{"as_of":"2026-08-13T15:33:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:bb72747464885a18215498b1e225d401502e309d135f1c87e81100083433ec42","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":"2026-08-13T06:32:02.005865+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":"2026-08-12T10:57:08.449289Z","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":"2026-08-07T05:47:14.348285Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2409.15897","last_updated":"2025-02-24T18:34:41Z","snapshot_observed_at":"2026-08-12T22:38:50.246432Z","submitted_at":"2024-09-24T09:16:11Z","title":"ESPnet-Codec: Comprehensive Training and Evaluation of Neural Codecs for Audio, Music, and Speech","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.15897","snapshot_observed_at":"2026-08-12T10:57:08.449289Z","title":"Espnet-codec: Compre- hensive training and evaluation of neural codecs for audio, music, and speech,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.18803","last_updated":"2025-04-27T16:37:28Z","snapshot_observed_at":"2026-08-13T14:50:55.342669Z","submitted_at":"2024-11-27T23:07:52Z","title":"TS3-Codec: Transformer-Based Simple Streaming Single Codec","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T10:57:08.449289Z"},"links":{"cited_paper":"/paper/2409.15897","citing_paper":"/paper/2411.18803"},"observation_digest":"sha256:9d8ba45c59588ddec7de6bfdcf3c83bb5e3920ae9c72b488af1948088af5ac57","observation_id":"ed60375e-15fe-446a-be80-5f813c7d875b","resolution":{"observed_at":"2026-08-12T10:57:08.449289Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.15897","last_updated":"2025-02-24T18:34:41Z","snapshot_observed_at":"2026-08-12T22:38:50.246432Z","submitted_at":"2024-09-24T09:16:11Z","title":"ESPnet-Codec: Comprehensive Training and Evaluation of Neural Codecs for Audio, Music, and Speech","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.15897","snapshot_observed_at":"2026-08-11T05:20:45.095799Z","title":"835: A non-intrusive percep- tual objective speech quality metric to evaluate noise suppressors","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.17667","last_updated":"2025-03-27T03:50:10Z","snapshot_observed_at":"2026-08-11T15:07:28.270038Z","submitted_at":"2024-12-23T15:53:21Z","title":"VERSA: A Versatile Evaluation Toolkit for Speech, Audio, and Music","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-11T05:20:45.095799Z"},"links":{"cited_paper":"/paper/2409.15897","citing_paper":"/paper/2412.17667"},"observation_digest":"sha256:3bb1e451e790c9c43021d892fa79573aeecc4e42f45c61de272617137a7dfadc","observation_id":"5966c653-7880-4e04-9fb2-7cd00e391d2c","resolution":{"observed_at":"2026-08-11T05:20:45.095799Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.15897","last_updated":"2025-02-24T18:34:41Z","snapshot_observed_at":"2026-08-12T22:38:50.246432Z","submitted_at":"2024-09-24T09:16:11Z","title":"ESPnet-Codec: Comprehensive Training and Evaluation of Neural Codecs for Audio, Music, and Speech","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.15897","snapshot_observed_at":"2026-08-07T12:04:33.706834Z","title":"Espnet-codec: Comprehensive training and eval- uation of neural codecs for audio, music, and speech,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.00722","last_updated":"2025-05-31T21:43:37Z","snapshot_observed_at":"2026-08-09T13:25:00.234934Z","submitted_at":"2025-05-31T21:43:37Z","title":"Chain-of-Thought Training for Open E2E Spoken Dialogue Systems","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T12:04:33.706834Z"},"links":{"cited_paper":"/paper/2409.15897","citing_paper":"/paper/2506.00722"},"observation_digest":"sha256:520ef73342a0ae7a578bf8c14fb206f3349131184e3b02d82ba1380e3e6baa51","observation_id":"8a5f30cd-9596-4953-bc6d-a8f17d175927","resolution":{"observed_at":"2026-08-07T12:04:33.706834Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.15897","last_updated":"2025-02-24T18:34:41Z","snapshot_observed_at":"2026-08-12T22:38:50.246432Z","submitted_at":"2024-09-24T09:16:11Z","title":"ESPnet-Codec: Comprehensive Training and Evaluation of Neural Codecs for Audio, Music, and Speech","version":2},"cited_work":{"arxiv_id":"2409.15897","doi":null,"metadata_source":"pith","pith_arxiv_id":"2409.15897","snapshot_observed_at":"2026-08-07T05:47:14.348285Z","title":"ESPnet-Codec: Comprehensive Training and Evaluation of Neural Codecs for Audio, Music, and Speech","venue":"eess.AS","work_id":"9a63511b-6dcb-4119-aabe-067e438be83d","year":2024},"citing_paper":{"arxiv_id":"2506.07081","last_updated":"2025-06-19T09:40:25Z","snapshot_observed_at":"2026-08-13T09:17:12.746526Z","submitted_at":"2025-06-08T10:54:23Z","title":"Streaming Endpointer for Spoken Dialogue using Neural Audio Codecs and Label-Delayed Training","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:12.794875Z"},"links":{"cited_paper":"/paper/2409.15897","citing_paper":"/paper/2506.07081"},"observation_digest":"sha256:8233d835667aa01013e27cc962d1a0f286e8f6b443954200a15dfa404d018955","observation_id":"6595c748-2f80-4c2f-b947-401edb609c36","resolution":{"observed_at":"2026-08-07T05:47:14.407787Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2409.15897/citation-record","integrity":"/paper/2409.15897/integrity","json":"/paper/2409.15897/citation-record.json","paper":"/paper/2409.15897"},"outbound":[],"paper":{"arxiv_id":"2409.15897","last_updated":"2025-02-24T18:34:41Z","latest_version":2,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-12T22:38:50.246432Z","submitted_at":"2024-09-24T09:16:11Z","title":"ESPnet-Codec: Comprehensive Training and Evaluation of Neural Codecs for Audio, Music, and Speech"},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2409.15897."}