{"as_of":"2026-08-13T02:27:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:218f89e54cedc969fb2d625bfbdff9d8c321267c56079f6878a29da225e4bc36","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":"2026-08-12T06:34:41.77262+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":"2026-08-11T18:11:54.500386Z","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":"2026-08-11T18:11:56.502674Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2309.10783","last_updated":"2023-09-19T17:32:21Z","snapshot_observed_at":"2026-07-06T16:20:40.674175Z","submitted_at":"2023-09-19T17:32:21Z","title":"Language as the Medium: Multimodal Video Classification through text only","version":1},"cited_work":{"arxiv_id":"2309.10783","doi":null,"metadata_source":"pith","pith_arxiv_id":"2309.10783","snapshot_observed_at":"2026-08-11T18:11:56.502674Z","title":"Language as the Medium: Multimodal Video Classification through text only","venue":"cs.CV","work_id":"4ea45c71-608d-4efb-8b48-0b9b2ab5929f","year":2023},"citing_paper":{"arxiv_id":"2412.08158","last_updated":"2024-12-11T07:29:04Z","snapshot_observed_at":"2026-08-12T07:36:23.412895Z","submitted_at":"2024-12-11T07:29:04Z","title":"How Vision-Language Tasks Benefit from Large Pre-trained Models: A Survey","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-11T18:11:54.500386Z"},"links":{"cited_paper":"/paper/2309.10783","citing_paper":"/paper/2412.08158"},"observation_digest":"sha256:f277e000a110430fa4b6e69c49564ae89d57be8ecdfded9dc3cb4b2024f07f76","observation_id":"db0487ce-303f-4a8d-b77b-6d2977114b46","resolution":{"observed_at":"2026-08-11T18:11:56.508315Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2309.10783/citation-record","integrity":"/paper/2309.10783/integrity","json":"/paper/2309.10783/citation-record.json","paper":"/paper/2309.10783"},"outbound":[],"paper":{"arxiv_id":"2309.10783","last_updated":"2023-09-19T17:32:21Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T16:20:40.674175Z","submitted_at":"2023-09-19T17:32:21Z","title":"Language as the Medium: Multimodal Video Classification through text only"},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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:2309.10783."}