{"as_of":"2026-08-23T17:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d0826e7d035a819b4c7d247af5c9e8a874625334d8145fbd35949cd41ea1da9b","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T12:40:23.863317Z","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":"2026-08-06T23:49:30.811814Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2011.07735","last_updated":"2020-11-16T05:44:45Z","snapshot_observed_at":"2026-08-22T00:14:08.193544Z","submitted_at":"2020-11-16T05:44:45Z","title":"iPerceive: Applying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.07735","snapshot_observed_at":"2026-08-16T12:40:23.863317Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.12157","last_updated":"2025-05-10T07:12:53Z","snapshot_observed_at":"2026-08-19T12:04:15.610247Z","submitted_at":"2025-04-16T15:04:14Z","title":"FocusedAD: Character-centric Movie Audio Description","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-16T12:40:23.863317Z"},"links":{"cited_paper":"/paper/2011.07735","citing_paper":"/paper/2504.12157"},"observation_digest":"sha256:44481907d9ebbfad0ba5d0a15723c74fed4e978e11967d9a6dd8e8715cd9454a","observation_id":"1b158e96-27fa-4e44-8650-8c5b9228eaf3","resolution":{"observed_at":"2026-08-16T12:40:23.863317Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2011.07735","last_updated":"2020-11-16T05:44:45Z","snapshot_observed_at":"2026-08-22T00:14:08.193544Z","submitted_at":"2020-11-16T05:44:45Z","title":"iPerceive: Applying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering","version":1},"cited_work":{"arxiv_id":"2011.07735","doi":null,"metadata_source":"pith","pith_arxiv_id":"2011.07735","snapshot_observed_at":"2026-08-06T23:49:30.811814Z","title":"iPerceive: Applying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering","venue":"cs.CV","work_id":"781501cc-e745-45b5-b41d-332299496fbb","year":2020},"citing_paper":{"arxiv_id":"2506.16082","last_updated":"2025-06-19T07:07:42Z","snapshot_observed_at":"2026-08-22T00:14:25.788293Z","submitted_at":"2025-06-19T07:07:42Z","title":"PR-DETR: Injecting Position and Relation Prior for Dense Video Captioning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T23:49:30.622323Z"},"links":{"cited_paper":"/paper/2011.07735","citing_paper":"/paper/2506.16082"},"observation_digest":"sha256:0df38822bd37a11bfd61dc710441597c9f3b28278047bc20c9646dc9bf88bd36","observation_id":"5ed51ade-4dbb-4174-b9d4-1445d517539f","resolution":{"observed_at":"2026-08-06T23:49:30.817671Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2011.07735/citation-record","integrity":"/paper/2011.07735/integrity","json":"/paper/2011.07735/citation-record.json","paper":"/paper/2011.07735"},"outbound":[],"paper":{"arxiv_id":"2011.07735","last_updated":"2020-11-16T05:44:45Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-22T00:14:08.193544Z","submitted_at":"2020-11-16T05:44:45Z","title":"iPerceive: Applying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering"},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2011.07735."}