{"as_of":"2026-08-13T06:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c9f4aa1008ecca8227077ea92d7019d03286ea4a4315cf079cf9795d28c8cb1a","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T10:46:23.499141Z","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":"2026-08-05T05:01:37.362509Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2407.06947","last_updated":"2025-01-08T15:54:39Z","snapshot_observed_at":"2026-08-12T23:25:44.676749Z","submitted_at":"2024-07-09T15:23:35Z","title":"Audio-Language Datasets of Scenes and Events: A Survey","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.06947","snapshot_observed_at":"2026-08-12T10:46:23.499141Z","title":"Audio- language datasets of scenes and events: A survey,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.18953","last_updated":"2024-11-28T06:50:13Z","snapshot_observed_at":"2026-08-13T05:00:42.428982Z","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},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T10:46:23.499141Z"},"links":{"cited_paper":"/paper/2407.06947","citing_paper":"/paper/2411.18953"},"observation_digest":"sha256:61c6927cad7b5ddae76b59479dd920d6719937a6383728a8b31f5ef736ed764a","observation_id":"70798fde-685b-4eb8-8f9d-94e74084282b","resolution":{"observed_at":"2026-08-12T10:46:23.499141Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.06947","last_updated":"2025-01-08T15:54:39Z","snapshot_observed_at":"2026-08-12T23:25:44.676749Z","submitted_at":"2024-07-09T15:23:35Z","title":"Audio-Language Datasets of Scenes and Events: A Survey","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.06947","snapshot_observed_at":"2026-08-10T14:36:19.182620Z","title":"Audio-Language Datasets of Scenes and Events: A Survey,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.15177","last_updated":"2026-07-03T16:46:09Z","snapshot_observed_at":"2026-08-10T17:21:32.264725Z","submitted_at":"2025-01-25T11:15:06Z","title":"Audio-Language Models for Audio-Centric Tasks: A Systematic Survey","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T14:36:19.182620Z"},"links":{"cited_paper":"/paper/2407.06947","citing_paper":"/paper/2501.15177"},"observation_digest":"sha256:bd361a90735e565e24322848a85146784e80452955aa02d8bc6e7e3081cbe3c7","observation_id":"c12161ed-ee77-4d57-8fa2-de2e17ddc279","resolution":{"observed_at":"2026-08-10T14:36:19.182620Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.06947","last_updated":"2025-01-08T15:54:39Z","snapshot_observed_at":"2026-08-12T23:25:44.676749Z","submitted_at":"2024-07-09T15:23:35Z","title":"Audio-Language Datasets of Scenes and Events: A Survey","version":2},"cited_work":{"arxiv_id":"2407.06947","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.06947","snapshot_observed_at":"2026-08-05T05:01:37.362509Z","title":"Audio-Language Datasets of Scenes and Events: A Survey","venue":"cs.SD","work_id":"c3be00f1-0447-450b-b07d-d5fa1a8c8246","year":2024},"citing_paper":{"arxiv_id":"2509.05786","last_updated":"2025-09-06T17:42:22Z","snapshot_observed_at":"2026-08-10T04:42:02.831696Z","submitted_at":"2025-09-06T17:42:22Z","title":"Effectively obtaining acoustic, visual and textual data from videos","version":1},"reference_index":117,"source":"pdf_text","source_observed_at":"2026-08-05T05:01:37.068858Z"},"links":{"cited_paper":"/paper/2407.06947","citing_paper":"/paper/2509.05786"},"observation_digest":"sha256:2c84d3b1bc33e6b608fa381a99465c9a69e907b712c122eb294a88e7027c666b","observation_id":"5ad55894-4ffc-4011-8562-5b149b76c111","resolution":{"observed_at":"2026-08-05T05:01:37.369824Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2407.06947/citation-record","integrity":"/paper/2407.06947/integrity","json":"/paper/2407.06947/citation-record.json","paper":"/paper/2407.06947"},"outbound":[],"paper":{"arxiv_id":"2407.06947","last_updated":"2025-01-08T15:54:39Z","latest_version":2,"primary_category":"cs.SD","snapshot_observed_at":"2026-08-12T23:25:44.676749Z","submitted_at":"2024-07-09T15:23:35Z","title":"Audio-Language Datasets of Scenes and Events: A Survey"},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2407.06947."}