{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LMYVSNTKBAYM6MYMNS7H2DHA3F","short_pith_number":"pith:LMYVSNTK","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"},"canonical_sha256":"5b3159366a0830cf330c6cbe7d0ce0d97da5f9e2522f06dc55f9d4cc916a06f5","source":{"kind":"arxiv","id":"2508.11224","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.11224","created_at":"2026-07-05T11:54:20Z"},{"alias_kind":"arxiv_version","alias_value":"2508.11224v1","created_at":"2026-07-05T11:54:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11224","created_at":"2026-07-05T11:54:20Z"},{"alias_kind":"pith_short_12","alias_value":"LMYVSNTKBAYM","created_at":"2026-07-05T11:54:20Z"},{"alias_kind":"pith_short_16","alias_value":"LMYVSNTKBAYM6MYM","created_at":"2026-07-05T11:54:20Z"},{"alias_kind":"pith_short_8","alias_value":"LMYVSNTK","created_at":"2026-07-05T11:54:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LMYVSNTKBAYM6MYMNS7H2DHA3F","target":"record","payload":{"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"},"canonical_sha256":"5b3159366a0830cf330c6cbe7d0ce0d97da5f9e2522f06dc55f9d4cc916a06f5","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"},"source_kind":"arxiv","source_id":"2508.11224","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:54:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WLASkGqBhY0Qa7iysi/YgQtQPmUGdbP0J/DnKZmzeLIvuIqYRJLRkOE0yf9h5RNNZ7qE2aprHLEmEpBQvMh1BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:24:11.405178Z"},"content_sha256":"143ef35aa19a683fad4b6183088eb36f2daf03064dfde4d4e812de273a421bef","schema_version":"1.0","event_id":"sha256:143ef35aa19a683fad4b6183088eb36f2daf03064dfde4d4e812de273a421bef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LMYVSNTKBAYM6MYMNS7H2DHA3F","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:54:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u7lHVdWdY/0LiwVJonBqPhVkJPgxC8RJ79GVuXpH0V7QUev2UsY6wgr0Cect4+20Ol+C9nwOiRDuv0pPEv+SCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:24:11.405702Z"},"content_sha256":"705e571d023109f681f044049e4dc122150f5a86fb68368e621a39e7e82146f9","schema_version":"1.0","event_id":"sha256:705e571d023109f681f044049e4dc122150f5a86fb68368e621a39e7e82146f9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LMYVSNTKBAYM6MYMNS7H2DHA3F/bundle.json","state_url":"https://pith.science/pith/LMYVSNTKBAYM6MYMNS7H2DHA3F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LMYVSNTKBAYM6MYMNS7H2DHA3F/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T13:24:11Z","links":{"resolver":"https://pith.science/pith/LMYVSNTKBAYM6MYMNS7H2DHA3F","bundle":"https://pith.science/pith/LMYVSNTKBAYM6MYMNS7H2DHA3F/bundle.json","state":"https://pith.science/pith/LMYVSNTKBAYM6MYMNS7H2DHA3F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LMYVSNTKBAYM6MYMNS7H2DHA3F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LMYVSNTKBAYM6MYMNS7H2DHA3F","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"581db5f4f0a4170ee1b64b56a82075bd4d037dfdbbece0c79edc2bb624d4fb80","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-08-15T05:11:16Z","title_canon_sha256":"8d15b349924f117c4e6a5b344771514d8b202fd3dc9abcbacd13a6a8bff8f160"},"schema_version":"1.0","source":{"id":"2508.11224","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.11224","created_at":"2026-07-05T11:54:20Z"},{"alias_kind":"arxiv_version","alias_value":"2508.11224v1","created_at":"2026-07-05T11:54:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11224","created_at":"2026-07-05T11:54:20Z"},{"alias_kind":"pith_short_12","alias_value":"LMYVSNTKBAYM","created_at":"2026-07-05T11:54:20Z"},{"alias_kind":"pith_short_16","alias_value":"LMYVSNTKBAYM6MYM","created_at":"2026-07-05T11:54:20Z"},{"alias_kind":"pith_short_8","alias_value":"LMYVSNTK","created_at":"2026-07-05T11:54:20Z"}],"graph_snapshots":[{"event_id":"sha256:705e571d023109f681f044049e4dc122150f5a86fb68368e621a39e7e82146f9","target":"graph","created_at":"2026-07-05T11:54:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2508.11224/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Daisuke Saito, Kentaro Onda, Nobuaki Minematsu, Satoru Fukayama","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-08-15T05:11:16Z","title":"Benchmarking Prosody Encoding in Discrete Speech Tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11224","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:143ef35aa19a683fad4b6183088eb36f2daf03064dfde4d4e812de273a421bef","target":"record","created_at":"2026-07-05T11:54:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"581db5f4f0a4170ee1b64b56a82075bd4d037dfdbbece0c79edc2bb624d4fb80","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-08-15T05:11:16Z","title_canon_sha256":"8d15b349924f117c4e6a5b344771514d8b202fd3dc9abcbacd13a6a8bff8f160"},"schema_version":"1.0","source":{"id":"2508.11224","kind":"arxiv","version":1}},"canonical_sha256":"5b3159366a0830cf330c6cbe7d0ce0d97da5f9e2522f06dc55f9d4cc916a06f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b3159366a0830cf330c6cbe7d0ce0d97da5f9e2522f06dc55f9d4cc916a06f5","first_computed_at":"2026-07-05T11:54:20.940238Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:54:20.940238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NhNUeQp7wkKBrjTLD7xj6vQ1/MN9IdZcxo6YlJJYNyqdZqlOkQ6JE8Qq3BMcu6TNbQIQWh7S2FQCWepEhCqOCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:54:20.940681Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.11224","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:143ef35aa19a683fad4b6183088eb36f2daf03064dfde4d4e812de273a421bef","sha256:705e571d023109f681f044049e4dc122150f5a86fb68368e621a39e7e82146f9"],"state_sha256":"2503d2493d3fdbd79217c775d15e10885df8c0e2f2ec44a1341808e909c83b29"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"703rB418WNBVetD4coTk7sRlQ5Cs/2jU5zUtYaglnmqd3IJRp5f6xELLyYQpY/wQITLt2lS0y77x82I/hOd0Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T13:24:11.409613Z","bundle_sha256":"1e49218973ced2c973089efdcb8c8d529783d1d7d3a36db1c166d1cc5d4d58c9"}}