{"as_of":"2026-08-12T05:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1631224bd815b7927205d558bde3643dc00298626200c096670afacd3fea023a","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":1,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":1,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+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":"2026-05-15T06:30:22.431538Z","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":"2026-05-15T06:30:22.652994Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2007.14937","last_updated":"2021-08-27T18:03:37Z","snapshot_observed_at":"2026-08-08T04:19:05.063098Z","submitted_at":"2020-07-29T16:19:50Z","title":"Learning Video Representations from Textual Web Supervision","version":2},"cited_work":{"arxiv_id":"2007.14937","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2007.14937","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learning video representations from textual web supervision","venue":null,"work_id":"a7681afd-d28e-4239-b3df-294ee949469f","year":2007},"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":51,"source":"pdf_text","source_observed_at":"2026-05-15T06:30:22.431538Z"},"links":{"cited_paper":"/paper/2007.14937","citing_paper":"/paper/2307.06942"},"observation_digest":"sha256:a1f391521fb9138622f1735628317adc845f49f63901bdb82ab89da178381e0e","observation_id":"38a704ec-a40f-4f74-a192-1bc11d1d17ec","resolution":{"observed_at":"2026-05-15T06:30:22.656697Z","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/2007.14937/citation-record","integrity":"/paper/2007.14937/integrity","json":"/paper/2007.14937/citation-record.json","paper":"/paper/2007.14937"},"outbound":[],"paper":{"arxiv_id":"2007.14937","last_updated":"2021-08-27T18:03:37Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-08T04:19:05.063098Z","submitted_at":"2020-07-29T16:19:50Z","title":"Learning Video Representations from Textual Web Supervision"},"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 1 inbound Pith citation observation for arXiv:2007.14937."}