{"as_of":"2026-08-06T19:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:64e0e5b67db50df42960d88df9a10e48a49e37d4b15dde0f67c87344055c347d","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":"2026-05-16T20:54:07.572136Z","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":"2026-05-16T20:54:07.639214Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2006.00753","last_updated":"2021-11-26T03:00:58Z","snapshot_observed_at":"2026-07-06T09:24:54.881719Z","submitted_at":"2020-06-01T07:07:36Z","title":"Structured Multimodal Attentions for TextVQA","version":2},"cited_work":{"arxiv_id":"2006.00753","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2006.00753","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Structured multimodal attentions for textvqa.arXiv preprint arXiv:2006.00753","venue":null,"work_id":"9cbf358d-e04a-45ae-aecd-55307aabda66","year":2006},"citing_paper":{"arxiv_id":"2205.14100","last_updated":"2022-12-15T19:21:35Z","snapshot_observed_at":"2026-08-04T09:31:34.784365Z","submitted_at":"2022-05-27T17:03:38Z","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","version":5},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-16T20:54:07.572136Z"},"links":{"cited_paper":"/paper/2006.00753","citing_paper":"/paper/2205.14100"},"observation_digest":"sha256:947cb2d87cd6c40fd12ab7952f2ad62498fbc88d3c19ccf1d97d299e98b402d5","observation_id":"7943f364-00cd-4373-8951-6ab8ea3cb0f3","resolution":{"observed_at":"2026-05-16T20:54:07.641724Z","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/2006.00753/citation-record","integrity":"/paper/2006.00753/integrity","json":"/paper/2006.00753/citation-record.json","paper":"/paper/2006.00753"},"outbound":[],"paper":{"arxiv_id":"2006.00753","last_updated":"2021-11-26T03:00:58Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T09:24:54.881719Z","submitted_at":"2020-06-01T07:07:36Z","title":"Structured Multimodal Attentions for TextVQA"},"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:2006.00753."}