{"as_of":"2026-08-05T04:38:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c470b0fcfd63d8b9ffb055e64e574c581b06e43802571cb56f908596bef3b249","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":"2026-08-04T06:34:03.388597+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":"2026-08-04T11:06:46.566015Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2005.03201","last_updated":"2020-05-07T01:58:05Z","snapshot_observed_at":"2026-08-04T21:04:37.896530Z","submitted_at":"2020-05-07T01:58:05Z","title":"What comprises a good talking-head video generation?: A Survey and Benchmark","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.03201","snapshot_observed_at":"2026-08-04T11:06:46.566015Z","title":"What comprises a good talking-head video gener- ation?: A survey and benchmark,","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2510.07355","last_updated":"2026-05-28T11:55:17Z","snapshot_observed_at":"2026-08-04T11:06:43.353437Z","submitted_at":"2025-10-08T14:13:28Z","title":"AV-EMO-Reasoning: Benchmarking Emotional Reasoning Capabilities in Omni-modal LLMS with Audio-visual Cues","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-04T11:06:46.566015Z"},"links":{"cited_paper":"/paper/2005.03201","citing_paper":"/paper/2510.07355"},"observation_digest":"sha256:01d1300388409cd0fd38d1d0ca93940a7eefdb7e51a92c4cdcf91630e0516e88","observation_id":"650e59fa-b87e-4d33-996e-ec183875082e","resolution":{"observed_at":"2026-08-04T11:06:46.566015Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2005.03201/citation-record","integrity":"/paper/2005.03201/integrity","json":"/paper/2005.03201/citation-record.json","paper":"/paper/2005.03201"},"outbound":[],"paper":{"arxiv_id":"2005.03201","last_updated":"2020-05-07T01:58:05Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-04T21:04:37.896530Z","submitted_at":"2020-05-07T01:58:05Z","title":"What comprises a good talking-head video generation?: A Survey and Benchmark"},"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":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2005.03201."}