{"as_of":"2026-08-17T02:35:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6bdbb0c43f804b75ba6e635ce049b1887428b5c815c99fbc6963eaac133f2b08","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":"2026-08-16T06:30:59.297886+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":"2026-08-15T18:08:18.812315Z","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":"2026-08-05T17:34:02.993507Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2503.11315","last_updated":"2025-06-05T05:58:37Z","snapshot_observed_at":"2026-08-16T12:50:02.793500Z","submitted_at":"2025-03-14T11:31:30Z","title":"MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.11315","snapshot_observed_at":"2026-08-15T18:08:18.812315Z","title":"Mms-llama: Efficient llm-based audio-visual speech recognition with minimal multimodal speech tokens,","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":11,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:18.812315Z"},"links":{"cited_paper":"/paper/2503.11315","citing_paper":"/paper/2507.19037"},"observation_digest":"sha256:15cbaa9718f15fdb212c9eae63e508573b69125da4cd59338e33f73ce8d1a6e2","observation_id":"d24fb121-cf20-4d97-9c81-0863c290eca7","resolution":{"observed_at":"2026-08-15T18:08:18.812315Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.11315","last_updated":"2025-06-05T05:58:37Z","snapshot_observed_at":"2026-08-16T12:50:02.793500Z","submitted_at":"2025-03-14T11:31:30Z","title":"MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens","version":2},"cited_work":{"arxiv_id":"2503.11315","doi":null,"metadata_source":"pith","pith_arxiv_id":"2503.11315","snapshot_observed_at":"2026-08-05T17:34:02.993507Z","title":"MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens","venue":"cs.CV","work_id":"faa6ff6b-e1c9-4004-a66b-f3812a77768c","year":2025},"citing_paper":{"arxiv_id":"2508.16188","last_updated":"2025-08-27T19:49:56Z","snapshot_observed_at":"2026-08-16T13:50:39.724461Z","submitted_at":"2025-08-22T08:08:45Z","title":"Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation","version":2},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-05T17:34:01.706260Z"},"links":{"cited_paper":"/paper/2503.11315","citing_paper":"/paper/2508.16188"},"observation_digest":"sha256:4aa5bbe2e42ea3f125c01cdf5536af73a23ea56138f2c85dd4bddccb206339d6","observation_id":"9f5fa781-25c0-46e3-9844-bdff186365df","resolution":{"observed_at":"2026-08-05T17:34:03.090588Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2503.11315/citation-record","integrity":"/paper/2503.11315/integrity","json":"/paper/2503.11315/citation-record.json","paper":"/paper/2503.11315"},"outbound":[],"paper":{"arxiv_id":"2503.11315","last_updated":"2025-06-05T05:58:37Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T12:50:02.793500Z","submitted_at":"2025-03-14T11:31:30Z","title":"MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens"},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2503.11315."}