{"as_of":"2026-08-07T01:02:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5cfdfad2b99c59ac830e207c297c6d86a2ec98e0a2c05687a982023f9dd89700","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":"2026-08-06T06:34:29.942622+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":"2026-08-07T00:23:16.841565Z","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":"2026-08-07T00:23:19.246908Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2411.18953","last_updated":"2024-11-28T06:50:13Z","snapshot_observed_at":"2026-07-06T19:58:22.387205Z","submitted_at":"2024-11-28T06:50:13Z","title":"AudioSetCaps: An Enriched Audio-Caption Dataset using Automated Generation Pipeline with Large Audio and Language Models","version":1},"cited_work":{"arxiv_id":"2411.18953","doi":null,"metadata_source":"pith","pith_arxiv_id":"2411.18953","snapshot_observed_at":"2026-08-07T00:23:19.246908Z","title":"AudioSetCaps: An Enriched Audio-Caption Dataset using Automated Generation Pipeline with Large Audio and Language Models","venue":"eess.AS","work_id":"0fed9bee-d6f1-498a-be0d-6fe82dafded4","year":2024},"citing_paper":{"arxiv_id":"2506.14445","last_updated":"2025-06-17T12:10:19Z","snapshot_observed_at":"2026-08-07T00:15:30.364862Z","submitted_at":"2025-06-17T12:10:19Z","title":"Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T00:23:16.841565Z"},"links":{"cited_paper":"/paper/2411.18953","citing_paper":"/paper/2506.14445"},"observation_digest":"sha256:384cd97fc3969a226aa46f832fbb31ab0e8240aa43e4c2d618423d55a81f7d9a","observation_id":"d4795b6c-b14e-4649-ba61-c559c05a85d5","resolution":{"observed_at":"2026-08-07T00:23:19.253506Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.18953","last_updated":"2024-11-28T06:50:13Z","snapshot_observed_at":"2026-07-06T19:58:22.387205Z","submitted_at":"2024-11-28T06:50:13Z","title":"AudioSetCaps: An Enriched Audio-Caption Dataset using Automated Generation Pipeline with Large Audio and Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.18953","snapshot_observed_at":"2026-08-01T14:46:34.886995Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18666","last_updated":"2026-07-21T03:25:34Z","snapshot_observed_at":"2026-08-06T07:56:47.796949Z","submitted_at":"2026-07-21T03:25:34Z","title":"Fusion Embedding: A Unified Embedding Space for Text, Image, Video, and Audio","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-01T14:46:34.886995Z"},"links":{"cited_paper":"/paper/2411.18953","citing_paper":"/paper/2607.18666"},"observation_digest":"sha256:bf096b9bdae3dbd67b28ddc0704d7285645cbb39b35b908f77ac29ab58cd4f16","observation_id":"03c50d2d-29da-42ee-90ed-d6ba7bb606b0","resolution":{"observed_at":"2026-08-01T14:46:34.886995Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2411.18953/citation-record","integrity":"/paper/2411.18953/integrity","json":"/paper/2411.18953/citation-record.json","paper":"/paper/2411.18953"},"outbound":[],"paper":{"arxiv_id":"2411.18953","last_updated":"2024-11-28T06:50:13Z","latest_version":1,"primary_category":"eess.AS","snapshot_observed_at":"2026-07-06T19:58:22.387205Z","submitted_at":"2024-11-28T06:50:13Z","title":"AudioSetCaps: An Enriched Audio-Caption Dataset using Automated Generation Pipeline with Large Audio and Language Models"},"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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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:2411.18953."}