{"as_of":"2026-08-11T09:50:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3b06edf5af8eb6f973e07988ea54b8f86960095b5a274639e5f210b3eb1509e5","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":"2026-08-10T00:35:48.760306Z","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":"2026-08-05T22:04:12.245470Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2207.06020","last_updated":"2022-07-13T08:07:19Z","snapshot_observed_at":"2026-08-11T00:49:13.343148Z","submitted_at":"2022-07-13T08:07:19Z","title":"Visual Context-driven Audio Feature Enhancement for Robust End-to-End Audio-Visual Speech Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.06020","snapshot_observed_at":"2026-08-10T00:35:48.760306Z","title":"Visual context-driven audio feature enhancement for robust end- to-end audio-visual speech recognition,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.18157","last_updated":"2025-01-30T05:46:30Z","snapshot_observed_at":"2026-08-10T16:57:37.742393Z","submitted_at":"2025-01-30T05:46:30Z","title":"Efficient Audiovisual Speech Processing via MUTUD: Multimodal Training and Unimodal Deployment","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T00:35:48.760306Z"},"links":{"cited_paper":"/paper/2207.06020","citing_paper":"/paper/2501.18157"},"observation_digest":"sha256:162ede7437b59c502fa9c24220a6ae574125d91a5eac65d8b09c9c6ff1c52632","observation_id":"35eb0f89-8803-4db4-af71-3679525007c4","resolution":{"observed_at":"2026-08-10T00:35:48.760306Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2207.06020","last_updated":"2022-07-13T08:07:19Z","snapshot_observed_at":"2026-08-11T00:49:13.343148Z","submitted_at":"2022-07-13T08:07:19Z","title":"Visual Context-driven Audio Feature Enhancement for Robust End-to-End Audio-Visual Speech Recognition","version":1},"cited_work":{"arxiv_id":"2207.06020","doi":null,"metadata_source":"pith","pith_arxiv_id":"2207.06020","snapshot_observed_at":"2026-08-05T22:04:12.245470Z","title":"Visual Context-driven Audio Feature Enhancement for Robust End-to-End Audio-Visual Speech Recognition","venue":"cs.SD","work_id":"228a9b0a-6457-4102-aa5c-9a6852e37483","year":2022},"citing_paper":{"arxiv_id":"2508.07608","last_updated":"2025-08-11T04:23:08Z","snapshot_observed_at":"2026-08-09T03:37:21.312258Z","submitted_at":"2025-08-11T04:23:08Z","title":"AD-AVSR: Asymmetric Dual-stream Enhancement for Robust Audio-Visual Speech Recognition","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T22:04:11.990223Z"},"links":{"cited_paper":"/paper/2207.06020","citing_paper":"/paper/2508.07608"},"observation_digest":"sha256:fabe9403c7170f08811e18959c63cd27eba5da94d6d1f19c4e58159c2de80610","observation_id":"da0ff8f8-9e9b-4834-81d6-ac14ff1a27f3","resolution":{"observed_at":"2026-08-05T22:04:12.250071Z","resolver_source":"local_arxiv","status":"verified_exact"},"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/2207.06020/citation-record","integrity":"/paper/2207.06020/integrity","json":"/paper/2207.06020/citation-record.json","paper":"/paper/2207.06020"},"outbound":[],"paper":{"arxiv_id":"2207.06020","last_updated":"2022-07-13T08:07:19Z","latest_version":1,"primary_category":"cs.SD","snapshot_observed_at":"2026-08-11T00:49:13.343148Z","submitted_at":"2022-07-13T08:07:19Z","title":"Visual Context-driven Audio Feature Enhancement for Robust End-to-End Audio-Visual Speech Recognition"},"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:2207.06020."}