{"as_of":"2026-08-18T17:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4b81d9c71910eed38932657d637097800e6cf6d490ad677086f8b53c2cfb5cdd","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":1,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":1,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T15:03:07.916668Z","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":"2026-08-09T15:03:08.001423Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2407.06606","last_updated":"2025-05-06T08:24:18Z","snapshot_observed_at":"2026-08-18T08:41:38.308587Z","submitted_at":"2024-07-09T07:15:56Z","title":"Tailored Design of Audio-Visual Speech Recognition Models using Branchformers","version":4},"cited_work":{"arxiv_id":"2407.06606","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.06606","snapshot_observed_at":"2026-08-09T15:03:08.001423Z","title":"Tailored Design of Audio-Visual Speech Recognition Models using Branchformers","venue":"cs.CV","work_id":"9e023ef5-8d3e-4419-9609-25924dee17b2","year":2024},"citing_paper":{"arxiv_id":"2502.01547","last_updated":"2025-05-07T13:06:56Z","snapshot_observed_at":"2026-08-17T16:55:09.443445Z","submitted_at":"2025-02-03T17:29:52Z","title":"mWhisper-Flamingo for Multilingual Audio-Visual Noise-Robust Speech Recognition","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-09T15:03:07.916668Z"},"links":{"cited_paper":"/paper/2407.06606","citing_paper":"/paper/2502.01547"},"observation_digest":"sha256:867456b152807861e60a01028fbc7509171245d60e8d01f89a9b1f41aaed1159","observation_id":"4404c09d-99be-479d-be85-4e0fa608f3ef","resolution":{"observed_at":"2026-08-09T15:03:08.009407Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2407.06606/citation-record","integrity":"/paper/2407.06606/integrity","json":"/paper/2407.06606/citation-record.json","paper":"/paper/2407.06606"},"outbound":[],"paper":{"arxiv_id":"2407.06606","last_updated":"2025-05-06T08:24:18Z","latest_version":4,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-18T08:41:38.308587Z","submitted_at":"2024-07-09T07:15:56Z","title":"Tailored Design of Audio-Visual Speech Recognition Models using Branchformers"},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2407.06606."}