{"as_of":"2026-08-11T03:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:235ebf63859ea124ca8df7ed199ac9dbb3702a26bd9ac8f8c8c64bbd7de70b78","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T20:50:17.385174Z","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":"2026-08-06T06:04:30.231041Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2305.19603","last_updated":"2023-05-31T07:17:32Z","snapshot_observed_at":"2026-07-06T15:35:49.019768Z","submitted_at":"2023-05-31T07:17:32Z","title":"Intelligible Lip-to-Speech Synthesis with Speech Units","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.19603","snapshot_observed_at":"2026-08-09T20:50:17.385174Z","title":"Intelligible lip-to-speech synthe- sis with speech units,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.19258","last_updated":"2025-08-16T21:44:41Z","snapshot_observed_at":"2026-08-10T16:30:40.863297Z","submitted_at":"2025-01-31T16:16:52Z","title":"VisualSpeech: Enhancing Prosody Modeling in TTS Using Video","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-09T20:50:17.385174Z"},"links":{"cited_paper":"/paper/2305.19603","citing_paper":"/paper/2501.19258"},"observation_digest":"sha256:342c50f039e71e2dfce73cb002a0d1c58ebfd7ac5d006cfcdb8dc8689eb6534c","observation_id":"dce0b177-93b1-4bad-ac6b-1a923b5ebdff","resolution":{"observed_at":"2026-08-09T20:50:17.385174Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.19603","last_updated":"2023-05-31T07:17:32Z","snapshot_observed_at":"2026-07-06T15:35:49.019768Z","submitted_at":"2023-05-31T07:17:32Z","title":"Intelligible Lip-to-Speech Synthesis with Speech Units","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.19603","snapshot_observed_at":"2026-08-09T05:54:18.462539Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.03128","last_updated":"2025-02-05T12:36:21Z","snapshot_observed_at":"2026-08-09T08:33:22.897642Z","submitted_at":"2025-02-05T12:36:21Z","title":"Metis: A Foundation Speech Generation Model with Masked Generative Pre-training","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-09T05:54:18.462539Z"},"links":{"cited_paper":"/paper/2305.19603","citing_paper":"/paper/2502.03128"},"observation_digest":"sha256:ea4cf960466153adfb6f3147c4649854deb381ed83d71123a4169557275069ee","observation_id":"18e1d699-ac5c-432a-9943-863877db5bdd","resolution":{"observed_at":"2026-08-09T05:54:18.462539Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.19603","last_updated":"2023-05-31T07:17:32Z","snapshot_observed_at":"2026-07-06T15:35:49.019768Z","submitted_at":"2023-05-31T07:17:32Z","title":"Intelligible Lip-to-Speech Synthesis with Speech Units","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.19603","snapshot_observed_at":"2026-08-06T21:19:51.402047Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.00498","last_updated":"2025-08-03T15:08:39Z","snapshot_observed_at":"2026-08-09T05:55:49.445628Z","submitted_at":"2025-07-01T07:13:34Z","title":"MuteSwap: Visual-informed Silent Video Identity Conversion","version":3},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-06T21:19:51.402047Z"},"links":{"cited_paper":"/paper/2305.19603","citing_paper":"/paper/2507.00498"},"observation_digest":"sha256:85f672b188f449f2ddfae90da89370bf56a10b7bd3adc8357651d25569eb077e","observation_id":"d0dcf465-cbdc-4f90-8470-770e0df21ade","resolution":{"observed_at":"2026-08-06T21:19:51.402047Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.19603","last_updated":"2023-05-31T07:17:32Z","snapshot_observed_at":"2026-07-06T15:35:49.019768Z","submitted_at":"2023-05-31T07:17:32Z","title":"Intelligible Lip-to-Speech Synthesis with Speech Units","version":1},"cited_work":{"arxiv_id":"2305.19603","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.19603","snapshot_observed_at":"2026-08-06T06:04:30.231041Z","title":"Intelligible Lip-to-Speech Synthesis with Speech Units","venue":"cs.SD","work_id":"a2147df0-8758-4154-8d82-6bd46a0e516b","year":2023},"citing_paper":{"arxiv_id":"2508.00733","last_updated":"2025-08-07T04:31:04Z","snapshot_observed_at":"2026-08-09T12:20:24.219814Z","submitted_at":"2025-08-01T16:03:57Z","title":"AudioGen-Omni: A Unified Multimodal Diffusion Transformer for Video-Synchronized Audio, Speech, and Song Generation","version":4},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-06T06:04:29.497216Z"},"links":{"cited_paper":"/paper/2305.19603","citing_paper":"/paper/2508.00733"},"observation_digest":"sha256:38c4e0903948a229c3c71ab4a17671a28fc19f66326a21e54e1e2659f478825b","observation_id":"cc18a5d3-7b85-4190-9dbd-4c6d356f4faa","resolution":{"observed_at":"2026-08-06T06:04:30.235068Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2305.19603/citation-record","integrity":"/paper/2305.19603/integrity","json":"/paper/2305.19603/citation-record.json","paper":"/paper/2305.19603"},"outbound":[],"paper":{"arxiv_id":"2305.19603","last_updated":"2023-05-31T07:17:32Z","latest_version":1,"primary_category":"cs.SD","snapshot_observed_at":"2026-07-06T15:35:49.019768Z","submitted_at":"2023-05-31T07:17:32Z","title":"Intelligible Lip-to-Speech Synthesis with Speech Units"},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2305.19603."}