{"as_of":"2026-08-07T22:08:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:90f874bb5df05c7474131b929f5879042ad744f84cac87aba2406260ac1d749e","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":"2026-08-07T06:34:17.273281+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":"2026-08-07T13:26:50.042373Z","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":"2026-08-06T12:18:26.626332Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.16438","last_updated":"2024-10-21T19:02:13Z","snapshot_observed_at":"2026-07-06T19:37:24.895623Z","submitted_at":"2024-10-21T19:02:13Z","title":"AlignVSR: Audio-Visual Cross-Modal Alignment for Visual Speech Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.16438","snapshot_observed_at":"2026-08-07T13:26:50.042373Z","title":"AlignVSR: Audio-visual cross-modal alignment for visual speech recogni- tion,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.02012","last_updated":"2025-05-27T21:00:12Z","snapshot_observed_at":"2026-08-07T13:21:16.377095Z","submitted_at":"2025-05-27T21:00:12Z","title":"Leveraging Large Language Models in Visual Speech Recognition: Model Scaling, Context-Aware Decoding, and Iterative Polishing","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:50.042373Z"},"links":{"cited_paper":"/paper/2410.16438","citing_paper":"/paper/2506.02012"},"observation_digest":"sha256:a8648213044cb936d662fd69411692c8f3118e210b9cbb51bb1d1ed5277c1795","observation_id":"150bd5e0-5047-4913-b84f-9f45720ad619","resolution":{"observed_at":"2026-08-07T13:26:50.042373Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.16438","last_updated":"2024-10-21T19:02:13Z","snapshot_observed_at":"2026-07-06T19:37:24.895623Z","submitted_at":"2024-10-21T19:02:13Z","title":"AlignVSR: Audio-Visual Cross-Modal Alignment for Visual Speech Recognition","version":1},"cited_work":{"arxiv_id":"2410.16438","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.16438","snapshot_observed_at":"2026-08-06T12:18:26.626332Z","title":"AlignVSR: Audio-Visual Cross-Modal Alignment for Visual Speech Recognition","venue":"cs.SD","work_id":"600299b6-bf5e-4070-8db7-589c61902e96","year":2024},"citing_paper":{"arxiv_id":"2507.21945","last_updated":"2025-07-29T15:58:39Z","snapshot_observed_at":"2026-08-06T12:18:17.390006Z","submitted_at":"2025-07-29T15:58:39Z","title":"Attention-Driven Multimodal Alignment for Long-term Action Quality Assessment","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T12:18:25.094671Z"},"links":{"cited_paper":"/paper/2410.16438","citing_paper":"/paper/2507.21945"},"observation_digest":"sha256:c39a96271eafe05515bc0cac18df27f66476a4afc8ce7fad80febd441acd43e1","observation_id":"dc635a20-9a1d-41c8-b400-95e65f7d9f20","resolution":{"observed_at":"2026-08-06T12:18:26.702155Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2410.16438/citation-record","integrity":"/paper/2410.16438/integrity","json":"/paper/2410.16438/citation-record.json","paper":"/paper/2410.16438"},"outbound":[],"paper":{"arxiv_id":"2410.16438","last_updated":"2024-10-21T19:02:13Z","latest_version":1,"primary_category":"cs.SD","snapshot_observed_at":"2026-07-06T19:37:24.895623Z","submitted_at":"2024-10-21T19:02:13Z","title":"AlignVSR: Audio-Visual Cross-Modal Alignment for Visual Speech 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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2410.16438."}