{"as_of":"2026-08-11T01:29:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8e2f57132237c4865bab9c0b8a27299885a5dcbf305ff2010406a84049fa65f7","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":"2026-08-10T06:31:04.303077+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":"2026-08-06T19:20:44.449219Z","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":"2026-05-16T20:54:07.673279Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2111.13196","last_updated":"2022-06-18T07:42:52Z","snapshot_observed_at":"2026-07-06T12:12:15.254030Z","submitted_at":"2021-11-25T18:02:12Z","title":"SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning","version":4},"cited_work":{"arxiv_id":"2111.13196","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2111.13196","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Swinbert: End-to-end transformers with sparse attention for video captioning.arXiv preprint arXiv:2111.13196, 2021a","venue":null,"work_id":"26aca490-1e6b-4764-bef4-579f42a1d9f4","year":null},"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":19,"source":"pdf_text","source_observed_at":"2026-05-16T20:54:07.572136Z"},"links":{"cited_paper":"/paper/2111.13196","citing_paper":"/paper/2205.14100"},"observation_digest":"sha256:c6017144ab7aceeb639ed951e455ace522c4d37389e5e0c20c39510c959b38e9","observation_id":"cb158afd-4ddb-4e40-9d5c-d8ce68bbb667","resolution":{"observed_at":"2026-05-16T20:54:07.675223Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2111.13196","last_updated":"2022-06-18T07:42:52Z","snapshot_observed_at":"2026-07-06T12:12:15.254030Z","submitted_at":"2021-11-25T18:02:12Z","title":"SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.13196","snapshot_observed_at":"2026-08-06T19:20:44.449219Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.05894","last_updated":"2025-07-08T11:32:02Z","snapshot_observed_at":"2026-08-08T14:24:14.486497Z","submitted_at":"2025-07-08T11:32:02Z","title":"MusiScene: Leveraging MU-LLaMA for Scene Imagination and Enhanced Video Background Music Generation","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-06T19:20:44.449219Z"},"links":{"cited_paper":"/paper/2111.13196","citing_paper":"/paper/2507.05894"},"observation_digest":"sha256:b43abf87713d847d319c3b08f2686736b8d60ce535a286ac55f78ba473ad2e94","observation_id":"f6b4739f-16a9-4b7c-8066-b9f4b34dc5a6","resolution":{"observed_at":"2026-08-06T19:20:44.449219Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2111.13196/citation-record","integrity":"/paper/2111.13196/integrity","json":"/paper/2111.13196/citation-record.json","paper":"/paper/2111.13196"},"outbound":[],"paper":{"arxiv_id":"2111.13196","last_updated":"2022-06-18T07:42:52Z","latest_version":4,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T12:12:15.254030Z","submitted_at":"2021-11-25T18:02:12Z","title":"SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning"},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2111.13196."}