{"as_of":"2026-08-07T05:47:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:dd88e4d4a304a728f8a4adec330a699f7a28bb010bccf539818ba011a2ff0fcc","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":"2026-08-06T06:34:29.942622+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":"2026-05-10T15:46:58.010112Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-11T09:51:00.804082Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2503.16956","last_updated":"2025-03-21T09:02:38Z","snapshot_observed_at":"2026-07-06T20:56:36.184649Z","submitted_at":"2025-03-21T09:02:38Z","title":"From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speech","version":1},"cited_work":{"arxiv_id":"2503.16956","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.16956","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2503.16956 (2025)","venue":null,"work_id":"89536f68-ebac-4143-8c16-5d832a0d0105","year":2025},"citing_paper":{"arxiv_id":"2604.12292","last_updated":"2026-04-14T05:03:57Z","snapshot_observed_at":"2026-08-06T05:09:28.270784Z","submitted_at":"2026-04-14T05:03:57Z","title":"CoSyncDiT: Cognitive Synchronous Diffusion Transformer for Movie Dubbing","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-10T15:46:58.010112Z"},"links":{"cited_paper":"/paper/2503.16956","citing_paper":"/paper/2604.12292"},"observation_digest":"sha256:c46f81f9fe910972621e5d4ac2e5875c2669c5dc850206a0d6aa626bb9cf4209","observation_id":"731e3434-6f59-4259-a34b-3e8acd5f42a9","resolution":{"observed_at":"2026-05-11T09:51:00.811250Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2503.16956/citation-record","integrity":"/paper/2503.16956/integrity","json":"/paper/2503.16956/citation-record.json","paper":"/paper/2503.16956"},"outbound":[],"paper":{"arxiv_id":"2503.16956","last_updated":"2025-03-21T09:02:38Z","latest_version":1,"primary_category":"eess.AS","snapshot_observed_at":"2026-07-06T20:56:36.184649Z","submitted_at":"2025-03-21T09:02:38Z","title":"From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speech"},"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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2503.16956."}