{"as_of":"2026-08-12T10:14:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0836e610f58bcbd2ddde2205de8868d60a20c48892a327cb87b9254e1210617d","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":1,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":1,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-21T04:52:12.045880Z","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":"2026-05-21T04:53:57.818244Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2007.04134","last_updated":"2020-07-08T14:07:06Z","snapshot_observed_at":"2026-08-11T09:42:40.272479Z","submitted_at":"2020-07-08T14:07:06Z","title":"Learning Speech Representations from Raw Audio by Joint Audiovisual Self-Supervision","version":1},"cited_work":{"arxiv_id":"2007.04134","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2007.04134","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learning speech representations from raw audio by joint audiovisual self-supervision","venue":null,"work_id":"1318a547-6947-4805-8c65-9be59b73c6e8","year":2007},"citing_paper":{"arxiv_id":"2605.20838","last_updated":"2026-05-20T07:27:36Z","snapshot_observed_at":"2026-08-03T00:00:48.827421Z","submitted_at":"2026-05-20T07:27:36Z","title":"USV: Towards Understanding the User-generated Short-form Videos","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-05-21T04:52:12.045880Z"},"links":{"cited_paper":"/paper/2007.04134","citing_paper":"/paper/2605.20838"},"observation_digest":"sha256:cc8c36dd523ca27238c81e30c7b545e966b2ca85a315db1f64eb65a987df2c81","observation_id":"5df7220e-6658-4b02-8d90-02f339d8fd3e","resolution":{"observed_at":"2026-05-21T04:53:57.819712Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2007.04134/citation-record","integrity":"/paper/2007.04134/integrity","json":"/paper/2007.04134/citation-record.json","paper":"/paper/2007.04134"},"outbound":[],"paper":{"arxiv_id":"2007.04134","last_updated":"2020-07-08T14:07:06Z","latest_version":1,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-11T09:42:40.272479Z","submitted_at":"2020-07-08T14:07:06Z","title":"Learning Speech Representations from Raw Audio by Joint Audiovisual Self-Supervision"},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2007.04134."}