{"as_of":"2026-07-23T01:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c9482d3358082391b2f58d2c9a8fa32bc959923277c8fc0a5299c8f158637cb0","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":"2026-07-22T06:31:00.163083+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":"2026-05-16T20:54:07.572136Z","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":"2026-05-16T20:54:07.703327Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2110.05204","last_updated":"2021-10-14T05:05:39Z","snapshot_observed_at":"2026-07-06T11:56:30.963062Z","submitted_at":"2021-10-11T12:13:22Z","title":"CLIP4Caption ++: Multi-CLIP for Video Caption","version":3},"cited_work":{"arxiv_id":"2110.05204","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.05204","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Clip4caption ++: Multi-clip for video caption","venue":null,"work_id":"c1544f9b-e1fd-44e4-b31a-eb83e5b05758","year":null},"citing_paper":{"arxiv_id":"2205.14100","last_updated":"2022-12-15T19:21:35Z","snapshot_observed_at":"2026-07-06T13:14:45.097902Z","submitted_at":"2022-05-27T17:03:38Z","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","version":5},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-16T20:54:07.572136Z"},"links":{"cited_paper":"/paper/2110.05204","citing_paper":"/paper/2205.14100"},"observation_digest":"sha256:7e7966d0f53f92a2a57053e3fe8cdc9540bb136d2ddd5fe501f7020b8249a9bc","observation_id":"e5b0138d-daab-4f9b-8127-db67394b10f1","resolution":{"observed_at":"2026-05-16T20:54:07.705855Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-22T06:31:00.163083+00:00","source":"crossref"},{"observed_at":"2026-07-22T06:30:55.410749+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2110.05204/citation-record","integrity":"/paper/2110.05204/integrity","json":"/paper/2110.05204/citation-record.json","paper":"/paper/2110.05204"},"outbound":[],"paper":{"arxiv_id":"2110.05204","last_updated":"2021-10-14T05:05:39Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T11:56:30.963062Z","submitted_at":"2021-10-11T12:13:22Z","title":"CLIP4Caption ++: Multi-CLIP for Video Caption"},"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":"2026-07-22T06:31:00.163083+00:00","source":"crossref"},{"observed_at":"2026-07-22T06:30:55.410749+00:00","source":"retraction_watch"}],"thesis":"As of 23 July 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2110.05204."}