{"as_of":"2026-08-08T22:01:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:237dcb9c8d374b6ab0ba6fa1d07d6da7c2a4173d02fd93a268857dd6eeb02b40","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T15:03:37.652640Z","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":"2026-05-16T09:20:20.379433Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2011.00597","last_updated":"2020-11-01T18:54:09Z","snapshot_observed_at":"2026-07-06T10:10:39.816933Z","submitted_at":"2020-11-01T18:54:09Z","title":"COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning","version":1},"cited_work":{"arxiv_id":"2011.00597","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2011.00597","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2011.00597 , year=","venue":null,"work_id":"7398ece1-ccc9-4f83-b4ee-6dab9e62e414","year":2011},"citing_paper":{"arxiv_id":"2309.16671","last_updated":"2025-11-23T00:34:43Z","snapshot_observed_at":"2026-08-02T18:24:11.208164Z","submitted_at":"2023-09-28T17:59:56Z","title":"Demystifying CLIP Data","version":6},"reference_index":117,"source":"arxiv_source","source_observed_at":"2026-05-16T09:20:20.143143Z"},"links":{"cited_paper":"/paper/2011.00597","citing_paper":"/paper/2309.16671"},"observation_digest":"sha256:8b2ced415a3c9fe74d481e5bf60047ceb19335b6fd9691ed4cb9e770755c4562","observation_id":"8ba1bcc9-bab7-45c6-b4a7-d2e5bb3f6e3c","resolution":{"observed_at":"2026-05-16T09:20:20.380750Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2011.00597","last_updated":"2020-11-01T18:54:09Z","snapshot_observed_at":"2026-07-06T10:10:39.816933Z","submitted_at":"2020-11-01T18:54:09Z","title":"COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.00597","snapshot_observed_at":"2026-08-07T15:03:37.652640Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.16425","last_updated":"2025-05-22T09:10:09Z","snapshot_observed_at":"2026-08-07T14:58:56.454326Z","submitted_at":"2025-05-22T09:10:09Z","title":"$I^2G$: Generating Instructional Illustrations via Text-Conditioned Diffusion","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T15:03:37.652640Z"},"links":{"cited_paper":"/paper/2011.00597","citing_paper":"/paper/2505.16425"},"observation_digest":"sha256:123a2bbf82e106a6c4fbc0a7cde3725fe2abfb05f18319825a5cebab80c79d1e","observation_id":"66908ad7-fc0f-4d95-9147-fc4620f8c7f4","resolution":{"observed_at":"2026-08-07T15:03:37.652640Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2011.00597/citation-record","integrity":"/paper/2011.00597/integrity","json":"/paper/2011.00597/citation-record.json","paper":"/paper/2011.00597"},"outbound":[],"paper":{"arxiv_id":"2011.00597","last_updated":"2020-11-01T18:54:09Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T10:10:39.816933Z","submitted_at":"2020-11-01T18:54:09Z","title":"COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2011.00597."}