{"as_of":"2026-08-17T20:14:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d409bea5db00862e20ca883249a544d974a17be2b06af777470b1e9acbaa599f","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":"2026-08-17T06:30:58.91139+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":"2026-08-16T06:01:23.242223Z","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":"2026-08-16T06:01:23.562791Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2010.06775","last_updated":"2020-10-14T02:11:51Z","snapshot_observed_at":"2026-08-17T08:01:03.104669Z","submitted_at":"2020-10-14T02:11:51Z","title":"Vokenization: Improving Language Understanding with Contextualized, Visual-Grounded Supervision","version":1},"cited_work":{"arxiv_id":"2010.06775","doi":null,"metadata_source":"pith","pith_arxiv_id":"2010.06775","snapshot_observed_at":"2026-08-16T06:01:23.562791Z","title":"Vokenization: Improving Language Understanding with Contextualized, Visual-Grounded Supervision","venue":"cs.CL","work_id":"ad1b57db-74a6-423b-bec9-ff9a133c1190","year":2020},"citing_paper":{"arxiv_id":"2504.19267","last_updated":"2025-06-10T12:19:13Z","snapshot_observed_at":"2026-08-17T19:52:19.059318Z","submitted_at":"2025-04-27T14:55:51Z","title":"VIST-GPT: Ushering in the Era of Visual Storytelling with LLMs?","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-16T06:01:23.242223Z"},"links":{"cited_paper":"/paper/2010.06775","citing_paper":"/paper/2504.19267"},"observation_digest":"sha256:f6d38a3649b28a9d986d88d778d72ae501a89b3131b994ec35483e42c3314254","observation_id":"818e9292-15ac-4b03-8570-65409f501950","resolution":{"observed_at":"2026-08-16T06:01:23.567815Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2010.06775/citation-record","integrity":"/paper/2010.06775/integrity","json":"/paper/2010.06775/citation-record.json","paper":"/paper/2010.06775"},"outbound":[],"paper":{"arxiv_id":"2010.06775","last_updated":"2020-10-14T02:11:51Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-17T08:01:03.104669Z","submitted_at":"2020-10-14T02:11:51Z","title":"Vokenization: Improving Language Understanding with Contextualized, Visual-Grounded 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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2010.06775."}