{"as_of":"2026-08-11T17:24:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4694422d09a9257b6729045e6080043fa14ba264f7287d55908cdb30149f0e26","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":"2026-08-11T06:34:44.6726+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":"2026-08-10T22:56:54.629726Z","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":"2026-08-10T13:53:28.846946Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2312.11897","last_updated":"2024-08-19T12:47:11Z","snapshot_observed_at":"2026-08-02T02:18:16.022611Z","submitted_at":"2023-12-19T06:42:47Z","title":"Text-Conditioned Resampler For Long Form Video Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.11897","snapshot_observed_at":"2026-08-10T22:56:54.629726Z","title":"Text-conditioned resam- pler for long form video understanding","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.00358","last_updated":"2025-01-09T03:25:24Z","snapshot_observed_at":"2026-08-10T22:50:40.043012Z","submitted_at":"2024-12-31T09:22:38Z","title":"Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T22:56:54.629726Z"},"links":{"cited_paper":"/paper/2312.11897","citing_paper":"/paper/2501.00358"},"observation_digest":"sha256:b2820d5144062b772c688afe56db72a1230e395110f074ef3d234426594fb7d2","observation_id":"adba18a1-8500-414f-842c-786be24e70ea","resolution":{"observed_at":"2026-08-10T22:56:54.629726Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.11897","last_updated":"2024-08-19T12:47:11Z","snapshot_observed_at":"2026-08-02T02:18:16.022611Z","submitted_at":"2023-12-19T06:42:47Z","title":"Text-Conditioned Resampler For Long Form Video Understanding","version":3},"cited_work":{"arxiv_id":"2312.11897","doi":null,"metadata_source":"pith","pith_arxiv_id":"2312.11897","snapshot_observed_at":"2026-08-10T13:53:28.846946Z","title":"Text-Conditioned Resampler For Long Form Video Understanding","venue":"cs.CV","work_id":"8a9faa14-564f-41b6-bd81-9655c24beb63","year":2023},"citing_paper":{"arxiv_id":"2501.15953","last_updated":"2025-01-27T10:57:24Z","snapshot_observed_at":"2026-08-10T13:47:43.852671Z","submitted_at":"2025-01-27T10:57:24Z","title":"Understanding Long Videos via LLM-Powered Entity Relation Graphs","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T13:53:26.047053Z"},"links":{"cited_paper":"/paper/2312.11897","citing_paper":"/paper/2501.15953"},"observation_digest":"sha256:e27e41a26b52e549622075d67bca67f62b1125e318ef77063a6a5da6286b0f70","observation_id":"7edf763c-3bd1-4d39-96d4-6e1f06330c06","resolution":{"observed_at":"2026-08-10T13:53:28.894062Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2312.11897/citation-record","integrity":"/paper/2312.11897/integrity","json":"/paper/2312.11897/citation-record.json","paper":"/paper/2312.11897"},"outbound":[],"paper":{"arxiv_id":"2312.11897","last_updated":"2024-08-19T12:47:11Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-02T02:18:16.022611Z","submitted_at":"2023-12-19T06:42:47Z","title":"Text-Conditioned Resampler For Long Form Video Understanding"},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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:2312.11897."}