{"as_of":"2026-08-09T10:54:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6b91889c4e238e0323cda3ad600ade7f505501cb4ea2f54ec1dfb49ecca2ef1c","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T11:28:54.976320Z","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":"2026-05-22T20:45:08.103023Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.18603","last_updated":"2025-07-10T17:52:43Z","snapshot_observed_at":"2026-07-06T20:12:54.710203Z","submitted_at":"2024-12-24T18:56:46Z","title":"Long-Form Speech Generation with Spoken Language Models","version":2},"cited_work":{"arxiv_id":"2412.18603","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.18603","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Long-form speech generation with spoken language models.arXiv preprint arXiv:2412.18603","venue":null,"work_id":"1c13e2d8-f9ae-416a-a31b-53dc02a8547a","year":null},"citing_paper":{"arxiv_id":"2504.08528","last_updated":"2026-04-07T06:11:20Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-04-11T13:40:53Z","title":"On The Landscape of Spoken Language Models: A Comprehensive Survey","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-22T20:44:57.476464Z"},"links":{"cited_paper":"/paper/2412.18603","citing_paper":"/paper/2504.08528"},"observation_digest":"sha256:7f2a5bfa518b6d722438b752f5ab37c5dd3789842a55c76c800dd38e8a7783bb","observation_id":"1d28ab25-dc4e-4589-9451-ec978873e3d3","resolution":{"observed_at":"2026-05-22T20:45:08.107364Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2412.18603","last_updated":"2025-07-10T17:52:43Z","snapshot_observed_at":"2026-07-06T20:12:54.710203Z","submitted_at":"2024-12-24T18:56:46Z","title":"Long-Form Speech Generation with Spoken Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.18603","snapshot_observed_at":"2026-08-07T11:28:54.976320Z","title":"Long-form speech generation with spoken language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.02443","last_updated":"2025-06-03T05:02:14Z","snapshot_observed_at":"2026-08-09T03:40:47.360103Z","submitted_at":"2025-06-03T05:02:14Z","title":"Breaking the Barriers of Text-Hungry and Audio-Deficient AI","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-07T11:28:54.976320Z"},"links":{"cited_paper":"/paper/2412.18603","citing_paper":"/paper/2506.02443"},"observation_digest":"sha256:1106e888e03da68db6e57f17f54d0abfbc997ad304ad299f2f914bc1c52753c6","observation_id":"69f5a34b-30cf-4b75-8c5b-9544d342ba84","resolution":{"observed_at":"2026-08-07T11:28:54.976320Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.18603","last_updated":"2025-07-10T17:52:43Z","snapshot_observed_at":"2026-07-06T20:12:54.710203Z","submitted_at":"2024-12-24T18:56:46Z","title":"Long-Form Speech Generation with Spoken Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.18603","snapshot_observed_at":"2026-08-03T12:02:01.567892Z","title":"J., Salazar, J., Jansen, A., Kinoshita, K., Ro, Y","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2601.06199","last_updated":"2026-06-01T03:39:22Z","snapshot_observed_at":"2026-08-06T01:59:30.134013Z","submitted_at":"2026-01-08T07:46:03Z","title":"FastSLM: Hierarchical Temporal Abstraction for Efficient Long-Form Speech Adaptation","version":3},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-03T12:02:01.567892Z"},"links":{"cited_paper":"/paper/2412.18603","citing_paper":"/paper/2601.06199"},"observation_digest":"sha256:93164dfb7f19cfe061c40b67dae9fee853a5fb32173b1cfb1fa75a1f82f2f3ce","observation_id":"b939a71c-37e4-4ef9-8bcd-72e63db097a8","resolution":{"observed_at":"2026-08-03T12:02:01.567892Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.18603","last_updated":"2025-07-10T17:52:43Z","snapshot_observed_at":"2026-07-06T20:12:54.710203Z","submitted_at":"2024-12-24T18:56:46Z","title":"Long-Form Speech Generation with Spoken Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.18603","snapshot_observed_at":"2026-07-31T23:35:25.666736Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.23938","last_updated":"2026-07-27T02:30:15Z","snapshot_observed_at":"2026-08-06T09:15:17.907620Z","submitted_at":"2026-07-27T02:30:15Z","title":"Qwen-Audio-3.0-TTS: Freely Controllable and Highly Robust Speech Synthesis with Multi-Stage Training Paradigm","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-07-31T23:35:25.666736Z"},"links":{"cited_paper":"/paper/2412.18603","citing_paper":"/paper/2607.23938"},"observation_digest":"sha256:72667fbb089eff2bcf48159352dfc8113cd3a9336098016a3737796215d07bde","observation_id":"1aadb9fd-d495-4538-9360-e8c659be5998","resolution":{"observed_at":"2026-07-31T23:35:25.666736Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2412.18603/citation-record","integrity":"/paper/2412.18603/integrity","json":"/paper/2412.18603/citation-record.json","paper":"/paper/2412.18603"},"outbound":[],"paper":{"arxiv_id":"2412.18603","last_updated":"2025-07-10T17:52:43Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T20:12:54.710203Z","submitted_at":"2024-12-24T18:56:46Z","title":"Long-Form Speech Generation with Spoken Language Models"},"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 4 inbound Pith citation observations for arXiv:2412.18603."}