{"as_of":"2026-08-10T17:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9bbb6fcd1b767a0bd7bcadac64625451976980f6eff3a5e9cbb9f674e7af7ac9","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":"2026-08-10T06:31:04.303077+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":"2026-08-06T13:12:40.512824Z","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":"2026-07-02T17:27:15.584784Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.11775","last_updated":"2025-02-17T13:07:40Z","snapshot_observed_at":"2026-08-09T14:00:25.020138Z","submitted_at":"2025-02-17T13:07:40Z","title":"video-SALMONN-o1: Reasoning-enhanced Audio-visual Large Language Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.11775","snapshot_observed_at":"2026-08-06T13:12:40.512824Z","title":"video- salmonn-o1: Reasoning-enhanced audio-visual large language model.arXiv preprint arXiv:2502.11775,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.20939","last_updated":"2025-07-28T15:52:36Z","snapshot_observed_at":"2026-08-10T06:10:12.904760Z","submitted_at":"2025-07-28T15:52:36Z","title":"ARC-Hunyuan-Video-7B: Structured Video Comprehension of Real-World Shorts","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T13:12:40.512824Z"},"links":{"cited_paper":"/paper/2502.11775","citing_paper":"/paper/2507.20939"},"observation_digest":"sha256:c46093c4579ad4e868a78c5fa34557ee6d554605ff8134126f90db755ce85e82","observation_id":"f9929eab-f34d-4ddf-99e4-742369172e99","resolution":{"observed_at":"2026-08-06T13:12:40.512824Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.11775","last_updated":"2025-02-17T13:07:40Z","snapshot_observed_at":"2026-08-09T14:00:25.020138Z","submitted_at":"2025-02-17T13:07:40Z","title":"video-SALMONN-o1: Reasoning-enhanced Audio-visual Large Language Model","version":1},"cited_work":{"arxiv_id":"2502.11775","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.11775","snapshot_observed_at":"2026-07-02T17:27:15.584784Z","title":"video-salmonn-o1: Reasoning-enhanced audio-visual large language model","venue":null,"work_id":"5d599dfd-f96a-48d3-969e-63f87f0e3e73","year":2025},"citing_paper":{"arxiv_id":"2604.24317","last_updated":"2026-04-27T11:07:03Z","snapshot_observed_at":"2026-07-06T23:10:24.992210Z","submitted_at":"2026-04-27T11:07:03Z","title":"Don't Pause! Every prediction matters in a streaming video","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-05-08T04:32:01.379605Z"},"links":{"cited_paper":"/paper/2502.11775","citing_paper":"/paper/2604.24317"},"observation_digest":"sha256:8343b1ccc335adba41e068c52a8f26776e86655d7998ebcfdb08955d7708b0ad","observation_id":"7c6f1db6-991e-4db1-bcd2-5aa8ccc26fa3","resolution":{"observed_at":"2026-05-11T21:41:17.930806Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.11775","last_updated":"2025-02-17T13:07:40Z","snapshot_observed_at":"2026-08-09T14:00:25.020138Z","submitted_at":"2025-02-17T13:07:40Z","title":"video-SALMONN-o1: Reasoning-enhanced Audio-visual Large Language Model","version":1},"cited_work":{"arxiv_id":"2502.11775","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.11775","snapshot_observed_at":"2026-07-02T17:27:15.584784Z","title":"video-salmonn-o1: Reasoning-enhanced audio-visual large language model","venue":null,"work_id":"5d599dfd-f96a-48d3-969e-63f87f0e3e73","year":2025},"citing_paper":{"arxiv_id":"2606.07433","last_updated":"2026-06-05T16:29:13Z","snapshot_observed_at":"2026-08-01T21:05:06.439607Z","submitted_at":"2026-06-05T16:29:13Z","title":"Watch, Remember, Reason: Human-View Video Understanding with MLLMs","version":1},"reference_index":217,"source":"pdf_text","source_observed_at":"2026-06-27T22:00:28.350003Z"},"links":{"cited_paper":"/paper/2502.11775","citing_paper":"/paper/2606.07433"},"observation_digest":"sha256:335414c0a163aa0de8c55b2e72ba114b1af401adbe0515ecb34c06df79b3b3ee","observation_id":"b4c2268c-b6d4-4d87-a82c-7a7e7247923c","resolution":{"observed_at":"2026-07-02T17:27:15.586256Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2502.11775/citation-record","integrity":"/paper/2502.11775/integrity","json":"/paper/2502.11775/citation-record.json","paper":"/paper/2502.11775"},"outbound":[],"paper":{"arxiv_id":"2502.11775","last_updated":"2025-02-17T13:07:40Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T14:00:25.020138Z","submitted_at":"2025-02-17T13:07:40Z","title":"video-SALMONN-o1: Reasoning-enhanced Audio-visual Large Language Model"},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2502.11775."}