{"as_of":"2026-08-07T15:32:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3875274a4503c96e15ecf67b9d2f7d6fa08991a17c1296e8a6cd183dcfa6a870","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":"2026-08-06T21:19:52.752908Z","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":"2026-05-23T17:23:15.008725Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2205.07180","last_updated":"2022-07-14T23:02:59Z","snapshot_observed_at":"2026-08-06T15:39:59.936882Z","submitted_at":"2022-05-15T04:48:41Z","title":"Learning Lip-Based Audio-Visual Speaker Embeddings with AV-HuBERT","version":2},"cited_work":{"arxiv_id":"2205.07180","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2205.07180","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learning lip-based audio-visual speaker embeddings with av-hubert","venue":null,"work_id":"9645b5d1-60fe-4ca7-8be7-d97736d42394","year":2022},"citing_paper":{"arxiv_id":"2411.17690","last_updated":"2026-04-20T17:56:40Z","snapshot_observed_at":"2026-08-02T10:11:40.015144Z","submitted_at":"2024-11-26T18:57:29Z","title":"Mechanisms of Multimodal Synchronization: Insights from Decoder-Based Video-Text-to-Speech Synthesis","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-23T17:22:23.797551Z"},"links":{"cited_paper":"/paper/2205.07180","citing_paper":"/paper/2411.17690"},"observation_digest":"sha256:4a93b96f598e58b0d8eaa6f60d50ffa7ea5342985547cf0967c47b338d36abf1","observation_id":"d0a3ac82-16d9-4bf0-9b2d-ad51a7edfcf5","resolution":{"observed_at":"2026-05-23T17:23:15.012786Z","resolver_source":"arxiv_id","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"}},{"citation":{"cited_paper":{"arxiv_id":"2205.07180","last_updated":"2022-07-14T23:02:59Z","snapshot_observed_at":"2026-08-06T15:39:59.936882Z","submitted_at":"2022-05-15T04:48:41Z","title":"Learning Lip-Based Audio-Visual Speaker Embeddings with AV-HuBERT","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.07180","snapshot_observed_at":"2026-08-06T21:19:52.752908Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.00498","last_updated":"2025-08-03T15:08:39Z","snapshot_observed_at":"2026-08-06T21:11:21.419989Z","submitted_at":"2025-07-01T07:13:34Z","title":"MuteSwap: Visual-informed Silent Video Identity Conversion","version":3},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-06T21:19:52.752908Z"},"links":{"cited_paper":"/paper/2205.07180","citing_paper":"/paper/2507.00498"},"observation_digest":"sha256:2e2b25b4b9eb10f3cdbb7115bb262e2707f77ea8eaa08163f4038e3e5c1429d7","observation_id":"8cb0660a-527a-42db-9ce8-43d9d600d0a5","resolution":{"observed_at":"2026-08-06T21:19:52.752908Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2205.07180/citation-record","integrity":"/paper/2205.07180/integrity","json":"/paper/2205.07180/citation-record.json","paper":"/paper/2205.07180"},"outbound":[],"paper":{"arxiv_id":"2205.07180","last_updated":"2022-07-14T23:02:59Z","latest_version":2,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-06T15:39:59.936882Z","submitted_at":"2022-05-15T04:48:41Z","title":"Learning Lip-Based Audio-Visual Speaker Embeddings with AV-HuBERT"},"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:2205.07180."}