{"as_of":"2026-08-16T15:00:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a2157b40db5aac968f2fc9ae0bde278fb42b23ba9e3fd554d768212a84ccef1c","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":"2026-08-15T21:03:18.648277Z","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":"2026-08-15T18:08:19.187831Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.06582","last_updated":"2024-06-25T17:44:00Z","snapshot_observed_at":"2026-08-16T13:46:07.365155Z","submitted_at":"2024-06-04T20:08:25Z","title":"Discrete Multimodal Transformers with a Pretrained Large Language Model for Mixed-Supervision Speech Processing","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.06582","snapshot_observed_at":"2026-08-15T21:03:18.648277Z","title":"arXiv:2406.06582","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.10975","last_updated":"2026-05-27T20:17:05Z","snapshot_observed_at":"2026-08-16T06:33:06.115474Z","submitted_at":"2025-05-16T08:21:59Z","title":"Survey of End-to-End Multi-Speaker Automatic Speech Recognition for Monaural Audio","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T21:03:18.648277Z"},"links":{"cited_paper":"/paper/2406.06582","citing_paper":"/paper/2505.10975"},"observation_digest":"sha256:7cb36c5464524f8b95c11d8b5680233e93dea464e2d2bcf175e377e0122ec70d","observation_id":"7080dc02-17cb-4def-a954-e8273cd65e67","resolution":{"observed_at":"2026-08-15T21:03:18.648277Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.06582","last_updated":"2024-06-25T17:44:00Z","snapshot_observed_at":"2026-08-16T13:46:07.365155Z","submitted_at":"2024-06-04T20:08:25Z","title":"Discrete Multimodal Transformers with a Pretrained Large Language Model for Mixed-Supervision Speech Processing","version":2},"cited_work":{"arxiv_id":"2406.06582","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.06582","snapshot_observed_at":"2026-08-15T18:08:19.187831Z","title":"Discrete Multimodal Transformers with a Pretrained Large Language Model for Mixed-Supervision Speech Processing","venue":"cs.CL","work_id":"51d8cdcc-7110-4988-a3ab-d3deb376c44b","year":2024},"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":5,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:18.784896Z"},"links":{"cited_paper":"/paper/2406.06582","citing_paper":"/paper/2507.19037"},"observation_digest":"sha256:b00e29727cf06f075e548f3d522bcba56c098db8c20e03c5340f44efba236b75","observation_id":"3f8cdab4-09ad-4202-a4bb-e82f7aad9105","resolution":{"observed_at":"2026-08-15T18:08:19.194368Z","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/2406.06582/citation-record","integrity":"/paper/2406.06582/integrity","json":"/paper/2406.06582/citation-record.json","paper":"/paper/2406.06582"},"outbound":[],"paper":{"arxiv_id":"2406.06582","last_updated":"2024-06-25T17:44:00Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T13:46:07.365155Z","submitted_at":"2024-06-04T20:08:25Z","title":"Discrete Multimodal Transformers with a Pretrained Large Language Model for Mixed-Supervision Speech Processing"},"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 16 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2406.06582."}