{"as_of":"2026-08-04T09:09:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:26cecbd4a8a6411a6218c2ebfc008e5bc8d545b4c532f8fe4171f8767f55e226","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":"2026-08-04T06:34:03.388597+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":"2026-05-24T00:26:57.419537Z","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":"2026-05-24T00:28:39.561873Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2308.06873","last_updated":"2024-06-25T18:38:28Z","snapshot_observed_at":"2026-07-06T16:05:47.011408Z","submitted_at":"2023-08-14T01:01:19Z","title":"SpeechX: Neural Codec Language Model as a Versatile Speech Transformer","version":2},"cited_work":{"arxiv_id":"2308.06873","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2308.06873","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"SpeechX: Neural codec language model as a versatile speech transformer","venue":null,"work_id":"5077483b-4a04-4dae-8329-c776a4cca40e","year":2023},"citing_paper":{"arxiv_id":"2406.02430","last_updated":"2024-06-04T15:48:29Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-06-04T15:48:29Z","title":"Seed-TTS: A Family of High-Quality Versatile Speech Generation Models","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-15T12:26:37.300599Z"},"links":{"cited_paper":"/paper/2308.06873","citing_paper":"/paper/2406.02430"},"observation_digest":"sha256:39b5b4d508e5e3ee3ef44b09962694f5916b80433a5e6ecdbcb5ec1aacfb096f","observation_id":"cb7da3c8-9b5c-419a-aa7b-70d4dd5b084d","resolution":{"observed_at":"2026-05-15T12:26:37.412512Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.06873","last_updated":"2024-06-25T18:38:28Z","snapshot_observed_at":"2026-07-06T16:05:47.011408Z","submitted_at":"2023-08-14T01:01:19Z","title":"SpeechX: Neural Codec Language Model as a Versatile Speech Transformer","version":2},"cited_work":{"arxiv_id":"2308.06873","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2308.06873","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"SpeechX: Neural codec language model as a versatile speech transformer","venue":null,"work_id":"5077483b-4a04-4dae-8329-c776a4cca40e","year":2023},"citing_paper":{"arxiv_id":"2406.14294","last_updated":"2026-04-21T15:27:17Z","snapshot_observed_at":"2026-07-30T17:14:02.349402Z","submitted_at":"2024-06-20T13:23:27Z","title":"DASB - Discrete Audio and Speech Benchmark","version":4},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-24T00:26:57.419537Z"},"links":{"cited_paper":"/paper/2308.06873","citing_paper":"/paper/2406.14294"},"observation_digest":"sha256:ddafd7f88cab457046b00b110e56e23a2239bb2a95d27bd1071d4087ff56907c","observation_id":"fe4fb7ae-2b50-49c3-b335-f09f4c821bf1","resolution":{"observed_at":"2026-05-24T00:28:39.564746Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.06873","last_updated":"2024-06-25T18:38:28Z","snapshot_observed_at":"2026-07-06T16:05:47.011408Z","submitted_at":"2023-08-14T01:01:19Z","title":"SpeechX: Neural Codec Language Model as a Versatile Speech Transformer","version":2},"cited_work":{"arxiv_id":"2308.06873","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2308.06873","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"SpeechX: Neural codec language model as a versatile speech transformer","venue":null,"work_id":"5077483b-4a04-4dae-8329-c776a4cca40e","year":2023},"citing_paper":{"arxiv_id":"2509.11717","last_updated":"2026-06-21T14:09:38Z","snapshot_observed_at":"2026-07-06T22:29:58.066459Z","submitted_at":"2025-09-15T09:12:57Z","title":"CodecSep: Prompt-Driven Universal Sound Separation on Neural Audio Codec Latents","version":5},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-05-18T16:44:32.104114Z"},"links":{"cited_paper":"/paper/2308.06873","citing_paper":"/paper/2509.11717"},"observation_digest":"sha256:acb88453a1ddd2b70787743a0807e92cb276c16835f8697360bae7e6a29f3f25","observation_id":"d7713326-39ea-4e9d-af10-24777be3dd3f","resolution":{"observed_at":"2026-05-18T16:46:37.633741Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2308.06873/citation-record","integrity":"/paper/2308.06873/integrity","json":"/paper/2308.06873/citation-record.json","paper":"/paper/2308.06873"},"outbound":[],"paper":{"arxiv_id":"2308.06873","last_updated":"2024-06-25T18:38:28Z","latest_version":2,"primary_category":"eess.AS","snapshot_observed_at":"2026-07-06T16:05:47.011408Z","submitted_at":"2023-08-14T01:01:19Z","title":"SpeechX: Neural Codec Language Model as a Versatile Speech Transformer"},"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":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 4 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2308.06873."}