{"as_of":"2026-08-07T23:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0f189885471ca3f8fb562682e0811c2cbcd9ecb4e0045c38806408f6ed481015","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":"2026-08-07T06:34:17.273281+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":"2026-08-07T10:28:52.514103Z","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":"2026-05-23T17:33:15.718468Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2403.04640","last_updated":"2024-03-07T16:31:02Z","snapshot_observed_at":"2026-08-03T18:43:24.966971Z","submitted_at":"2024-03-07T16:31:02Z","title":"CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios","version":1},"cited_work":{"arxiv_id":"2403.04640","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.04640","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Cat: enhancing multimodal large language model to answer questions in dynamic audio-visual scenarios","venue":null,"work_id":"aa6669f8-0c40-4da1-bfc1-724471536276","year":2024},"citing_paper":{"arxiv_id":"2404.16994","last_updated":"2024-04-29T14:52:02Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-04-25T19:29:55Z","title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-05-15T20:21:57.873354Z"},"links":{"cited_paper":"/paper/2403.04640","citing_paper":"/paper/2404.16994"},"observation_digest":"sha256:5e376c526594645420a5bcf02dccf4a787de5be06c800b07c279bfa6731cc1fe","observation_id":"478af2b7-22ec-4f16-af64-7667eb3794cf","resolution":{"observed_at":"2026-05-15T20:21:58.038974Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2403.04640","last_updated":"2024-03-07T16:31:02Z","snapshot_observed_at":"2026-08-03T18:43:24.966971Z","submitted_at":"2024-03-07T16:31:02Z","title":"CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios","version":1},"cited_work":{"arxiv_id":"2403.04640","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.04640","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Cat: enhancing multimodal large language model to answer questions in dynamic audio-visual scenarios","venue":null,"work_id":"aa6669f8-0c40-4da1-bfc1-724471536276","year":2024},"citing_paper":{"arxiv_id":"2411.02327","last_updated":"2026-05-01T17:44:24Z","snapshot_observed_at":"2026-07-06T19:45:00.034364Z","submitted_at":"2024-11-04T17:50:36Z","title":"PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance","version":4},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-23T17:31:59.030963Z"},"links":{"cited_paper":"/paper/2403.04640","citing_paper":"/paper/2411.02327"},"observation_digest":"sha256:c551a3bd5c19950a26829fb7711187a190ba07540cc8eb503e239505068f11ef","observation_id":"a37cdb24-04e9-4629-941b-eb8447461fd4","resolution":{"observed_at":"2026-05-23T17:33:15.721769Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2403.04640","last_updated":"2024-03-07T16:31:02Z","snapshot_observed_at":"2026-08-03T18:43:24.966971Z","submitted_at":"2024-03-07T16:31:02Z","title":"CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.04640","snapshot_observed_at":"2026-08-07T10:28:52.514103Z","title":"Cat: enhancing multimodal large language model to answer questions in dynamic audio-visual scenarios.arXiv preprint arXiv:2403.04640, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.05260","last_updated":"2025-06-05T17:21:16Z","snapshot_observed_at":"2026-08-07T10:19:37.470353Z","submitted_at":"2025-06-05T17:21:16Z","title":"LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-07T10:28:52.514103Z"},"links":{"cited_paper":"/paper/2403.04640","citing_paper":"/paper/2506.05260"},"observation_digest":"sha256:1a8da87d71b7cd729a60d947978855feb14ea61db52c0d5d9b296f4612d292b2","observation_id":"5518530f-bb48-4847-adfb-cf52eff7b58f","resolution":{"observed_at":"2026-08-07T10:28:52.514103Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2403.04640/citation-record","integrity":"/paper/2403.04640/integrity","json":"/paper/2403.04640/citation-record.json","paper":"/paper/2403.04640"},"outbound":[],"paper":{"arxiv_id":"2403.04640","last_updated":"2024-03-07T16:31:02Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-03T18:43:24.966971Z","submitted_at":"2024-03-07T16:31:02Z","title":"CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios"},"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 3 inbound Pith citation observations for arXiv:2403.04640."}