{"as_of":"2026-08-08T21:27:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f0752bd7b3bd69912a02fb523925b7e59f79e577b54b3ecc17f34fc448b795e3","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T15:09:55.278233Z","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":"2026-08-06T19:40:07.019654Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2405.14598","last_updated":"2024-05-24T15:21:13Z","snapshot_observed_at":"2026-08-08T01:41:09.202426Z","submitted_at":"2024-05-23T14:13:16Z","title":"Visual Echoes: A Simple Unified Transformer for Audio-Visual Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.14598","snapshot_observed_at":"2026-08-07T15:09:55.278233Z","title":"Visual echoes: A simple unified transformer for audio- visual generation,","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":8,"source":"pdf_text","source_observed_at":"2026-08-07T15:09:55.278233Z"},"links":{"cited_paper":"/paper/2405.14598","citing_paper":"/paper/2505.16195"},"observation_digest":"sha256:f61643d4d605308c242e2389fec10807697fe0843f37e781b617472ae684c146","observation_id":"23d57b05-ab77-49f4-88f7-9f99a863cba2","resolution":{"observed_at":"2026-08-07T15:09:55.278233Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.14598","last_updated":"2024-05-24T15:21:13Z","snapshot_observed_at":"2026-08-08T01:41:09.202426Z","submitted_at":"2024-05-23T14:13:16Z","title":"Visual Echoes: A Simple Unified Transformer for Audio-Visual Generation","version":2},"cited_work":{"arxiv_id":"2405.14598","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.14598","snapshot_observed_at":"2026-08-06T19:40:07.019654Z","title":"Visual Echoes: A Simple Unified Transformer for Audio-Visual Generation","venue":"cs.CV","work_id":"1cb08225-16da-4cf4-8ea4-4df274224c3e","year":2024},"citing_paper":{"arxiv_id":"2507.04955","last_updated":"2025-07-07T12:56:20Z","snapshot_observed_at":"2026-08-08T07:21:10.713434Z","submitted_at":"2025-07-07T12:56:20Z","title":"EXPOTION: Facial Expression and Motion Control for Multimodal Music Generation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T19:40:02.934968Z"},"links":{"cited_paper":"/paper/2405.14598","citing_paper":"/paper/2507.04955"},"observation_digest":"sha256:d37e45cd824c928645fe17fba93e4c34e128678e8b64d431c5ed432272808372","observation_id":"3591a8b3-2211-42de-a461-5c3226339e1f","resolution":{"observed_at":"2026-08-06T19:40:07.069029Z","resolver_source":"local_arxiv","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/2405.14598/citation-record","integrity":"/paper/2405.14598/integrity","json":"/paper/2405.14598/citation-record.json","paper":"/paper/2405.14598"},"outbound":[],"paper":{"arxiv_id":"2405.14598","last_updated":"2024-05-24T15:21:13Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-08T01:41:09.202426Z","submitted_at":"2024-05-23T14:13:16Z","title":"Visual Echoes: A Simple Unified Transformer for Audio-Visual 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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2405.14598."}