{"as_of":"2026-08-09T23:38:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3258b41bc685a29d2b408278f13c9548efe5440ce4ecf12199359579a5706122","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":"2026-08-09T06:31:02.800959+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":"2026-08-07T15:16:32.899008Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-02T22:47:25.720115Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.09569","last_updated":"2024-06-13T20:20:29Z","snapshot_observed_at":"2026-08-03T20:22:45.687875Z","submitted_at":"2024-06-13T20:20:29Z","title":"Speech ReaLLM -- Real-time Streaming Speech Recognition with Multimodal LLMs by Teaching the Flow of Time","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.09569","snapshot_observed_at":"2026-08-07T15:16:32.899008Z","title":"Speech reallm–real-time streaming speech recognition with mul- timodal llms by teaching the flow of time,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.15646","last_updated":"2025-05-21T15:24:29Z","snapshot_observed_at":"2026-08-08T05:52:07.191787Z","submitted_at":"2025-05-21T15:24:29Z","title":"Word Level Timestamp Generation for Automatic Speech Recognition and Translation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T15:16:32.899008Z"},"links":{"cited_paper":"/paper/2406.09569","citing_paper":"/paper/2505.15646"},"observation_digest":"sha256:fa3355a0abf92b342341b9da8a75801846212ca373d619ad124c83cb44f687b5","observation_id":"05fdcdc4-da76-46da-8233-f171d23a0edc","resolution":{"observed_at":"2026-08-07T15:16:32.899008Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.09569","last_updated":"2024-06-13T20:20:29Z","snapshot_observed_at":"2026-08-03T20:22:45.687875Z","submitted_at":"2024-06-13T20:20:29Z","title":"Speech ReaLLM -- Real-time Streaming Speech Recognition with Multimodal LLMs by Teaching the Flow of Time","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.09569","snapshot_observed_at":"2026-08-06T14:42:56.029693Z","title":"Speech reallm– real-time streaming speech recognition with multimodal llms by teaching the flow of time,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.18181","last_updated":"2025-07-28T08:55:09Z","snapshot_observed_at":"2026-08-07T03:43:34.568661Z","submitted_at":"2025-07-24T08:27:53Z","title":"SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T14:42:56.029693Z"},"links":{"cited_paper":"/paper/2406.09569","citing_paper":"/paper/2507.18181"},"observation_digest":"sha256:3d10701b3b9e1d6ce57c74e7cc0d01c407e2826500d734d143ed56ae765f48f7","observation_id":"21734548-2019-4bc3-8084-296e92507613","resolution":{"observed_at":"2026-08-06T14:42:56.029693Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.09569","last_updated":"2024-06-13T20:20:29Z","snapshot_observed_at":"2026-08-03T20:22:45.687875Z","submitted_at":"2024-06-13T20:20:29Z","title":"Speech ReaLLM -- Real-time Streaming Speech Recognition with Multimodal LLMs by Teaching the Flow of Time","version":1},"cited_work":{"arxiv_id":"2406.09569","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.09569","snapshot_observed_at":"2026-07-02T22:47:25.720115Z","title":null,"venue":null,"work_id":"501bffa2-184a-41c6-ae36-f4ae89905a48","year":2024},"citing_paper":{"arxiv_id":"2606.08486","last_updated":"2026-06-07T07:15:34Z","snapshot_observed_at":"2026-07-06T23:47:57.376596Z","submitted_at":"2026-06-07T07:15:34Z","title":"TRADE: Transducer-Augmented Decoder for Speech LLM","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-06-27T18:40:19.688550Z"},"links":{"cited_paper":"/paper/2406.09569","citing_paper":"/paper/2606.08486"},"observation_digest":"sha256:221580d9fe0dfefdbc49757cd0f3e968be74f061e59ee5d5d64880ade310da49","observation_id":"8dddc640-cd0f-4395-b344-b411f5674321","resolution":{"observed_at":"2026-07-02T22:47:25.721453Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2406.09569/citation-record","integrity":"/paper/2406.09569/integrity","json":"/paper/2406.09569/citation-record.json","paper":"/paper/2406.09569"},"outbound":[],"paper":{"arxiv_id":"2406.09569","last_updated":"2024-06-13T20:20:29Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-03T20:22:45.687875Z","submitted_at":"2024-06-13T20:20:29Z","title":"Speech ReaLLM -- Real-time Streaming Speech Recognition with Multimodal LLMs by Teaching the Flow of Time"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2406.09569."}