{"as_of":"2026-08-08T05:49:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ae10411de95f031d1df05ccc54c0da96c083ff23ef56ba9de1c446c6d7349b38","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":"2026-08-07T06:34:17.273281+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":"2026-08-06T22:56:46.234160Z","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":"2026-08-06T22:56:47.247617Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2404.06095","last_updated":"2024-04-09T07:57:08Z","snapshot_observed_at":"2026-08-07T00:42:22.022720Z","submitted_at":"2024-04-09T07:57:08Z","title":"Masked Modeling Duo: Towards a Universal Audio Pre-training Framework","version":1},"cited_work":{"arxiv_id":"2404.06095","doi":null,"metadata_source":"pith","pith_arxiv_id":"2404.06095","snapshot_observed_at":"2026-08-06T22:56:47.247617Z","title":"Masked Modeling Duo: Towards a Universal Audio Pre-training Framework","venue":"eess.AS","work_id":"69a078fd-1f2a-4481-91b3-c594a0d0ed71","year":2024},"citing_paper":{"arxiv_id":"2507.02915","last_updated":"2025-06-25T08:38:27Z","snapshot_observed_at":"2026-08-08T03:45:09.219779Z","submitted_at":"2025-06-25T08:38:27Z","title":"Audio-JEPA: Joint-Embedding Predictive Architecture for Audio Representation Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T22:56:46.234160Z"},"links":{"cited_paper":"/paper/2404.06095","citing_paper":"/paper/2507.02915"},"observation_digest":"sha256:0c2229f4b038397cf5387cdca24dbf4627250afb2e0719f681b4e32583e304bb","observation_id":"79718107-558b-4fc2-916e-de189db3939b","resolution":{"observed_at":"2026-08-06T22:56:47.251153Z","resolver_source":"local_arxiv","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"}}],"links":{"evidence":"/evidence","html":"/paper/2404.06095/citation-record","integrity":"/paper/2404.06095/integrity","json":"/paper/2404.06095/citation-record.json","paper":"/paper/2404.06095"},"outbound":[],"paper":{"arxiv_id":"2404.06095","last_updated":"2024-04-09T07:57:08Z","latest_version":1,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-07T00:42:22.022720Z","submitted_at":"2024-04-09T07:57:08Z","title":"Masked Modeling Duo: Towards a Universal Audio Pre-training Framework"},"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 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2404.06095."}