{"as_of":"2026-08-10T09:47:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:29310f213ed9a2ae26b8732b3e5ea3fb57ffdb4903d6804a8683eded6a8f8797","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":"2026-08-10T06:31:04.303077+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":"2026-08-08T15:01:38.397539Z","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":"2026-07-04T17:09:58.608230Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2403.19638","last_updated":"2024-03-28T17:52:24Z","snapshot_observed_at":"2026-08-08T06:06:44.152320Z","submitted_at":"2024-03-28T17:52:24Z","title":"Siamese Vision Transformers are Scalable Audio-visual Learners","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.19638","snapshot_observed_at":"2026-08-08T15:01:38.397539Z","title":"Siamese vision transformers are scalable audio-visual learners,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.06583","last_updated":"2025-02-10T15:50:26Z","snapshot_observed_at":"2026-08-08T14:55:18.557727Z","submitted_at":"2025-02-10T15:50:26Z","title":"Adaptive Perception for Unified Visual Multi-modal Object Tracking","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-08T15:01:38.397539Z"},"links":{"cited_paper":"/paper/2403.19638","citing_paper":"/paper/2502.06583"},"observation_digest":"sha256:053b240a09b4130c079a2c4d5249aac76f1224ca122abe0a86b6247685d354f1","observation_id":"766d9f0a-ffd3-4334-8fdf-9469ea52f920","resolution":{"observed_at":"2026-08-08T15:01:38.397539Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.19638","last_updated":"2024-03-28T17:52:24Z","snapshot_observed_at":"2026-08-08T06:06:44.152320Z","submitted_at":"2024-03-28T17:52:24Z","title":"Siamese Vision Transformers are Scalable Audio-visual Learners","version":1},"cited_work":{"arxiv_id":"2403.19638","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.19638","snapshot_observed_at":"2026-07-04T17:09:58.608230Z","title":"arXiv preprint arXiv:2403.19638 (2024)","venue":null,"work_id":"0dc13936-e653-4ce7-8ba0-22615091841f","year":2024},"citing_paper":{"arxiv_id":"2606.25225","last_updated":"2026-06-23T22:48:42Z","snapshot_observed_at":"2026-08-07T15:32:28.900926Z","submitted_at":"2026-06-23T22:48:42Z","title":"MJEPA: A Simple and Scalable Joint-Embedding Predictive Architecture for Audio-Visual Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-06-25T23:57:19.880950Z"},"links":{"cited_paper":"/paper/2403.19638","citing_paper":"/paper/2606.25225"},"observation_digest":"sha256:13d7fc759e706925c3bd604aac4f8ba3ea3dcff7531dc078dc5bbfd98048fb9c","observation_id":"52598400-a27f-4d9f-9824-0b52587d667c","resolution":{"observed_at":"2026-07-04T17:09:58.609754Z","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/2403.19638/citation-record","integrity":"/paper/2403.19638/integrity","json":"/paper/2403.19638/citation-record.json","paper":"/paper/2403.19638"},"outbound":[],"paper":{"arxiv_id":"2403.19638","last_updated":"2024-03-28T17:52:24Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-08T06:06:44.152320Z","submitted_at":"2024-03-28T17:52:24Z","title":"Siamese Vision Transformers are Scalable Audio-visual Learners"},"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 2 inbound Pith citation observations for arXiv:2403.19638."}