{"as_of":"2026-08-09T20:16:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:60e7a8b9e0bb914e5c4e22687e712e9dfc527892d52e79494fab7a031ab4bdb6","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":"2026-08-09T06:31:02.800959+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":"2026-08-08T19:15:52.087678Z","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":"2026-08-06T16:45:54.654784Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2312.15197","last_updated":"2023-12-23T08:45:57Z","snapshot_observed_at":"2026-08-02T21:07:22.279100Z","submitted_at":"2023-12-23T08:45:57Z","title":"TransFace: Unit-Based Audio-Visual Speech Synthesizer for Talking Head Translation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.15197","snapshot_observed_at":"2026-08-08T19:15:52.087678Z","title":"Transface: Unit-based audio-visual speech synthesizer for talking head translation,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.05471","last_updated":"2025-02-08T07:14:04Z","snapshot_observed_at":"2026-08-08T19:09:27.361732Z","submitted_at":"2025-02-08T07:14:04Z","title":"Enhancing Expressive Voice Conversion with Discrete Pitch-Conditioned Flow Matching Model","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-08T19:15:52.087678Z"},"links":{"cited_paper":"/paper/2312.15197","citing_paper":"/paper/2502.05471"},"observation_digest":"sha256:8e1b26b85024e136a6b2cc9913ce5fafd4c7b9f0d9d191c930dec7f9d684b7a8","observation_id":"82359265-8bcb-441c-92b6-2f423f7bf549","resolution":{"observed_at":"2026-08-08T19:15:52.087678Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.15197","last_updated":"2023-12-23T08:45:57Z","snapshot_observed_at":"2026-08-02T21:07:22.279100Z","submitted_at":"2023-12-23T08:45:57Z","title":"TransFace: Unit-Based Audio-Visual Speech Synthesizer for Talking Head Translation","version":1},"cited_work":{"arxiv_id":"2312.15197","doi":null,"metadata_source":"pith","pith_arxiv_id":"2312.15197","snapshot_observed_at":"2026-08-06T16:45:54.654784Z","title":"TransFace: Unit-Based Audio-Visual Speech Synthesizer for Talking Head Translation","venue":"cs.SD","work_id":"144a9565-1541-49bc-9b23-16fd000bdf85","year":2023},"citing_paper":{"arxiv_id":"2507.12723","last_updated":"2025-07-17T02:02:39Z","snapshot_observed_at":"2026-08-09T16:41:23.778371Z","submitted_at":"2025-07-17T02:02:39Z","title":"Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T16:45:51.295199Z"},"links":{"cited_paper":"/paper/2312.15197","citing_paper":"/paper/2507.12723"},"observation_digest":"sha256:669b22aac85891d262a35a3d4c4d32ff9b1354e900151880432fd175f5ce3b22","observation_id":"98f9c78d-94b4-4d71-bb5e-9f17137ba254","resolution":{"observed_at":"2026-08-06T16:45:54.731731Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2312.15197/citation-record","integrity":"/paper/2312.15197/integrity","json":"/paper/2312.15197/citation-record.json","paper":"/paper/2312.15197"},"outbound":[],"paper":{"arxiv_id":"2312.15197","last_updated":"2023-12-23T08:45:57Z","latest_version":1,"primary_category":"cs.SD","snapshot_observed_at":"2026-08-02T21:07:22.279100Z","submitted_at":"2023-12-23T08:45:57Z","title":"TransFace: Unit-Based Audio-Visual Speech Synthesizer for Talking Head Translation"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2312.15197."}