{"as_of":"2026-08-21T10:27:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d56a6e0df6582867bb727f6f83c39da6ecac97d197253e4d29b911e1b76e013d","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":"2026-08-21T06:32:19.484+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":"2026-08-07T11:50:47.026015Z","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":"2026-08-07T11:50:47.597288Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.13363","last_updated":"2025-02-19T01:53:03Z","snapshot_observed_at":"2026-08-16T12:57:08.739349Z","submitted_at":"2025-02-19T01:53:03Z","title":"Pretrained Image-Text Models are Secretly Video Captioners","version":1},"cited_work":{"arxiv_id":"2502.13363","doi":null,"metadata_source":"pith","pith_arxiv_id":"2502.13363","snapshot_observed_at":"2026-08-07T11:50:47.597288Z","title":"Pretrained Image-Text Models are Secretly Video Captioners","venue":"cs.CV","work_id":"eec30ca5-f137-424c-915f-145f211e4e9e","year":2025},"citing_paper":{"arxiv_id":"2506.01319","last_updated":"2025-06-02T05:02:03Z","snapshot_observed_at":"2026-08-17T08:26:34.822082Z","submitted_at":"2025-06-02T05:02:03Z","title":"Learning Sparsity for Effective and Efficient Music Performance Question Answering","version":1},"reference_index":77,"source":"arxiv_source","source_observed_at":"2026-08-07T11:50:47.026015Z"},"links":{"cited_paper":"/paper/2502.13363","citing_paper":"/paper/2506.01319"},"observation_digest":"sha256:89b13b9b5fd793346342eaeee7809905174e69ddd2464857e9f8a538598625e7","observation_id":"b19827a0-a316-40a1-ae2a-ab6c88aff745","resolution":{"observed_at":"2026-08-07T11:50:47.708585Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2502.13363/citation-record","integrity":"/paper/2502.13363/integrity","json":"/paper/2502.13363/citation-record.json","paper":"/paper/2502.13363"},"outbound":[],"paper":{"arxiv_id":"2502.13363","last_updated":"2025-02-19T01:53:03Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T12:57:08.739349Z","submitted_at":"2025-02-19T01:53:03Z","title":"Pretrained Image-Text Models are Secretly Video Captioners"},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2502.13363."}