{"as_of":"2026-08-05T21:38:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:107c93decea792e2303a39b278184a603cd7c9101d4f8714b925b4ff3556d099","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":"2026-08-05T06:32:48.257954+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":"2026-08-01T07:12:12.988342Z","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":"2026-05-17T00:50:13.938169Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2409.18042","last_updated":"2025-03-20T08:47:39Z","snapshot_observed_at":"2026-08-03T18:53:30.527385Z","submitted_at":"2024-09-26T16:44:02Z","title":"EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions","version":4},"cited_work":{"arxiv_id":"2409.18042","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2409.18042","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"b7580389-8cda-4c92-8db6-b59aef233691","year":2024},"citing_paper":{"arxiv_id":"2410.17196","last_updated":"2024-12-11T15:45:21Z","snapshot_observed_at":"2026-07-06T19:37:56.214143Z","submitted_at":"2024-10-22T17:15:20Z","title":"VoiceBench: Benchmarking LLM-Based Voice Assistants","version":3},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-05-17T00:50:13.841689Z"},"links":{"cited_paper":"/paper/2409.18042","citing_paper":"/paper/2410.17196"},"observation_digest":"sha256:32818704ffcf77986ecd1e9e6b3236c7cf5e993900e101e0be403413cec498d3","observation_id":"9d0958cb-b41e-4f06-ad3b-cfb81e1d753f","resolution":{"observed_at":"2026-05-17T00:50:13.940657Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.18042","last_updated":"2025-03-20T08:47:39Z","snapshot_observed_at":"2026-08-03T18:53:30.527385Z","submitted_at":"2024-09-26T16:44:02Z","title":"EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.18042","snapshot_observed_at":"2026-07-12T19:28:32.792370Z","title":"Internomni: Extending internvl with audio modality,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.05177","last_updated":"2026-04-17T12:31:17Z","snapshot_observed_at":"2026-08-02T21:40:51.010741Z","submitted_at":"2026-04-17T12:31:17Z","title":"MCBench: A Multicontext Safety Assessment Benchmark for Omni Large Language Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-12T19:28:32.792370Z"},"links":{"cited_paper":"/paper/2409.18042","citing_paper":"/paper/2606.05177"},"observation_digest":"sha256:0ef0b2b9968d8d9d0b3d711da828271c48af2279a21a99ccf8b3fb2d9191db69","observation_id":"047c6f91-bf8e-4dd3-b40d-9c1b001d6043","resolution":{"observed_at":"2026-07-12T19:28:32.792370Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.18042","last_updated":"2025-03-20T08:47:39Z","snapshot_observed_at":"2026-08-03T18:53:30.527385Z","submitted_at":"2024-09-26T16:44:02Z","title":"EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.18042","snapshot_observed_at":"2026-08-01T07:12:12.988342Z","title":"arXiv preprint arXiv:2409.18042 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.21550","last_updated":"2026-07-23T17:35:20Z","snapshot_observed_at":"2026-08-03T11:55:30.881091Z","submitted_at":"2026-07-23T17:35:20Z","title":"X$^3$-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment","version":1},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-01T07:12:12.988342Z"},"links":{"cited_paper":"/paper/2409.18042","citing_paper":"/paper/2607.21550"},"observation_digest":"sha256:0d79c29fd16ee087c9cb9aac6eb18152d51b8e0c869e2a111429cfafa9811500","observation_id":"d65ae3e8-d898-4b20-bd84-c976d9391b04","resolution":{"observed_at":"2026-08-01T07:12:12.988342Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2409.18042/citation-record","integrity":"/paper/2409.18042/integrity","json":"/paper/2409.18042/citation-record.json","paper":"/paper/2409.18042"},"outbound":[],"paper":{"arxiv_id":"2409.18042","last_updated":"2025-03-20T08:47:39Z","latest_version":4,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-03T18:53:30.527385Z","submitted_at":"2024-09-26T16:44:02Z","title":"EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions"},"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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2409.18042."}