{"as_of":"2026-08-14T10:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d3244a45fbb9d66ead4a7678779183f5baa5b40b1dc7bd553477842df60f80b1","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":"2026-08-14T06:32:32.682623+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":"2026-08-12T05:56:42.828585Z","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":"2026-07-03T16:08:37.447210Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.10735","last_updated":"2024-06-15T20:43:07Z","snapshot_observed_at":"2026-08-12T23:41:58.405020Z","submitted_at":"2024-06-15T20:43:07Z","title":"How Should We Extract Discrete Audio Tokens from Self-Supervised Models?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.10735","snapshot_observed_at":"2026-08-12T05:56:42.828585Z","title":"How should we extract discrete audio tokens from self-supervised models? arXiv:2406.10735, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.19842","last_updated":"2024-11-29T16:58:02Z","snapshot_observed_at":"2026-08-13T15:53:14.922964Z","submitted_at":"2024-11-29T16:58:02Z","title":"Scaling Transformers for Low-Bitrate High-Quality Speech Coding","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-12T05:56:42.828585Z"},"links":{"cited_paper":"/paper/2406.10735","citing_paper":"/paper/2411.19842"},"observation_digest":"sha256:b397e635d719c9b48e6bfec1e4fef246bf2e61cdea7f52726a0136a02fe5aa94","observation_id":"e0818596-5c7a-420f-b388-baf295849936","resolution":{"observed_at":"2026-08-12T05:56:42.828585Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.10735","last_updated":"2024-06-15T20:43:07Z","snapshot_observed_at":"2026-08-12T23:41:58.405020Z","submitted_at":"2024-06-15T20:43:07Z","title":"How Should We Extract Discrete Audio Tokens from Self-Supervised Models?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.10735","snapshot_observed_at":"2026-08-05T16:46:49.201803Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.17863","last_updated":"2025-08-25T10:16:07Z","snapshot_observed_at":"2026-08-09T22:28:55.202566Z","submitted_at":"2025-08-25T10:16:07Z","title":"Speech Discrete Tokens or Continuous Features? A Comparative Analysis for Spoken Language Understanding in SpeechLLMs","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-05T16:46:49.201803Z"},"links":{"cited_paper":"/paper/2406.10735","citing_paper":"/paper/2508.17863"},"observation_digest":"sha256:2a9b4b84209475fe82fb40bba72df0b5b86316847c45624e4674bb145a710688","observation_id":"7dcb80e2-5104-49ea-bc20-9dc7a316d8d6","resolution":{"observed_at":"2026-08-05T16:46:49.201803Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.10735","last_updated":"2024-06-15T20:43:07Z","snapshot_observed_at":"2026-08-12T23:41:58.405020Z","submitted_at":"2024-06-15T20:43:07Z","title":"How Should We Extract Discrete Audio Tokens from Self-Supervised Models?","version":1},"cited_work":{"arxiv_id":"2406.10735","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.10735","snapshot_observed_at":"2026-07-03T16:08:37.447210Z","title":"arXiv preprint arXiv:2406.10735 , year=","venue":null,"work_id":"0fae641e-2c46-43e3-beba-2695d4e3f2a7","year":null},"citing_paper":{"arxiv_id":"2606.12940","last_updated":"2026-06-11T06:06:02Z","snapshot_observed_at":"2026-08-13T18:47:34.345492Z","submitted_at":"2026-06-11T06:06:02Z","title":"Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignment","version":1},"reference_index":77,"source":"arxiv_source","source_observed_at":"2026-06-27T06:05:26.735340Z"},"links":{"cited_paper":"/paper/2406.10735","citing_paper":"/paper/2606.12940"},"observation_digest":"sha256:8350b8bcf0463d12ff1f3d18653166b75591ae014735c3941e5d281026af0603","observation_id":"b4fe5b26-44e0-4c80-b291-bd45e6787f1e","resolution":{"observed_at":"2026-07-03T16:08:37.448943Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.10735","last_updated":"2024-06-15T20:43:07Z","snapshot_observed_at":"2026-08-12T23:41:58.405020Z","submitted_at":"2024-06-15T20:43:07Z","title":"How Should We Extract Discrete Audio Tokens from Self-Supervised Models?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.10735","snapshot_observed_at":"2026-08-03T08:35:53.725939Z","title":"How should we extract discrete audio tokens from self-supervised models?arXiv preprint arXiv:2406.10735, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.29363","last_updated":"2026-07-31T12:51:24Z","snapshot_observed_at":"2026-08-11T13:01:28.550051Z","submitted_at":"2026-07-31T12:51:24Z","title":"Stable Autoregressive Speech Generation with Low-Frame-Rate High-Dimensional Continuous Tokens","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-03T08:35:53.725939Z"},"links":{"cited_paper":"/paper/2406.10735","citing_paper":"/paper/2607.29363"},"observation_digest":"sha256:427fc146a1fc200b81b2fff4a46eca91de425317a8a1826fc663ae734e9b7ea1","observation_id":"9305c4ad-b73a-4cd5-abea-2a92cc103243","resolution":{"observed_at":"2026-08-03T08:35:53.725939Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2406.10735/citation-record","integrity":"/paper/2406.10735/integrity","json":"/paper/2406.10735/citation-record.json","paper":"/paper/2406.10735"},"outbound":[],"paper":{"arxiv_id":"2406.10735","last_updated":"2024-06-15T20:43:07Z","latest_version":1,"primary_category":"cs.SD","snapshot_observed_at":"2026-08-12T23:41:58.405020Z","submitted_at":"2024-06-15T20:43:07Z","title":"How Should We Extract Discrete Audio Tokens from Self-Supervised Models?"},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2406.10735."}