{"as_of":"2026-08-16T01:27:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d1c0663570aa30f93f63b51496446039fc4784e888439d43cc47cebc8a6f5789","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T18:08:18.924921Z","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":"2026-08-07T15:39:34.525624Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2503.06362","last_updated":"2025-08-06T17:41:48Z","snapshot_observed_at":"2026-08-07T17:19:43.747391Z","submitted_at":"2025-03-09T00:02:10Z","title":"Adaptive Audio-Visual Speech Recognition via Matryoshka-Based Multimodal LLMs","version":2},"cited_work":{"arxiv_id":"2503.06362","doi":null,"metadata_source":"pith","pith_arxiv_id":"2503.06362","snapshot_observed_at":"2026-08-07T15:39:34.525624Z","title":"Adaptive Audio-Visual Speech Recognition via Matryoshka-Based Multimodal LLMs","venue":"cs.CV","work_id":"a1b20bb6-09da-4fc1-b83a-b7d134ed3c2b","year":2025},"citing_paper":{"arxiv_id":"2505.14336","last_updated":"2025-05-21T14:22:18Z","snapshot_observed_at":"2026-08-09T14:12:04.052166Z","submitted_at":"2025-05-20T13:20:55Z","title":"Scaling and Enhancing LLM-based AVSR: A Sparse Mixture of Projectors Approach","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T15:39:31.946915Z"},"links":{"cited_paper":"/paper/2503.06362","citing_paper":"/paper/2505.14336"},"observation_digest":"sha256:09a160adb49580feded065acdeda2f576d9195dcf08e90876a51ed06427eb6ae","observation_id":"74c03ad7-df57-4179-97a5-233f70fed895","resolution":{"observed_at":"2026-08-07T15:39:34.600776Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.06362","last_updated":"2025-08-06T17:41:48Z","snapshot_observed_at":"2026-08-07T17:19:43.747391Z","submitted_at":"2025-03-09T00:02:10Z","title":"Adaptive Audio-Visual Speech Recognition via Matryoshka-Based Multimodal LLMs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.06362","snapshot_observed_at":"2026-08-15T18:08:18.924921Z","title":"Adaptive audio-visual speech recognition via matryoshka-based multimodal llms,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.19037","last_updated":"2025-07-25T07:46:40Z","snapshot_observed_at":"2026-08-15T18:00:09.179106Z","submitted_at":"2025-07-25T07:46:40Z","title":"MLLM-based Speech Recognition: When and How is Multimodality Beneficial?","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:18.924921Z"},"links":{"cited_paper":"/paper/2503.06362","citing_paper":"/paper/2507.19037"},"observation_digest":"sha256:afc8408eae5a8427ad4230d1c55288c25e108c30518831d1fe9f74069af7b777","observation_id":"fc9ea407-1853-49bf-9f5d-8d534cac714e","resolution":{"observed_at":"2026-08-15T18:08:18.924921Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.06362","last_updated":"2025-08-06T17:41:48Z","snapshot_observed_at":"2026-08-07T17:19:43.747391Z","submitted_at":"2025-03-09T00:02:10Z","title":"Adaptive Audio-Visual Speech Recognition via Matryoshka-Based Multimodal LLMs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.06362","snapshot_observed_at":"2026-07-15T13:22:58.005580Z","title":"Adaptive audio-visual speech recognition via matryoshka-based multimodal llms,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.07262","last_updated":"2026-07-13T11:38:19Z","snapshot_observed_at":"2026-08-15T06:09:04.020344Z","submitted_at":"2026-03-07T15:39:36Z","title":"Existence of the longest arcs for left-invariant three-dimensional contact sub-Lorentzian structures","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-15T13:22:58.005580Z"},"links":{"cited_paper":"/paper/2503.06362","citing_paper":"/paper/2603.07262"},"observation_digest":"sha256:abf5f148548b1bf2d8b19dcb7e3830dbbeddc03385138694e32dee7ec3aaf100","observation_id":"b03aea7a-264d-4c51-8ea8-eb6d01991103","resolution":{"observed_at":"2026-07-15T13:22:58.005580Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2503.06362/citation-record","integrity":"/paper/2503.06362/integrity","json":"/paper/2503.06362/citation-record.json","paper":"/paper/2503.06362"},"outbound":[],"paper":{"arxiv_id":"2503.06362","last_updated":"2025-08-06T17:41:48Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T17:19:43.747391Z","submitted_at":"2025-03-09T00:02:10Z","title":"Adaptive Audio-Visual Speech Recognition via Matryoshka-Based Multimodal LLMs"},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2503.06362."}