{"as_of":"2026-08-14T16:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:85fb9a0b8e8284d0856df9da2e09f28ff2f3709046b83175a6dc1cc6e7be61a1","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":"2026-08-14T06:32:32.682623+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":"2026-08-11T16:56:06.220677Z","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":"2026-08-07T05:49:54.210292Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2411.16213","last_updated":"2024-12-10T19:43:46Z","snapshot_observed_at":"2026-07-06T19:56:25.704753Z","submitted_at":"2024-11-25T09:22:13Z","title":"SAVEn-Vid: Synergistic Audio-Visual Integration for Enhanced Understanding in Long Video Context","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.16213","snapshot_observed_at":"2026-08-11T16:56:06.220677Z","title":"SA VEn-Vid: Synergistic audio-visual integration for enhanced understanding in long video context","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.09596","last_updated":"2024-12-12T18:58:30Z","snapshot_observed_at":"2026-08-12T23:49:37.475723Z","submitted_at":"2024-12-12T18:58:30Z","title":"InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-11T16:56:06.220677Z"},"links":{"cited_paper":"/paper/2411.16213","citing_paper":"/paper/2412.09596"},"observation_digest":"sha256:2d05b534cc364fdf234721c312493fb233bbee5ff31da6a1b62573f256319bf1","observation_id":"8ad76a10-5bb5-430a-a9fb-20d3772ac61f","resolution":{"observed_at":"2026-08-11T16:56:06.220677Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.16213","last_updated":"2024-12-10T19:43:46Z","snapshot_observed_at":"2026-07-06T19:56:25.704753Z","submitted_at":"2024-11-25T09:22:13Z","title":"SAVEn-Vid: Synergistic Audio-Visual Integration for Enhanced Understanding in Long Video Context","version":2},"cited_work":{"arxiv_id":"2411.16213","doi":null,"metadata_source":"pith","pith_arxiv_id":"2411.16213","snapshot_observed_at":"2026-08-07T05:49:54.210292Z","title":"SAVEn-Vid: Synergistic Audio-Visual Integration for Enhanced Understanding in Long Video Context","venue":"cs.CV","work_id":"b0bc7851-a635-48f1-9ebe-8571f58d075c","year":2024},"citing_paper":{"arxiv_id":"2506.07016","last_updated":"2025-06-13T19:05:47Z","snapshot_observed_at":"2026-08-08T12:14:39.714543Z","submitted_at":"2025-06-08T06:34:29Z","title":"MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T05:49:53.299116Z"},"links":{"cited_paper":"/paper/2411.16213","citing_paper":"/paper/2506.07016"},"observation_digest":"sha256:2ec956d1c5499362d0016809d7e8fb8e5fcb61f064afcb49da1b4406482c4d0d","observation_id":"74a42b6f-062f-4581-8e7b-74b0436b721c","resolution":{"observed_at":"2026-08-07T05:49:54.215338Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2411.16213/citation-record","integrity":"/paper/2411.16213/integrity","json":"/paper/2411.16213/citation-record.json","paper":"/paper/2411.16213"},"outbound":[],"paper":{"arxiv_id":"2411.16213","last_updated":"2024-12-10T19:43:46Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T19:56:25.704753Z","submitted_at":"2024-11-25T09:22:13Z","title":"SAVEn-Vid: Synergistic Audio-Visual Integration for Enhanced Understanding in Long Video Context"},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2411.16213."}