{"as_of":"2026-08-07T07:32:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:bd4674391862b9cbe2f38cf7202d6e1e6bb250fc461aacb3f1c6846c4e13e154","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":"2026-08-07T06:34:17.273281+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":"2026-08-06T17:46:14.616924Z","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":"2026-07-04T20:40:07.723696Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.10591","last_updated":"2024-06-15T10:47:36Z","snapshot_observed_at":"2026-08-04T01:51:42.072498Z","submitted_at":"2024-06-15T10:47:36Z","title":"MINT: a Multi-modal Image and Narrative Text Dubbing Dataset for Foley Audio Content Planning and Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.10591","snapshot_observed_at":"2026-08-06T17:46:14.616924Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.10109","last_updated":"2025-07-14T09:50:53Z","snapshot_observed_at":"2026-08-06T17:36:51.361009Z","submitted_at":"2025-07-14T09:50:53Z","title":"DualDub: Video-to-Soundtrack Generation via Joint Speech and Background Audio Synthesis","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T17:46:14.616924Z"},"links":{"cited_paper":"/paper/2406.10591","citing_paper":"/paper/2507.10109"},"observation_digest":"sha256:ca92d9b39b4f6940d863106499318e2f1147f913d64e96adc59addc335fe382b","observation_id":"3e0bb405-fcd7-4792-a562-d92b225e889c","resolution":{"observed_at":"2026-08-06T17:46:14.616924Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.10591","last_updated":"2024-06-15T10:47:36Z","snapshot_observed_at":"2026-08-04T01:51:42.072498Z","submitted_at":"2024-06-15T10:47:36Z","title":"MINT: a Multi-modal Image and Narrative Text Dubbing Dataset for Foley Audio Content Planning and Generation","version":1},"cited_work":{"arxiv_id":"2406.10591","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.10591","snapshot_observed_at":"2026-07-04T20:40:07.723696Z","title":"Mint: a multi-modal image and narrative text dub- bing dataset for foley audio content planning and generation,","venue":null,"work_id":"1bf77ec1-45a0-4eac-a6a5-a805f3c5622d","year":2024},"citing_paper":{"arxiv_id":"2606.25980","last_updated":"2026-06-24T15:51:06Z","snapshot_observed_at":"2026-07-07T00:00:21.918469Z","submitted_at":"2026-06-24T15:51:06Z","title":"FoleySet: A Multi-Level Human-Annotated Foley Sound Dataset","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-06-25T19:56:19.179019Z"},"links":{"cited_paper":"/paper/2406.10591","citing_paper":"/paper/2606.25980"},"observation_digest":"sha256:e24d31ef66d66d3abaa429203b2a5b1a7496e3d77acbb914199ab7644b8f9428","observation_id":"71d4dcc1-d396-4d6c-a85f-0a59c8cd1fe5","resolution":{"observed_at":"2026-07-04T20:40:07.725321Z","resolver_source":"arxiv_id","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/2406.10591/citation-record","integrity":"/paper/2406.10591/integrity","json":"/paper/2406.10591/citation-record.json","paper":"/paper/2406.10591"},"outbound":[],"paper":{"arxiv_id":"2406.10591","last_updated":"2024-06-15T10:47:36Z","latest_version":1,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-04T01:51:42.072498Z","submitted_at":"2024-06-15T10:47:36Z","title":"MINT: a Multi-modal Image and Narrative Text Dubbing Dataset for Foley Audio Content Planning and Generation"},"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 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2406.10591."}