{"as_of":"2026-08-06T16:24:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:efe5d7cc51b527e5a9e84b0fd5f2bebb4387cc7f670501f6df47dee9048b3406","coverage":[{"denominator":3,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-10T18:39:47.054480Z","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":"2026-08-06T06:34:29.942622+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2604.06871/citation-record","integrity":"/paper/2604.06871/integrity","json":"/paper/2604.06871/citation-record.json","paper":"/paper/2604.06871"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2210.09461","last_updated":"2023-03-01T19:45:11Z","snapshot_observed_at":"2026-07-06T14:06:56.291161Z","submitted_at":"2022-10-17T22:23:40Z","title":"Token Merging: Your ViT But Faster","version":3},"cited_work":{"arxiv_id":"2210.09461","doi":"10.48550/arxiv.2210.09461","metadata_source":"pith","pith_arxiv_id":"2210.09461","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Token Merging: Your ViT But Faster","venue":"cs.CV","work_id":"528509bc-2611-4e7f-a772-ea14d25b6dae","year":2022},"citing_paper":{"arxiv_id":"2604.06871","last_updated":"2026-04-08T09:33:44Z","snapshot_observed_at":"2026-07-06T22:55:15.791334Z","submitted_at":"2026-04-08T09:33:44Z","title":"Do We Need Distinct Representations for Every Speech Token? Unveiling and Exploiting Redundancy in Large Speech Language Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-10T18:39:47.054480Z"},"links":{"cited_paper":"/paper/2210.09461","citing_paper":"/paper/2604.06871"},"observation_digest":"sha256:ee5d8926c27a6df7e12df7821d98d11c022e242f83925ade48f2b15197156323","observation_id":"00979cc7-5309-459b-b557-ddab3488c3b9","resolution":{"observed_at":"2026-05-12T20:52:10.541797Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.10759","last_updated":"2024-07-15T14:38:09Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-07-15T14:38:09Z","title":"Qwen2-Audio Technical Report","version":1},"cited_work":{"arxiv_id":"2407.10759","doi":"10.48550/arxiv.2407.10759","metadata_source":"pith","pith_arxiv_id":"2407.10759","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Qwen2-Audio Technical Report","venue":"eess.AS","work_id":"c249e63c-cf40-408f-a4ff-fdf68e8cbeb8","year":2024},"citing_paper":{"arxiv_id":"2604.06871","last_updated":"2026-04-08T09:33:44Z","snapshot_observed_at":"2026-07-06T22:55:15.791334Z","submitted_at":"2026-04-08T09:33:44Z","title":"Do We Need Distinct Representations for Every Speech Token? Unveiling and Exploiting Redundancy in Large Speech Language Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-10T18:39:47.054480Z"},"links":{"cited_paper":"/paper/2407.10759","citing_paper":"/paper/2604.06871"},"observation_digest":"sha256:0b59f3a8d47d06006872dbd9b6c75329a63be5a9220f85ac2b5628d5efb842f1","observation_id":"45a887f6-b69d-464d-a238-d764e14ffd5a","resolution":{"observed_at":"2026-05-11T02:14:45.520303Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"6133.5951","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"audio_answer","venue":null,"work_id":"50442a4e-5d45-4a9d-a824-0cc7c21cb03a","year":null},"citing_paper":{"arxiv_id":"2604.06871","last_updated":"2026-04-08T09:33:44Z","snapshot_observed_at":"2026-07-06T22:55:15.791334Z","submitted_at":"2026-04-08T09:33:44Z","title":"Do We Need Distinct Representations for Every Speech Token? Unveiling and Exploiting Redundancy in Large Speech Language Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-10T18:39:47.054480Z"},"links":{"citing_paper":"/paper/2604.06871"},"observation_digest":"sha256:e5bada1169ecf13e5239f0b729384f8cb7802308067da8a71cf328431d6a7ba1","observation_id":"0d097345-d28c-409d-9f95-3d73973d00aa","resolution":{"observed_at":"2026-05-11T00:10:52.310859Z","resolver_source":"arxiv_id","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2604.06871","last_updated":"2026-04-08T09:33:44Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T22:55:15.791334Z","submitted_at":"2026-04-08T09:33:44Z","title":"Do We Need Distinct Representations for Every Speech Token? Unveiling and Exploiting Redundancy in Large Speech Language Models"},"reference_resolution":{"displayed":3,"state_counts":{"malformed_identifier":1,"metadata_mismatch":2,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":3},"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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 6 August 2026, this Paper Citation Record lists 3 of 3 outbound references and 0 inbound Pith citation observations for arXiv:2604.06871."}