{"as_of":"2026-08-21T06:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3582a431b70cde52dd1ec89d334e400170690945d1773ca2760c7db21f153d7a","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":"2026-08-10T23:14:31.362775Z","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":"2026-08-10T23:14:31.474918Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2311.05152","last_updated":"2023-12-20T23:06:09Z","snapshot_observed_at":"2026-08-18T20:44:56.061187Z","submitted_at":"2023-11-09T05:24:20Z","title":"Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream Tasks","version":2},"cited_work":{"arxiv_id":"2311.05152","doi":null,"metadata_source":"pith","pith_arxiv_id":"2311.05152","snapshot_observed_at":"2026-08-10T23:14:31.474918Z","title":"Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream Tasks","venue":"cs.LG","work_id":"12afae91-a09a-47ea-8b23-bee70a7ecc6d","year":2023},"citing_paper":{"arxiv_id":"2412.20872","last_updated":"2024-12-31T03:39:42Z","snapshot_observed_at":"2026-08-10T23:05:50.113962Z","submitted_at":"2024-12-30T11:23:15Z","title":"LINK: Adaptive Modality Interaction for Audio-Visual Video Parsing","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T23:14:31.362775Z"},"links":{"cited_paper":"/paper/2311.05152","citing_paper":"/paper/2412.20872"},"observation_digest":"sha256:d86177f424e31f6a75319494c1b67358934f31b5fbb955a5020cf9a9744b49c0","observation_id":"772b055e-a842-4dae-8880-c4f23906bcb5","resolution":{"observed_at":"2026-08-10T23:14:31.479730Z","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/2311.05152/citation-record","integrity":"/paper/2311.05152/integrity","json":"/paper/2311.05152/citation-record.json","paper":"/paper/2311.05152"},"outbound":[],"paper":{"arxiv_id":"2311.05152","last_updated":"2023-12-20T23:06:09Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-18T20:44:56.061187Z","submitted_at":"2023-11-09T05:24:20Z","title":"Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream Tasks"},"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:2311.05152."}