{"as_of":"2026-08-11T06:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6d6460a3e6371690698fc5c14fece70f64a604ff16b6b4257b881b56b32ff18a","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":"2026-08-11T06:34:44.6726+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":"2026-08-11T06:05:02.260879Z","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":"2026-08-09T13:02:30.554419Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.10749","last_updated":"2024-12-14T08:34:44Z","snapshot_observed_at":"2026-07-06T20:07:01.648579Z","submitted_at":"2024-12-14T08:34:44Z","title":"Patch-level Sounding Object Tracking for Audio-Visual Question Answering","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.10749","snapshot_observed_at":"2026-08-11T06:05:02.260879Z","title":"Patch-level sounding object tracking for audio-visual question answering,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.16904","last_updated":"2024-12-22T07:37:13Z","snapshot_observed_at":"2026-08-11T05:57:40.737146Z","submitted_at":"2024-12-22T07:37:13Z","title":"Temporal-Frequency State Space Duality: An Efficient Paradigm for Speech Emotion Recognition","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:02.260879Z"},"links":{"cited_paper":"/paper/2412.10749","citing_paper":"/paper/2412.16904"},"observation_digest":"sha256:fcbc7b1aedbac75071567b47c1fef774d2dbbd360738a0ed6cd13217f971e0dc","observation_id":"a3e56950-e7cc-4896-84e2-f034a8d47ce7","resolution":{"observed_at":"2026-08-11T06:05:02.260879Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.10749","last_updated":"2024-12-14T08:34:44Z","snapshot_observed_at":"2026-07-06T20:07:01.648579Z","submitted_at":"2024-12-14T08:34:44Z","title":"Patch-level Sounding Object Tracking for Audio-Visual Question Answering","version":1},"cited_work":{"arxiv_id":"2412.10749","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.10749","snapshot_observed_at":"2026-08-09T13:02:30.554419Z","title":"Patch-level Sounding Object Tracking for Audio-Visual Question Answering","venue":"cs.MM","work_id":"018f06e7-5b12-478e-b780-4ea35c7a5f7d","year":2024},"citing_paper":{"arxiv_id":"2502.02196","last_updated":"2025-02-04T10:21:28Z","snapshot_observed_at":"2026-08-10T00:59:06.822803Z","submitted_at":"2025-02-04T10:21:28Z","title":"Exploiting Ensemble Learning for Cross-View Isolated Sign Language Recognition","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-09T13:02:30.317199Z"},"links":{"cited_paper":"/paper/2412.10749","citing_paper":"/paper/2502.02196"},"observation_digest":"sha256:5042f7dd527ff207efb66226bc3aca8c258f804be52522aed365bc24727532cf","observation_id":"0bf21e0f-49fd-4abd-9f80-c1a53ed69708","resolution":{"observed_at":"2026-08-09T13:02:30.558009Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2412.10749/citation-record","integrity":"/paper/2412.10749/integrity","json":"/paper/2412.10749/citation-record.json","paper":"/paper/2412.10749"},"outbound":[],"paper":{"arxiv_id":"2412.10749","last_updated":"2024-12-14T08:34:44Z","latest_version":1,"primary_category":"cs.MM","snapshot_observed_at":"2026-07-06T20:07:01.648579Z","submitted_at":"2024-12-14T08:34:44Z","title":"Patch-level Sounding Object Tracking for Audio-Visual Question Answering"},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2412.10749."}