{"as_of":"2026-08-23T04:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f7970dd7a4a59ec947b4d3c06295456b0dd4dadfe2e807d0782e96f4e178f5dc","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":"2026-08-22T06:32:14.747728+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":"2026-08-15T23:14:57.700621Z","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":"2026-05-15T07:39:50.461225Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2401.02584","last_updated":"2024-07-17T06:11:43Z","snapshot_observed_at":"2026-08-21T12:51:48.943019Z","submitted_at":"2024-01-05T00:27:32Z","title":"Towards Weakly Supervised Text-to-Audio Grounding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.02584","snapshot_observed_at":"2026-08-11T05:01:38.702238Z","title":"Towards weakly supervised text-to- audio grounding,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.18157","last_updated":"2024-12-24T04:29:46Z","snapshot_observed_at":"2026-08-19T11:45:47.754463Z","submitted_at":"2024-12-24T04:29:46Z","title":"Smooth-Foley: Creating Continuous Sound for Video-to-Audio Generation Under Semantic Guidance","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T05:01:38.702238Z"},"links":{"cited_paper":"/paper/2401.02584","citing_paper":"/paper/2412.18157"},"observation_digest":"sha256:bad9bd5a43fbceb7d171aa3074cd908ca1b4f0af49577aabb7574cd69f34066e","observation_id":"7d0daffe-6166-48ba-a9fb-836f29a9d52f","resolution":{"observed_at":"2026-08-11T05:01:38.702238Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.02584","last_updated":"2024-07-17T06:11:43Z","snapshot_observed_at":"2026-08-21T12:51:48.943019Z","submitted_at":"2024-01-05T00:27:32Z","title":"Towards Weakly Supervised Text-to-Audio Grounding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.02584","snapshot_observed_at":"2026-08-15T23:14:57.700621Z","title":"Towards weakly supervised text-to-audio grounding.arXiv preprint arXiv:2401.02584,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.05335","last_updated":"2025-06-08T18:21:26Z","snapshot_observed_at":"2026-08-21T12:51:56.879148Z","submitted_at":"2025-05-08T15:27:43Z","title":"FLAM: Frame-Wise Language-Audio Modeling","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T23:14:57.700621Z"},"links":{"cited_paper":"/paper/2401.02584","citing_paper":"/paper/2505.05335"},"observation_digest":"sha256:c03b6d526548da1402a2411acbf12912bd06f33313b7c2e44b0814929b2b3612","observation_id":"732d6036-e9da-45dc-aad2-a9ff31ac24fd","resolution":{"observed_at":"2026-08-15T23:14:57.700621Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.02584","last_updated":"2024-07-17T06:11:43Z","snapshot_observed_at":"2026-08-21T12:51:48.943019Z","submitted_at":"2024-01-05T00:27:32Z","title":"Towards Weakly Supervised Text-to-Audio Grounding","version":2},"cited_work":{"arxiv_id":"2401.02584","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2401.02584","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Towards weakly supervised text-to-audio grounding","venue":null,"work_id":"af8ea266-ea3e-48b8-87b8-caa2b55f0f13","year":2024},"citing_paper":{"arxiv_id":"2603.19857","last_updated":"2026-04-18T07:29:42Z","snapshot_observed_at":"2026-08-11T06:30:51.892484Z","submitted_at":"2026-03-20T11:19:29Z","title":"FoleyDirector: Fine-Grained Temporal Steering for Video-to-Audio Generation via Structured Scripts","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-15T07:35:14.257562Z"},"links":{"cited_paper":"/paper/2401.02584","citing_paper":"/paper/2603.19857"},"observation_digest":"sha256:e6d1361d41010f2e81ad4a1737fd6fa428f6e0dcee2ef13862ae334cb673598c","observation_id":"d246dbf2-cd28-4dbc-91ce-caf561cb1524","resolution":{"observed_at":"2026-05-15T07:39:50.464018Z","resolver_source":"arxiv_id","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"}}],"links":{"evidence":"/evidence","html":"/paper/2401.02584/citation-record","integrity":"/paper/2401.02584/integrity","json":"/paper/2401.02584/citation-record.json","paper":"/paper/2401.02584"},"outbound":[],"paper":{"arxiv_id":"2401.02584","last_updated":"2024-07-17T06:11:43Z","latest_version":2,"primary_category":"cs.SD","snapshot_observed_at":"2026-08-21T12:51:48.943019Z","submitted_at":"2024-01-05T00:27:32Z","title":"Towards Weakly Supervised Text-to-Audio Grounding"},"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 23 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2401.02584."}