{"as_of":"2026-08-05T01:14:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7862f661ac13f92b61f42837dbd1c568eef319eebb85b1ba6e9e75cb16f5b0e7","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":"2026-08-04T06:34:03.388597+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":"2026-05-12T18:57:28.666194Z","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":"2026-05-12T18:57:28.820331Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2309.07937","last_updated":"2024-01-24T15:36:31Z","snapshot_observed_at":"2026-07-06T16:18:37.399390Z","submitted_at":"2023-09-14T03:13:18Z","title":"Voxtlm: unified decoder-only models for consolidating speech recognition/synthesis and speech/text continuation tasks","version":3},"cited_work":{"arxiv_id":"2309.07937","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2309.07937","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Voxtlm: unified decoder-only models for consolidating speech recognition/synthesis and speech/text continuation tasks","venue":null,"work_id":"f014baca-7e3d-4528-a8d6-8117be741f4d","year":2023},"citing_paper":{"arxiv_id":"2311.07919","last_updated":"2023-12-21T10:20:42Z","snapshot_observed_at":"2026-07-06T16:47:12.709738Z","submitted_at":"2023-11-14T05:34:50Z","title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-12T18:57:28.666194Z"},"links":{"cited_paper":"/paper/2309.07937","citing_paper":"/paper/2311.07919"},"observation_digest":"sha256:d2ab14acfbfd37bd451db32fb962ee440604ade98f38a573adc7b2ea8dea99f8","observation_id":"8f2a679e-c6bd-4afd-850c-f503f410178f","resolution":{"observed_at":"2026-05-12T18:57:28.823612Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.07937","last_updated":"2024-01-24T15:36:31Z","snapshot_observed_at":"2026-07-06T16:18:37.399390Z","submitted_at":"2023-09-14T03:13:18Z","title":"Voxtlm: unified decoder-only models for consolidating speech recognition/synthesis and speech/text continuation tasks","version":3},"cited_work":{"arxiv_id":"2309.07937","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2309.07937","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Voxtlm: unified decoder-only models for consolidating speech recognition/synthesis and speech/text continuation tasks","venue":null,"work_id":"f014baca-7e3d-4528-a8d6-8117be741f4d","year":2023},"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":66,"source":"arxiv_source","source_observed_at":"2026-05-12T08:13:21.962488Z"},"links":{"cited_paper":"/paper/2309.07937","citing_paper":"/paper/2410.00037"},"observation_digest":"sha256:c2b9de027ddd462a778e7f4c228f1e7db3d31f33b471e6a2bd2f08419f14d835","observation_id":"69ba80e9-6304-4ece-b5f1-b51d7cf40ce9","resolution":{"observed_at":"2026-05-12T08:13:22.506650Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2309.07937/citation-record","integrity":"/paper/2309.07937/integrity","json":"/paper/2309.07937/citation-record.json","paper":"/paper/2309.07937"},"outbound":[],"paper":{"arxiv_id":"2309.07937","last_updated":"2024-01-24T15:36:31Z","latest_version":3,"primary_category":"eess.AS","snapshot_observed_at":"2026-07-06T16:18:37.399390Z","submitted_at":"2023-09-14T03:13:18Z","title":"Voxtlm: unified decoder-only models for consolidating speech recognition/synthesis and speech/text continuation tasks"},"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":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2309.07937."}