{"as_of":"2026-08-08T13:32:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7d8b23e3467b6f4412858ced96c00995316ec838daadfdd15a5b295ab02cb773","coverage":[{"denominator":4,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T11:31:44.746186Z","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":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2601.06329/citation-record","integrity":"/paper/2601.06329/integrity","json":"/paper/2601.06329/citation-record.json","paper":"/paper/2601.06329"},"outbound":[{"citation":{"cited_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},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.02111","snapshot_observed_at":"2026-08-03T11:31:44.746186Z","title":"InFindings of the Association for Computa- tional Linguistics: EMNLP 2022, pages 2707–2735, Abu Dhabi, United Arab Emirates","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.06329","last_updated":"2026-05-27T06:16:34Z","snapshot_observed_at":"2026-08-07T23:22:41.531750Z","submitted_at":"2026-01-09T22:01:56Z","title":"On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-03T11:31:44.746186Z"},"links":{"cited_paper":"/paper/2301.02111","citing_paper":"/paper/2601.06329"},"observation_digest":"sha256:07844a9acb82efef6fca060dc8d905427aa5a62ce2b2ed295e93721260d11dc0","observation_id":"07662bee-7395-480a-923e-d7af4d78f88c","resolution":{"observed_at":"2026-08-03T11:31:44.746186Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.17790","last_updated":"2025-01-29T17:31:26Z","snapshot_observed_at":"2026-07-06T20:28:00.278440Z","submitted_at":"2025-01-29T17:31:26Z","title":"BreezyVoice: Adapting TTS for Taiwanese Mandarin with Enhanced Polyphone Disambiguation -- Challenges and Insights","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.17790","snapshot_observed_at":"2026-08-03T11:31:44.503670Z","title":"Michael Hassid and 1 others","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.06329","last_updated":"2026-05-27T06:16:34Z","snapshot_observed_at":"2026-08-07T23:22:41.531750Z","submitted_at":"2026-01-09T22:01:56Z","title":"On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation","version":2},"reference_index":1330,"source":"pdf_text","source_observed_at":"2026-08-03T11:31:44.503670Z"},"links":{"cited_paper":"/paper/2501.17790","citing_paper":"/paper/2601.06329"},"observation_digest":"sha256:ca51396425e2f8af75c474d4611693a67faa6b826c05774e6851a89336f32d92","observation_id":"0dfdce69-0174-4c19-844f-12ec5399337b","resolution":{"observed_at":"2026-08-03T11:31:44.503670Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.05755","last_updated":"2024-10-18T19:18:41Z","snapshot_observed_at":"2026-08-07T23:22:37.030139Z","submitted_at":"2024-02-08T15:39:32Z","title":"Spirit LM: Interleaved Spoken and Written Language Model","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.05755","snapshot_observed_at":"2026-08-03T11:31:44.660373Z","title":"InICASSP 2022-2022 IEEE inter- national conference on acoustics, speech and signal processing (ICASSP), pages 8102–8106","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.06329","last_updated":"2026-05-27T06:16:34Z","snapshot_observed_at":"2026-08-07T23:22:41.531750Z","submitted_at":"2026-01-09T22:01:56Z","title":"On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-03T11:31:44.660373Z"},"links":{"cited_paper":"/paper/2402.05755","citing_paper":"/paper/2601.06329"},"observation_digest":"sha256:41fa747e55cd2e80f6d5a10973a5a6b3cdb068f9c008b9f0663ec1014bdb43d9","observation_id":"5032c03a-d9be-4e89-aadc-7d568ef02363","resolution":{"observed_at":"2026-08-03T11:31:44.660373Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.10759","last_updated":"2024-07-15T14:38:09Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-07-15T14:38:09Z","title":"Qwen2-Audio Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.10759","snapshot_observed_at":"2026-08-03T11:31:44.401702Z","title":"Yung-Sung Chuang, Yujia Xie, Hongyin Luo, Yoon Kim, James R","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.06329","last_updated":"2026-05-27T06:16:34Z","snapshot_observed_at":"2026-08-07T23:22:41.531750Z","submitted_at":"2026-01-09T22:01:56Z","title":"On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-03T11:31:44.401702Z"},"links":{"cited_paper":"/paper/2407.10759","citing_paper":"/paper/2601.06329"},"observation_digest":"sha256:aa520cab142a0073b61eee955468f81f99667e52aac9203df0af60b5db54e89c","observation_id":"9ce6841b-4f51-4132-a1a3-f153cc499f68","resolution":{"observed_at":"2026-08-03T11:31:44.401702Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2601.06329","last_updated":"2026-05-27T06:16:34Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-07T23:22:41.531750Z","submitted_at":"2026-01-09T22:01:56Z","title":"On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation"},"reference_resolution":{"displayed":4,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":3,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":4},"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 4 of 4 outbound references and 0 inbound Pith citation observations for arXiv:2601.06329."}