{"as_of":"2026-08-06T07:55:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4a6eb238b98ac641c58973a8088b49c4879f66b414793b21ef89581a2599e61e","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":"2026-08-06T06:34:29.942622+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":"2026-05-15T15:05:37.964883Z","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":"2026-05-15T15:06:09.620251Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2112.01194","last_updated":"2021-12-06T07:25:35Z","snapshot_observed_at":"2026-07-06T12:14:35.762605Z","submitted_at":"2021-12-02T13:06:53Z","title":"Video-Text Pre-training with Learned Regions","version":2},"cited_work":{"arxiv_id":"2112.01194","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2112.01194","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2112.01194 (2021)","venue":null,"work_id":"6eb18348-c24a-4712-bd9a-239b0e607e89","year":2021},"citing_paper":{"arxiv_id":"2605.00826","last_updated":"2026-03-07T12:28:35Z","snapshot_observed_at":"2026-07-06T23:14:11.211164Z","submitted_at":"2026-03-07T12:28:35Z","title":"Understanding the Performance Plateau in Text-to-Video Retrieval: A Comprehensive Empirical and Linguistic Analysis","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-05-15T15:05:37.964883Z"},"links":{"cited_paper":"/paper/2112.01194","citing_paper":"/paper/2605.00826"},"observation_digest":"sha256:b38bdd0f46222b87b8966eba7ce994ba0e798e472eb2190e84391fdd4c11d08c","observation_id":"ef07c0c5-b112-4734-af06-617e070298d7","resolution":{"observed_at":"2026-05-15T15:06:09.623105Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2112.01194/citation-record","integrity":"/paper/2112.01194/integrity","json":"/paper/2112.01194/citation-record.json","paper":"/paper/2112.01194"},"outbound":[],"paper":{"arxiv_id":"2112.01194","last_updated":"2021-12-06T07:25:35Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T12:14:35.762605Z","submitted_at":"2021-12-02T13:06:53Z","title":"Video-Text Pre-training with Learned Regions"},"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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 6 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2112.01194."}