{"as_of":"2026-08-22T19:41:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d6359442b873a84a584dd78b2dc39ffa931fdea46a4a247c7a41d255ffe0cad2","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":"2026-08-22T06:32:14.747728+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":"2026-08-16T10:28:36.166347Z","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":"2026-08-10T14:40:55.509178Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2401.05698","last_updated":"2024-04-01T07:19:40Z","snapshot_observed_at":"2026-08-16T14:28:20.262704Z","submitted_at":"2024-01-11T07:00:07Z","title":"HiCMAE: Hierarchical Contrastive Masked Autoencoder for Self-Supervised Audio-Visual Emotion Recognition","version":2},"cited_work":{"arxiv_id":"2401.05698","doi":null,"metadata_source":"pith","pith_arxiv_id":"2401.05698","snapshot_observed_at":"2026-08-10T14:40:55.509178Z","title":"HiCMAE: Hierarchical Contrastive Masked Autoencoder for Self-Supervised Audio-Visual Emotion Recognition","venue":"cs.CV","work_id":"77b1d937-d763-4987-a4b4-2ab0bda83f62","year":2024},"citing_paper":{"arxiv_id":"2501.15111","last_updated":"2025-01-25T07:26:37Z","snapshot_observed_at":"2026-08-18T05:01:23.171038Z","submitted_at":"2025-01-25T07:26:37Z","title":"HumanOmni: A Large Vision-Speech Language Model for Human-Centric Video Understanding","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-10T14:40:55.300372Z"},"links":{"cited_paper":"/paper/2401.05698","citing_paper":"/paper/2501.15111"},"observation_digest":"sha256:de778d27a92d4b49abea9b327d7e5b38e45d96d748f4799498065316d831a622","observation_id":"841206ea-90a1-4f72-a555-f83656009acf","resolution":{"observed_at":"2026-08-10T14:40:55.515579Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.05698","last_updated":"2024-04-01T07:19:40Z","snapshot_observed_at":"2026-08-16T14:28:20.262704Z","submitted_at":"2024-01-11T07:00:07Z","title":"HiCMAE: Hierarchical Contrastive Masked Autoencoder for Self-Supervised Audio-Visual Emotion Recognition","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.05698","snapshot_observed_at":"2026-08-16T10:28:36.166347Z","title":"Hic- mae: Hierarchical contrastive masked autoencoder for self- supervised audio-visual emotion recognition","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.18152","last_updated":"2025-04-25T08:05:32Z","snapshot_observed_at":"2026-08-18T23:12:11.726082Z","submitted_at":"2025-04-25T08:05:32Z","title":"ActionArt: Advancing Multimodal Large Models for Fine-Grained Human-Centric Video Understanding","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-16T10:28:36.166347Z"},"links":{"cited_paper":"/paper/2401.05698","citing_paper":"/paper/2504.18152"},"observation_digest":"sha256:c48831e6ee6ae94fcdb29022558cf71e5e6002862578b56ebf4dbf4a4af5158f","observation_id":"3cc4c6df-e62e-48f2-876c-d318a551c0cb","resolution":{"observed_at":"2026-08-16T10:28:36.166347Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2401.05698/citation-record","integrity":"/paper/2401.05698/integrity","json":"/paper/2401.05698/citation-record.json","paper":"/paper/2401.05698"},"outbound":[],"paper":{"arxiv_id":"2401.05698","last_updated":"2024-04-01T07:19:40Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T14:28:20.262704Z","submitted_at":"2024-01-11T07:00:07Z","title":"HiCMAE: Hierarchical Contrastive Masked Autoencoder for Self-Supervised Audio-Visual 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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2401.05698."}