{"as_of":"2026-08-23T10:43:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:af2796f374d993652e547a217f14a338299778f10bebece88287885dd32ba4ec","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":"2026-08-23T06:30:58.430688+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":"2026-08-16T00:47:52.778178Z","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":"2026-05-12T08:13:22.284065Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.00976","last_updated":"2024-11-01T13:54:48Z","snapshot_observed_at":"2026-08-16T13:46:54.193784Z","submitted_at":"2024-06-03T04:16:30Z","title":"Generative Pre-trained Speech Language Model with Efficient Hierarchical Transformer","version":2},"cited_work":{"arxiv_id":"2406.00976","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.00976","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Generative pre-trained speech language model with efficient hierarchical transformer","venue":null,"work_id":"57fba653-6fbd-42e8-9905-f6f095ccd757","year":2024},"citing_paper":{"arxiv_id":"2410.00037","last_updated":"2024-10-02T09:11:45Z","snapshot_observed_at":"2026-07-30T10:21:14.474746Z","submitted_at":"2024-09-17T17:55:39Z","title":"Moshi: a speech-text foundation model for real-time dialogue","version":2},"reference_index":117,"source":"arxiv_source","source_observed_at":"2026-05-12T08:13:21.962488Z"},"links":{"cited_paper":"/paper/2406.00976","citing_paper":"/paper/2410.00037"},"observation_digest":"sha256:259d6dbd3425a106f2f7a08cf69de7b03bf538e40df45a701569f56f95c00b71","observation_id":"0d9ab0e4-7e86-48b9-bf9f-e73b6d3f3d36","resolution":{"observed_at":"2026-05-12T08:13:22.288218Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.00976","last_updated":"2024-11-01T13:54:48Z","snapshot_observed_at":"2026-08-16T13:46:54.193784Z","submitted_at":"2024-06-03T04:16:30Z","title":"Generative Pre-trained Speech Language Model with Efficient Hierarchical Transformer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.00976","snapshot_observed_at":"2026-08-16T00:47:52.778178Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.02707","last_updated":"2025-05-05T15:05:01Z","snapshot_observed_at":"2026-08-18T17:55:59.387301Z","submitted_at":"2025-05-05T15:05:01Z","title":"Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play","version":1},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-08-16T00:47:52.778178Z"},"links":{"cited_paper":"/paper/2406.00976","citing_paper":"/paper/2505.02707"},"observation_digest":"sha256:3c30e72822ed0c4f6c3f6931bb677bb57ba90db9f7d940d41e7a76532380ff76","observation_id":"3c77d63f-3d38-4005-bdbd-50969192f301","resolution":{"observed_at":"2026-08-16T00:47:52.778178Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.00976","last_updated":"2024-11-01T13:54:48Z","snapshot_observed_at":"2026-08-16T13:46:54.193784Z","submitted_at":"2024-06-03T04:16:30Z","title":"Generative Pre-trained Speech Language Model with Efficient Hierarchical Transformer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.00976","snapshot_observed_at":"2026-08-07T14:19:53.626191Z","title":"Generative pre-trained speech language model with efficient hierarchical transformer.ArXiv, abs/2406.00976, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.19462","last_updated":"2025-05-31T22:36:04Z","snapshot_observed_at":"2026-08-09T03:57:33.373890Z","submitted_at":"2025-05-26T03:35:44Z","title":"VoiceStar: Robust Zero-Shot Autoregressive TTS with Duration Control and Extrapolation","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T14:19:53.626191Z"},"links":{"cited_paper":"/paper/2406.00976","citing_paper":"/paper/2505.19462"},"observation_digest":"sha256:f34f8214eb25ba49613d2e5ab355ce72b1231c8bd7f290afafbf7f65186a7cb5","observation_id":"012daf19-969a-4d96-a9d1-43fba4969a32","resolution":{"observed_at":"2026-08-07T14:19:53.626191Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2406.00976/citation-record","integrity":"/paper/2406.00976/integrity","json":"/paper/2406.00976/citation-record.json","paper":"/paper/2406.00976"},"outbound":[],"paper":{"arxiv_id":"2406.00976","last_updated":"2024-11-01T13:54:48Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T13:46:54.193784Z","submitted_at":"2024-06-03T04:16:30Z","title":"Generative Pre-trained Speech Language Model with Efficient Hierarchical Transformer"},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2406.00976."}