{"as_of":"2026-08-08T06:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:76806815110c3f0e80faa69987695368dd751c540fb718cde7b371505a4f2f16","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":"2026-08-08T06:32:00.761636+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":"2026-08-05T17:34:01.439343Z","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":"2026-05-18T02:29:46.342038Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2307.03917","last_updated":"2023-10-02T06:57:19Z","snapshot_observed_at":"2026-08-01T22:03:44.507208Z","submitted_at":"2023-07-08T06:47:58Z","title":"On decoder-only architecture for speech-to-text and large language model integration","version":3},"cited_work":{"arxiv_id":"2307.03917","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2307.03917","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv:2307.03917 , year=","venue":null,"work_id":"ba6e8a05-a0c1-49b4-84a6-41cdfa4ab392","year":null},"citing_paper":{"arxiv_id":"2310.13289","last_updated":"2024-04-08T06:12:52Z","snapshot_observed_at":"2026-08-02T21:51:36.809095Z","submitted_at":"2023-10-20T05:41:57Z","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","version":2},"reference_index":109,"source":"arxiv_source","source_observed_at":"2026-05-18T02:29:46.242983Z"},"links":{"cited_paper":"/paper/2307.03917","citing_paper":"/paper/2310.13289"},"observation_digest":"sha256:c4be472eb562eea85d7244c029bdfd7cbb4015bf16b7c378c351a927bc37db72","observation_id":"f8bd65b4-6fe0-4c2b-b504-7e1b3770391d","resolution":{"observed_at":"2026-05-18T02:29:46.344493Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.03917","last_updated":"2023-10-02T06:57:19Z","snapshot_observed_at":"2026-08-01T22:03:44.507208Z","submitted_at":"2023-07-08T06:47:58Z","title":"On decoder-only architecture for speech-to-text and large language model integration","version":3},"cited_work":{"arxiv_id":"2307.03917","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2307.03917","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv:2307.03917 , year=","venue":null,"work_id":"ba6e8a05-a0c1-49b4-84a6-41cdfa4ab392","year":null},"citing_paper":{"arxiv_id":"2503.20215","last_updated":"2025-03-26T04:17:55Z","snapshot_observed_at":"2026-08-06T08:46:20.194739Z","submitted_at":"2025-03-26T04:17:55Z","title":"Qwen2.5-Omni Technical Report","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-10T17:54:03.225439Z"},"links":{"cited_paper":"/paper/2307.03917","citing_paper":"/paper/2503.20215"},"observation_digest":"sha256:d19e08db2ff326ce3fc24dd8917dd2625234e11e026f8fa2ed63842ca38febe9","observation_id":"317ce89c-498a-4811-bc51-b9a3926514b8","resolution":{"observed_at":"2026-05-10T17:54:03.441195Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.03917","last_updated":"2023-10-02T06:57:19Z","snapshot_observed_at":"2026-08-01T22:03:44.507208Z","submitted_at":"2023-07-08T06:47:58Z","title":"On decoder-only architecture for speech-to-text and large language model integration","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.03917","snapshot_observed_at":"2026-08-05T17:34:01.439343Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.16188","last_updated":"2025-08-27T19:49:56Z","snapshot_observed_at":"2026-08-07T08:50:45.717514Z","submitted_at":"2025-08-22T08:08:45Z","title":"Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation","version":2},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-05T17:34:01.439343Z"},"links":{"cited_paper":"/paper/2307.03917","citing_paper":"/paper/2508.16188"},"observation_digest":"sha256:cf487ed64d152f57078a18c252b0d66365f714f677967b86091b52f8852e104f","observation_id":"e6774275-4465-4540-938b-a465f1af10e6","resolution":{"observed_at":"2026-08-05T17:34:01.439343Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2307.03917/citation-record","integrity":"/paper/2307.03917/integrity","json":"/paper/2307.03917/citation-record.json","paper":"/paper/2307.03917"},"outbound":[],"paper":{"arxiv_id":"2307.03917","last_updated":"2023-10-02T06:57:19Z","latest_version":3,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-01T22:03:44.507208Z","submitted_at":"2023-07-08T06:47:58Z","title":"On decoder-only architecture for speech-to-text and large language model integration"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2307.03917."}