{"as_of":"2026-08-07T17:38:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ae5a6f84490d285c597792785487ee090248ca92712e5e8c05f0aa7aa22e4d31","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":"2026-08-07T06:34:17.273281+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":"2026-08-07T10:27:05.560273Z","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":"2026-08-07T05:49:54.266142Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2503.13068","last_updated":"2025-03-17T11:19:03Z","snapshot_observed_at":"2026-08-07T16:58:15.380194Z","submitted_at":"2025-03-17T11:19:03Z","title":"Crab: A Unified Audio-Visual Scene Understanding Model with Explicit Cooperation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.13068","snapshot_observed_at":"2026-08-07T10:27:05.560273Z","title":"Crab: A unified audio-visual scene understanding model with explicit cooperation.arXiv preprint arXiv:2503.13068, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.05328","last_updated":"2025-07-22T07:00:35Z","snapshot_observed_at":"2026-08-07T11:49:44.536475Z","submitted_at":"2025-06-05T17:58:33Z","title":"AV-Reasoner: Improving and Benchmarking Clue-Grounded Audio-Visual Counting for MLLMs","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T10:27:05.560273Z"},"links":{"cited_paper":"/paper/2503.13068","citing_paper":"/paper/2506.05328"},"observation_digest":"sha256:436a835492f79c0981b42c7fbc792b5811d60c404c2a0eec0f62baae05b59445","observation_id":"18af2022-4246-4367-be8f-081bb7661fe2","resolution":{"observed_at":"2026-08-07T10:27:05.560273Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.13068","last_updated":"2025-03-17T11:19:03Z","snapshot_observed_at":"2026-08-07T16:58:15.380194Z","submitted_at":"2025-03-17T11:19:03Z","title":"Crab: A Unified Audio-Visual Scene Understanding Model with Explicit Cooperation","version":1},"cited_work":{"arxiv_id":"2503.13068","doi":null,"metadata_source":"pith","pith_arxiv_id":"2503.13068","snapshot_observed_at":"2026-08-07T05:49:54.266142Z","title":"Crab: A Unified Audio-Visual Scene Understanding Model with Explicit Cooperation","venue":"cs.CV","work_id":"cc5d08c3-8694-4a65-9989-da9f40af3197","year":2025},"citing_paper":{"arxiv_id":"2506.07016","last_updated":"2025-06-13T19:05:47Z","snapshot_observed_at":"2026-08-07T11:48:30.543139Z","submitted_at":"2025-06-08T06:34:29Z","title":"MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T05:49:53.235638Z"},"links":{"cited_paper":"/paper/2503.13068","citing_paper":"/paper/2506.07016"},"observation_digest":"sha256:3c91859823c89f3b4ab3dfea6227f0a5857e45f6f6146cc43a812bf3b09d2cf7","observation_id":"c9c349f6-6edd-46a0-bdcb-665277de79c7","resolution":{"observed_at":"2026-08-07T05:49:54.269852Z","resolver_source":"local_arxiv","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"}}],"links":{"evidence":"/evidence","html":"/paper/2503.13068/citation-record","integrity":"/paper/2503.13068/integrity","json":"/paper/2503.13068/citation-record.json","paper":"/paper/2503.13068"},"outbound":[],"paper":{"arxiv_id":"2503.13068","last_updated":"2025-03-17T11:19:03Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T16:58:15.380194Z","submitted_at":"2025-03-17T11:19:03Z","title":"Crab: A Unified Audio-Visual Scene Understanding Model with Explicit Cooperation"},"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 2 inbound Pith citation observations for arXiv:2503.13068."}