{"as_of":"2026-08-08T19:58:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:662d6c94d0348c4113c114a49572b7b30887e3c5bb5fef4c699ecf43f11e3579","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":"2026-07-30T11:48:49.494905Z","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":"2026-07-04T03:49:30.225955Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2102.01192","last_updated":"2021-09-09T22:36:33Z","snapshot_observed_at":"2026-07-06T10:37:37.039377Z","submitted_at":"2021-02-01T21:41:40Z","title":"Generative Spoken Language Modeling from Raw Audio","version":2},"cited_work":{"arxiv_id":"2102.01192","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2102.01192","snapshot_observed_at":"2026-07-04T03:49:30.225955Z","title":"Generative spoken language modeling from raw audio","venue":null,"work_id":"6d9290f7-6174-49b3-bb17-eb6bc996ff9c","year":2021},"citing_paper":{"arxiv_id":"2301.02111","last_updated":"2023-01-05T15:37:15Z","snapshot_observed_at":"2026-08-07T10:11:17.796562Z","submitted_at":"2023-01-05T15:37:15Z","title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-13T01:31:06.635613Z"},"links":{"cited_paper":"/paper/2102.01192","citing_paper":"/paper/2301.02111"},"observation_digest":"sha256:09c5a0ed76bb8e897328fae2283bf12144b40cd35a5e0818f36ad352152e91f1","observation_id":"a3fe5a0c-314d-47f0-b0b5-7f48da80f4f5","resolution":{"observed_at":"2026-05-13T01:31:07.097756Z","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":"2102.01192","last_updated":"2021-09-09T22:36:33Z","snapshot_observed_at":"2026-07-06T10:37:37.039377Z","submitted_at":"2021-02-01T21:41:40Z","title":"Generative Spoken Language Modeling from Raw Audio","version":2},"cited_work":{"arxiv_id":"2102.01192","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2102.01192","snapshot_observed_at":"2026-07-04T03:49:30.225955Z","title":"Generative spoken language modeling from raw audio","venue":null,"work_id":"6d9290f7-6174-49b3-bb17-eb6bc996ff9c","year":2021},"citing_paper":{"arxiv_id":"2606.19910","last_updated":"2026-06-23T10:40:32Z","snapshot_observed_at":"2026-08-05T15:52:37.159854Z","submitted_at":"2026-06-18T08:04:16Z","title":"Light-weight Pronunciation Assessment via Discrete Speech Token Surprisal","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-26T17:37:25.043607Z"},"links":{"cited_paper":"/paper/2102.01192","citing_paper":"/paper/2606.19910"},"observation_digest":"sha256:0e2976050349b4fa1de00e195ff5fe89b3a0ea83ddda856508acc6d0b7ba1ca8","observation_id":"dae99951-0b4b-4d5b-8205-f148b6daa330","resolution":{"observed_at":"2026-07-04T03:49:30.228311Z","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":"2102.01192","last_updated":"2021-09-09T22:36:33Z","snapshot_observed_at":"2026-07-06T10:37:37.039377Z","submitted_at":"2021-02-01T21:41:40Z","title":"Generative Spoken Language Modeling from Raw Audio","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.01192","snapshot_observed_at":"2026-07-30T11:48:49.494905Z","title":"Doyup Lee, Chiheon Kim, Saehoon Kim, Minsu Cho, and Wook-Shin Han","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.23811","last_updated":"2026-07-26T19:20:01Z","snapshot_observed_at":"2026-08-05T02:59:42.567093Z","submitted_at":"2026-07-26T19:20:01Z","title":"Memory Efficient Audio Synthesis with Decoupled Temporal Depth Diffusion Transformers","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-07-30T11:48:49.494905Z"},"links":{"cited_paper":"/paper/2102.01192","citing_paper":"/paper/2607.23811"},"observation_digest":"sha256:e29bea743e3ea2d8f110089c8435d2668cd147d71a1db0ba08636fdad9598659","observation_id":"d0504c5b-bbea-47b6-a591-41777f8f3a14","resolution":{"observed_at":"2026-07-30T11:48:49.494905Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2102.01192/citation-record","integrity":"/paper/2102.01192/integrity","json":"/paper/2102.01192/citation-record.json","paper":"/paper/2102.01192"},"outbound":[],"paper":{"arxiv_id":"2102.01192","last_updated":"2021-09-09T22:36:33Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T10:37:37.039377Z","submitted_at":"2021-02-01T21:41:40Z","title":"Generative Spoken Language Modeling from Raw Audio"},"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:2102.01192."}