{"as_of":"2026-08-13T15:16:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5afd8a64629a9fb661c39ee8016291f556e60187cd8a4eef9dcfb95faa00d1b8","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":"2026-08-13T06:32:02.005865+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":"2026-08-12T14:04:00.470622Z","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":"2026-08-12T14:04:04.429355Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2304.02560","last_updated":"2024-03-29T16:56:33Z","snapshot_observed_at":"2026-08-13T12:08:37.876115Z","submitted_at":"2023-04-05T16:30:36Z","title":"VicTR: Video-conditioned Text Representations for Activity Recognition","version":2},"cited_work":{"arxiv_id":"2304.02560","doi":null,"metadata_source":"pith","pith_arxiv_id":"2304.02560","snapshot_observed_at":"2026-08-12T14:04:04.429355Z","title":"VicTR: Video-conditioned Text Representations for Activity Recognition","venue":"cs.CV","work_id":"51cc1204-eaba-449c-a211-c9d840e30f01","year":2023},"citing_paper":{"arxiv_id":"2412.00049","last_updated":"2024-11-24T03:26:34Z","snapshot_observed_at":"2026-08-13T08:29:44.393581Z","submitted_at":"2024-11-24T03:26:34Z","title":"A Survey of Recent Advances and Challenges in Deep Audio-Visual Correlation Learning","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-12T14:04:00.470622Z"},"links":{"cited_paper":"/paper/2304.02560","citing_paper":"/paper/2412.00049"},"observation_digest":"sha256:ea3156a08c35ccfc74162e8c13f630464f2cdee271e6601246acf19b6e18a5fb","observation_id":"b4aedebb-b76a-4019-9841-e1c1834ef237","resolution":{"observed_at":"2026-08-12T14:04:04.434377Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2304.02560/citation-record","integrity":"/paper/2304.02560/integrity","json":"/paper/2304.02560/citation-record.json","paper":"/paper/2304.02560"},"outbound":[],"paper":{"arxiv_id":"2304.02560","last_updated":"2024-03-29T16:56:33Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-13T12:08:37.876115Z","submitted_at":"2023-04-05T16:30:36Z","title":"VicTR: Video-conditioned Text Representations for Activity Recognition"},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2304.02560."}