{"as_of":"2026-08-12T06:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:080616f2fa7df98e8f70c58fddc6d04860669794bc1d5339e918960a7da33308","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":"2026-08-11T06:34:44.6726+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":"2026-08-10T21:18:15.048903Z","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":"2026-06-29T13:03:26.052167Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2305.03568","last_updated":"2025-05-09T08:19:45Z","snapshot_observed_at":"2026-08-11T21:14:24.975933Z","submitted_at":"2023-05-05T14:19:46Z","title":"A vector quantized masked autoencoder for audiovisual speech emotion recognition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.03568","snapshot_observed_at":"2026-08-10T21:18:15.048903Z","title":"A vector quantized masked autoencoder for audiovisual speech emotion recognition,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.05332","last_updated":"2025-01-09T15:58:37Z","snapshot_observed_at":"2026-08-11T15:56:53.524011Z","submitted_at":"2025-01-09T15:58:37Z","title":"AnCoGen: Analysis, Control and Generation of Speech with a Masked Autoencoder","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T21:18:15.048903Z"},"links":{"cited_paper":"/paper/2305.03568","citing_paper":"/paper/2501.05332"},"observation_digest":"sha256:37189fe0d87717c35574ebfd01aa1d04198467be7ec9ed6fc6010109f6c27800","observation_id":"0131dad0-d0cc-41a3-9ce5-e2bf3e9f6390","resolution":{"observed_at":"2026-08-10T21:18:15.048903Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.03568","last_updated":"2025-05-09T08:19:45Z","snapshot_observed_at":"2026-08-11T21:14:24.975933Z","submitted_at":"2023-05-05T14:19:46Z","title":"A vector quantized masked autoencoder for audiovisual speech emotion recognition","version":3},"cited_work":{"arxiv_id":"2305.03568","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2305.03568","snapshot_observed_at":"2026-06-29T13:03:26.052167Z","title":"A vector QUANTIZED MASKED AUTOENCODER FOR AUDIOVISUAL SPEECH EMOTION RECOG- NITION","venue":null,"work_id":"19188326-78c8-428a-be9e-3634a1cbb308","year":2023},"citing_paper":{"arxiv_id":"2606.07585","last_updated":"2026-05-27T16:36:58Z","snapshot_observed_at":"2026-08-09T13:17:31.634660Z","submitted_at":"2026-05-27T16:36:58Z","title":"Multimodal Group Emotion Recognition In-the-Wild Towards a Privacy-Safe Non-Individual Approach","version":1},"reference_index":196,"source":"pdf_text","source_observed_at":"2026-06-29T13:01:00.924735Z"},"links":{"cited_paper":"/paper/2305.03568","citing_paper":"/paper/2606.07585"},"observation_digest":"sha256:98512652bc040deb500621555ce62261fd745b1e3c100ccd934f7e7267ea64e2","observation_id":"c2c4ddb2-8143-415a-8ff4-936d0d2d0621","resolution":{"observed_at":"2026-06-29T13:03:26.053734Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2305.03568/citation-record","integrity":"/paper/2305.03568/integrity","json":"/paper/2305.03568/citation-record.json","paper":"/paper/2305.03568"},"outbound":[],"paper":{"arxiv_id":"2305.03568","last_updated":"2025-05-09T08:19:45Z","latest_version":3,"primary_category":"cs.SD","snapshot_observed_at":"2026-08-11T21:14:24.975933Z","submitted_at":"2023-05-05T14:19:46Z","title":"A vector quantized masked autoencoder for audiovisual speech emotion recognition"},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2305.03568."}