{"as_of":"2026-08-09T00:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f68c8eb82927cb051148330af67f0766780899e8787de5d2b5bdfa94dfee7df3","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T00:23:08.197960Z","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":"2026-07-03T13:28:18.768732Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2411.05679","last_updated":"2025-04-04T21:50:29Z","snapshot_observed_at":"2026-07-06T19:47:30.083298Z","submitted_at":"2024-11-08T16:29:07Z","title":"Tell What You Hear From What You See -- Video to Audio Generation Through Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.05679","snapshot_observed_at":"2026-08-09T00:23:08.197960Z","title":"Tell what you hear from what you see–video to audio generation through text,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.03897","last_updated":"2025-07-07T10:40:56Z","snapshot_observed_at":"2026-08-09T00:16:57.664764Z","submitted_at":"2025-02-06T09:18:30Z","title":"UniForm: A Unified Multi-Task Diffusion Transformer for Audio-Video Generation","version":5},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-09T00:23:08.197960Z"},"links":{"cited_paper":"/paper/2411.05679","citing_paper":"/paper/2502.03897"},"observation_digest":"sha256:bfbb74e8a21538018e7f7b3045de6b8486c2d3950c8e372cc201b5f13fa66008","observation_id":"bd44a722-c613-4d0f-a766-13a72221c16e","resolution":{"observed_at":"2026-08-09T00:23:08.197960Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.05679","last_updated":"2025-04-04T21:50:29Z","snapshot_observed_at":"2026-07-06T19:47:30.083298Z","submitted_at":"2024-11-08T16:29:07Z","title":"Tell What You Hear From What You See -- Video to Audio Generation Through Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.05679","snapshot_observed_at":"2026-08-07T15:09:55.988743Z","title":"Tell what you hear from what you see– video to audio generation through text,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.16195","last_updated":"2025-07-17T19:01:00Z","snapshot_observed_at":"2026-08-07T16:55:17.995778Z","submitted_at":"2025-05-22T03:58:16Z","title":"SpecMaskFoley: Steering Pretrained Spectral Masked Generative Transformer Toward Synchronized Video-to-audio Synthesis via ControlNet","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T15:09:55.988743Z"},"links":{"cited_paper":"/paper/2411.05679","citing_paper":"/paper/2505.16195"},"observation_digest":"sha256:9ac3c699b25dfe02e097a48d06039494e8111fb899c2acfb450d0d6599ac5e8b","observation_id":"0dd4b443-d5f0-4fa6-a51c-394681685a84","resolution":{"observed_at":"2026-08-07T15:09:55.988743Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.05679","last_updated":"2025-04-04T21:50:29Z","snapshot_observed_at":"2026-07-06T19:47:30.083298Z","submitted_at":"2024-11-08T16:29:07Z","title":"Tell What You Hear From What You See -- Video to Audio Generation Through Text","version":3},"cited_work":{"arxiv_id":"2411.05679","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.05679","snapshot_observed_at":"2026-07-03T13:28:18.768732Z","title":"Tell what you hear from what you see–video to audio generation through text","venue":null,"work_id":"60551585-a0be-4436-9377-aa8bbf6f6fa5","year":2024},"citing_paper":{"arxiv_id":"2510.09065","last_updated":"2026-04-17T15:00:46Z","snapshot_observed_at":"2026-07-06T22:32:17.816175Z","submitted_at":"2025-10-10T07:13:06Z","title":"MMAudioSep: Taming Video-to-Audio Generative Model Towards Video/Text-Queried Sound Separation","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-18T08:20:02.986562Z"},"links":{"cited_paper":"/paper/2411.05679","citing_paper":"/paper/2510.09065"},"observation_digest":"sha256:913af508924319baf883110882779add6d68fedc3863e2d8f841305324d27bcf","observation_id":"3f90ac27-c90c-4a0d-86ed-52635f83d628","resolution":{"observed_at":"2026-05-18T08:21:06.822114Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.05679","last_updated":"2025-04-04T21:50:29Z","snapshot_observed_at":"2026-07-06T19:47:30.083298Z","submitted_at":"2024-11-08T16:29:07Z","title":"Tell What You Hear From What You See -- Video to Audio Generation Through Text","version":3},"cited_work":{"arxiv_id":"2411.05679","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.05679","snapshot_observed_at":"2026-07-03T13:28:18.768732Z","title":"Tell what you hear from what you see–video to audio generation through text","venue":null,"work_id":"60551585-a0be-4436-9377-aa8bbf6f6fa5","year":2024},"citing_paper":{"arxiv_id":"2606.12555","last_updated":"2026-07-02T19:10:03Z","snapshot_observed_at":"2026-07-12T14:16:32.755376Z","submitted_at":"2026-06-10T18:06:27Z","title":"AudioX-Turbo: A Unified Framework for Efficient Anything-to-Audio Generation","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-06-27T08:04:48.283908Z"},"links":{"cited_paper":"/paper/2411.05679","citing_paper":"/paper/2606.12555"},"observation_digest":"sha256:eab768023f9676aadc705a767f87273dee49cd4d1f892f7749362858fbb2bb35","observation_id":"aaf8c426-8722-433a-8e88-0f54fab4850c","resolution":{"observed_at":"2026-07-03T13:28:18.770490Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2411.05679/citation-record","integrity":"/paper/2411.05679/integrity","json":"/paper/2411.05679/citation-record.json","paper":"/paper/2411.05679"},"outbound":[],"paper":{"arxiv_id":"2411.05679","last_updated":"2025-04-04T21:50:29Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T19:47:30.083298Z","submitted_at":"2024-11-08T16:29:07Z","title":"Tell What You Hear From What You See -- Video to Audio Generation Through Text"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2411.05679."}