{"as_of":"2026-08-09T16:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1adb68e94385100aac3cc5e636745abdf1e5f31c9cbb2f27354d69d1e03a10bb","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":"2026-08-09T06:31:02.800959+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":"2026-08-08T19:15:52.190529Z","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":"2026-07-02T00:46:24.533188Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2109.03264","last_updated":"2022-05-10T16:41:20Z","snapshot_observed_at":"2026-07-31T00:23:19.156175Z","submitted_at":"2021-09-07T18:03:21Z","title":"Text-Free Prosody-Aware Generative Spoken Language Modeling","version":2},"cited_work":{"arxiv_id":"2109.03264","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2109.03264","snapshot_observed_at":"2026-07-02T00:46:24.533188Z","title":"Text-free prosody-aware generative spoken language modeling","venue":null,"work_id":"d77db77c-32c8-4f9a-8680-b43eb8a85391","year":null},"citing_paper":{"arxiv_id":"2210.13438","last_updated":"2022-10-24T17:52:02Z","snapshot_observed_at":"2026-08-09T07:12:13.721596Z","submitted_at":"2022-10-24T17:52:02Z","title":"High Fidelity Neural Audio Compression","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-13T21:49:52.184932Z"},"links":{"cited_paper":"/paper/2109.03264","citing_paper":"/paper/2210.13438"},"observation_digest":"sha256:d2729a2d25afc481802c0301a8603d9cc6a47ca48f8dc50bb40d1fe056ddac27","observation_id":"a20ada46-66c9-4473-b63e-bb9bf5e67fb1","resolution":{"observed_at":"2026-05-13T21:49:52.233159Z","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":"2109.03264","last_updated":"2022-05-10T16:41:20Z","snapshot_observed_at":"2026-07-31T00:23:19.156175Z","submitted_at":"2021-09-07T18:03:21Z","title":"Text-Free Prosody-Aware Generative Spoken Language Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.03264","snapshot_observed_at":"2026-08-08T19:15:52.190529Z","title":"Text-free prosody-aware generative spoken language modeling,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.05471","last_updated":"2025-02-08T07:14:04Z","snapshot_observed_at":"2026-08-08T19:09:27.361732Z","submitted_at":"2025-02-08T07:14:04Z","title":"Enhancing Expressive Voice Conversion with Discrete Pitch-Conditioned Flow Matching Model","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-08T19:15:52.190529Z"},"links":{"cited_paper":"/paper/2109.03264","citing_paper":"/paper/2502.05471"},"observation_digest":"sha256:b1506055b0d31d7a7a45434889a0c6ba368bc42003b5cca842d9bf240edf6552","observation_id":"e7e8479f-ed8a-4ef3-ab44-15efc7b8ad70","resolution":{"observed_at":"2026-08-08T19:15:52.190529Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.03264","last_updated":"2022-05-10T16:41:20Z","snapshot_observed_at":"2026-07-31T00:23:19.156175Z","submitted_at":"2021-09-07T18:03:21Z","title":"Text-Free Prosody-Aware Generative Spoken Language Modeling","version":2},"cited_work":{"arxiv_id":"2109.03264","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2109.03264","snapshot_observed_at":"2026-07-02T00:46:24.533188Z","title":"Text-free prosody-aware generative spoken language modeling","venue":null,"work_id":"d77db77c-32c8-4f9a-8680-b43eb8a85391","year":null},"citing_paper":{"arxiv_id":"2606.01677","last_updated":"2026-06-01T04:35:28Z","snapshot_observed_at":"2026-08-01T15:52:02.822088Z","submitted_at":"2026-06-01T04:35:28Z","title":"UniVocal: Unified Speech-Singing Code-Switching Synthesis","version":1},"reference_index":86,"source":"arxiv_source","source_observed_at":"2026-06-28T13:17:13.510587Z"},"links":{"cited_paper":"/paper/2109.03264","citing_paper":"/paper/2606.01677"},"observation_digest":"sha256:25fc24904065b0b9626db98059bd53707d591bacf1ab902af1e556754290b75a","observation_id":"715c339b-6d93-4459-bff0-b325a60a52ed","resolution":{"observed_at":"2026-07-02T00:46:24.535183Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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"}}],"links":{"evidence":"/evidence","html":"/paper/2109.03264/citation-record","integrity":"/paper/2109.03264/integrity","json":"/paper/2109.03264/citation-record.json","paper":"/paper/2109.03264"},"outbound":[],"paper":{"arxiv_id":"2109.03264","last_updated":"2022-05-10T16:41:20Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-31T00:23:19.156175Z","submitted_at":"2021-09-07T18:03:21Z","title":"Text-Free Prosody-Aware Generative Spoken Language Modeling"},"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 3 inbound Pith citation observations for arXiv:2109.03264."}