{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LMYVSNTKBAYM6MYMNS7H2DHA3F","short_pith_number":"pith:LMYVSNTK","schema_version":"1.0","canonical_sha256":"5b3159366a0830cf330c6cbe7d0ce0d97da5f9e2522f06dc55f9d4cc916a06f5","source":{"kind":"arxiv","id":"2508.11224","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking Prosody Encoding in Discrete Speech Tokens","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Daisuke Saito, Kentaro Onda, Nobuaki Minematsu, Satoru Fukayama","submitted_at":"2025-08-15T05:11:16Z","abstract_excerpt":"Recently, discrete tokens derived from self-supervised learning (SSL) models via k-means clustering have been actively studied as pseudo-text in speech language models and as efficient intermediate representations for various tasks. However, these discrete tokens are typically learned in advance, separately from the training of language models or downstream tasks. As a result, choices related to discretization, such as the SSL model used or the number of clusters, must be made heuristically. In particular, speech language models are expected to understand and generate responses that reflect no"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2508.11224","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-08-15T05:11:16Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"8d15b349924f117c4e6a5b344771514d8b202fd3dc9abcbacd13a6a8bff8f160","abstract_canon_sha256":"581db5f4f0a4170ee1b64b56a82075bd4d037dfdbbece0c79edc2bb624d4fb80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:20.940681Z","signature_b64":"NhNUeQp7wkKBrjTLD7xj6vQ1/MN9IdZcxo6YlJJYNyqdZqlOkQ6JE8Qq3BMcu6TNbQIQWh7S2FQCWepEhCqOCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b3159366a0830cf330c6cbe7d0ce0d97da5f9e2522f06dc55f9d4cc916a06f5","last_reissued_at":"2026-07-05T11:54:20.940238Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:20.940238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Prosody Encoding in Discrete Speech Tokens","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Daisuke Saito, Kentaro Onda, Nobuaki Minematsu, Satoru Fukayama","submitted_at":"2025-08-15T05:11:16Z","abstract_excerpt":"Recently, discrete tokens derived from self-supervised learning (SSL) models via k-means clustering have been actively studied as pseudo-text in speech language models and as efficient intermediate representations for various tasks. However, these discrete tokens are typically learned in advance, separately from the training of language models or downstream tasks. As a result, choices related to discretization, such as the SSL model used or the number of clusters, must be made heuristically. In particular, speech language models are expected to understand and generate responses that reflect no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11224","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.11224/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2508.11224","created_at":"2026-07-05T11:54:20.940294+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.11224v1","created_at":"2026-07-05T11:54:20.940294+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11224","created_at":"2026-07-05T11:54:20.940294+00:00"},{"alias_kind":"pith_short_12","alias_value":"LMYVSNTKBAYM","created_at":"2026-07-05T11:54:20.940294+00:00"},{"alias_kind":"pith_short_16","alias_value":"LMYVSNTKBAYM6MYM","created_at":"2026-07-05T11:54:20.940294+00:00"},{"alias_kind":"pith_short_8","alias_value":"LMYVSNTK","created_at":"2026-07-05T11:54:20.940294+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LMYVSNTKBAYM6MYMNS7H2DHA3F","json":"https://pith.science/pith/LMYVSNTKBAYM6MYMNS7H2DHA3F.json","graph_json":"https://pith.science/api/pith-number/LMYVSNTKBAYM6MYMNS7H2DHA3F/graph.json","events_json":"https://pith.science/api/pith-number/LMYVSNTKBAYM6MYMNS7H2DHA3F/events.json","paper":"https://pith.science/paper/LMYVSNTK"},"agent_actions":{"view_html":"https://pith.science/pith/LMYVSNTKBAYM6MYMNS7H2DHA3F","download_json":"https://pith.science/pith/LMYVSNTKBAYM6MYMNS7H2DHA3F.json","view_paper":"https://pith.science/paper/LMYVSNTK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.11224&json=true","fetch_graph":"https://pith.science/api/pith-number/LMYVSNTKBAYM6MYMNS7H2DHA3F/graph.json","fetch_events":"https://pith.science/api/pith-number/LMYVSNTKBAYM6MYMNS7H2DHA3F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LMYVSNTKBAYM6MYMNS7H2DHA3F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LMYVSNTKBAYM6MYMNS7H2DHA3F/action/storage_attestation","attest_author":"https://pith.science/pith/LMYVSNTKBAYM6MYMNS7H2DHA3F/action/author_attestation","sign_citation":"https://pith.science/pith/LMYVSNTKBAYM6MYMNS7H2DHA3F/action/citation_signature","submit_replication":"https://pith.science/pith/LMYVSNTKBAYM6MYMNS7H2DHA3F/action/replication_record"}},"created_at":"2026-07-05T11:54:20.940294+00:00","updated_at":"2026-07-05T11:54:20.940294+00:00"}