{"as_of":"2026-08-20T07:27:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d92616226d48b56b775583c0eeab421843e1046702e59e60413f154254e3306a","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":"2026-08-20T06:33:59.587034+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":"2026-08-15T17:54:19.293507Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-05T13:12:14.924792Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2305.10763","last_updated":"2023-05-18T07:07:04Z","snapshot_observed_at":"2026-08-16T15:32:06.418190Z","submitted_at":"2023-05-18T07:07:04Z","title":"CLAPSpeech: Learning Prosody from Text Context with Contrastive Language-Audio Pre-training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.10763","snapshot_observed_at":"2026-08-15T17:54:19.293507Z","title":"Clapspeech: Learning prosody from text context with contrastive language-audio pre-training","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.20091","last_updated":"2025-08-07T23:23:12Z","snapshot_observed_at":"2026-08-20T06:38:54.503781Z","submitted_at":"2025-07-27T00:59:01Z","title":"ProsodyLM: Uncovering the Emerging Prosody Processing Capabilities in Speech Language Models","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-15T17:54:19.293507Z"},"links":{"cited_paper":"/paper/2305.10763","citing_paper":"/paper/2507.20091"},"observation_digest":"sha256:724fbcedec305183426064257beccf117003988cef6a55351da5e0f0badff188","observation_id":"0ccb4176-9e30-49ea-9647-bda5a5e460e9","resolution":{"observed_at":"2026-08-15T17:54:19.293507Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.10763","last_updated":"2023-05-18T07:07:04Z","snapshot_observed_at":"2026-08-16T15:32:06.418190Z","submitted_at":"2023-05-18T07:07:04Z","title":"CLAPSpeech: Learning Prosody from Text Context with Contrastive Language-Audio Pre-training","version":1},"cited_work":{"arxiv_id":"2305.10763","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.10763","snapshot_observed_at":"2026-08-05T13:12:14.924792Z","title":"CLAPSpeech: Learning Prosody from Text Context with Contrastive Language-Audio Pre-training","venue":"cs.SD","work_id":"56fe92ec-0609-47c3-8676-09e2cfeba4a0","year":2023},"citing_paper":{"arxiv_id":"2509.00914","last_updated":"2025-08-31T15:57:13Z","snapshot_observed_at":"2026-08-19T21:59:50.184743Z","submitted_at":"2025-08-31T15:57:13Z","title":"TinyMusician: On-Device Music Generation with Knowledge Distillation and Mixed Precision Quantization","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:14.594403Z"},"links":{"cited_paper":"/paper/2305.10763","citing_paper":"/paper/2509.00914"},"observation_digest":"sha256:0aed96ddf86dc22bab433fd8de7d8ab22b67ca58e197fbc08a1cc603a2d992bd","observation_id":"ad0d1f56-1bb9-4a5a-9ddd-4e7128e4cf75","resolution":{"observed_at":"2026-08-05T13:12:14.933337Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2305.10763/citation-record","integrity":"/paper/2305.10763/integrity","json":"/paper/2305.10763/citation-record.json","paper":"/paper/2305.10763"},"outbound":[],"paper":{"arxiv_id":"2305.10763","last_updated":"2023-05-18T07:07:04Z","latest_version":1,"primary_category":"cs.SD","snapshot_observed_at":"2026-08-16T15:32:06.418190Z","submitted_at":"2023-05-18T07:07:04Z","title":"CLAPSpeech: Learning Prosody from Text Context with Contrastive Language-Audio Pre-training"},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2305.10763."}