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":"2026-05-17T03:27:58.952076Z","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":"2026-05-17T03:27:59.168417Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2305.14173","last_updated":"2023-05-23T15:44:56Z","snapshot_observed_at":"2026-07-06T15:31:36.425535Z","submitted_at":"2023-05-23T15:44:56Z","title":"TVTSv2: Learning Out-of-the-box Spatiotemporal Visual Representations at Scale","version":1},"cited_work":{"arxiv_id":"2305.14173","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2305.14173","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2305.14173 , year=","venue":null,"work_id":"7e82492b-c85e-49a6-924e-fce29eb6293f","year":2023},"citing_paper":{"arxiv_id":"2307.06942","last_updated":"2024-01-04T05:00:34Z","snapshot_observed_at":"2026-07-06T15:53:46.393481Z","submitted_at":"2023-07-13T17:58:32Z","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-15T06:30:22.431538Z"},"links":{"cited_paper":"/paper/2305.14173","citing_paper":"/paper/2307.06942"},"observation_digest":"sha256:25314b704ebb0eb5e2fa0fbf5d146ea721b4563c5ef73a9dd2040dd48c8992f5","observation_id":"3d770f5c-d9a9-4c27-9943-6e07d6fa0a35","resolution":{"observed_at":"2026-05-15T06:30:22.594600Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.14173","last_updated":"2023-05-23T15:44:56Z","snapshot_observed_at":"2026-07-06T15:31:36.425535Z","submitted_at":"2023-05-23T15:44:56Z","title":"TVTSv2: Learning Out-of-the-box Spatiotemporal Visual Representations at Scale","version":1},"cited_work":{"arxiv_id":"2305.14173","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2305.14173","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2305.14173 , year=","venue":null,"work_id":"7e82492b-c85e-49a6-924e-fce29eb6293f","year":2023},"citing_paper":{"arxiv_id":"2310.01852","last_updated":"2024-01-22T03:11:15Z","snapshot_observed_at":"2026-08-07T05:10:33.059352Z","submitted_at":"2023-10-03T07:33:27Z","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","version":7},"reference_index":217,"source":"arxiv_source","source_observed_at":"2026-05-17T03:27:58.952076Z"},"links":{"cited_paper":"/paper/2305.14173","citing_paper":"/paper/2310.01852"},"observation_digest":"sha256:89fefd156bb82b640e4fe0a7ce83c9d9e7e371c38711f25891037c22cfb60f07","observation_id":"ad65510c-2878-4d29-936c-e57cc01d6721","resolution":{"observed_at":"2026-05-17T03:27:59.171293Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2305.14173/citation-record","integrity":"/paper/2305.14173/integrity","json":"/paper/2305.14173/citation-record.json","paper":"/paper/2305.14173"},"outbound":[],"paper":{"arxiv_id":"2305.14173","last_updated":"2023-05-23T15:44:56Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T15:31:36.425535Z","submitted_at":"2023-05-23T15:44:56Z","title":"TVTSv2: Learning Out-of-the-box Spatiotemporal Visual Representations at Scale"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2305.14173."}