{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:I32UCBHIJVS6NN2B5ZEAURLQF2","short_pith_number":"pith:I32UCBHI","canonical_record":{"source":{"id":"2505.17446","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T04:03:27Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"fd5723c81a2f986e32990d7c816d39ae9f2675fb097ebff5a4c3d4567857d011","abstract_canon_sha256":"56cb271e7823fbbf527f314d834b9117f804d1edadd4039f8d8a85b9a693c952"},"schema_version":"1.0"},"canonical_sha256":"46f54104e84d65e6b741ee480a45702ebba335cf975f9068834a260be7ab5c75","source":{"kind":"arxiv","id":"2505.17446","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17446","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17446v2","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17446","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"pith_short_12","alias_value":"I32UCBHIJVS6","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"pith_short_16","alias_value":"I32UCBHIJVS6NN2B","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"pith_short_8","alias_value":"I32UCBHI","created_at":"2026-07-05T11:13:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:I32UCBHIJVS6NN2B5ZEAURLQF2","target":"record","payload":{"canonical_record":{"source":{"id":"2505.17446","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T04:03:27Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"fd5723c81a2f986e32990d7c816d39ae9f2675fb097ebff5a4c3d4567857d011","abstract_canon_sha256":"56cb271e7823fbbf527f314d834b9117f804d1edadd4039f8d8a85b9a693c952"},"schema_version":"1.0"},"canonical_sha256":"46f54104e84d65e6b741ee480a45702ebba335cf975f9068834a260be7ab5c75","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:26.401008Z","signature_b64":"t3P71j/+Z2Yu0uL55rU7QtocqX3L86/1JJsG9hYQGEld2pCdI8fVzPlgKeQgzPjGp6Synl8Z+Vl0zoLPc+QaDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46f54104e84d65e6b741ee480a45702ebba335cf975f9068834a260be7ab5c75","last_reissued_at":"2026-07-05T11:13:26.400582Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:26.400582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.17446","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:13:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dTg+jpq91sSl8eImOI0yohwetKZlvL6LK/gcaeaY9tggE8sFpxF+hoqZtlyG0vD0T5mjCHML8u/74cjRX+zaDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:38:38.387201Z"},"content_sha256":"bd7f5009e87b0b693bfbf1e4a5ba88a218ab571bb1b525cfee5ad1da02b261cd","schema_version":"1.0","event_id":"sha256:bd7f5009e87b0b693bfbf1e4a5ba88a218ab571bb1b525cfee5ad1da02b261cd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:I32UCBHIJVS6NN2B5ZEAURLQF2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring the Effect of Segmentation and Vocabulary Size on Speech Tokenization for Speech Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Shinnosuke Takamichi, Shunsuke Kando, Yusuke Miyao","submitted_at":"2025-05-23T04:03:27Z","abstract_excerpt":"The purpose of speech tokenization is to transform a speech signal into a sequence of discrete representations, serving as the foundation for speech language models (SLMs). While speech tokenization has many options, their effect on the performance of SLMs remains unclear. This paper investigates two key aspects of speech tokenization: the segmentation width and the cluster size of discrete units. First, we segment speech signals into fixed/variable widths and pooled representations. We then train K-means models in multiple cluster sizes. Through the evaluation on zero-shot spoken language und"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17446","kind":"arxiv","version":2},"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/2505.17446/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":"2026-07-05T11:13:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZxfzD6rYTcKdqAuonW6//6fRYNJU02CnOGovUDErdvc4uuQt9L7yHb5b2R1AQ9HpfU5N4eYT2gKM6fjaAzEPCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:38:38.387770Z"},"content_sha256":"a34f53195b73b6876800c737830ffdc99e32a56be3c92bd97cc5e4ea04348c3b","schema_version":"1.0","event_id":"sha256:a34f53195b73b6876800c737830ffdc99e32a56be3c92bd97cc5e4ea04348c3b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I32UCBHIJVS6NN2B5ZEAURLQF2/bundle.json","state_url":"https://pith.science/pith/I32UCBHIJVS6NN2B5ZEAURLQF2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I32UCBHIJVS6NN2B5ZEAURLQF2/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":"2026-08-08T18:38:38Z","links":{"resolver":"https://pith.science/pith/I32UCBHIJVS6NN2B5ZEAURLQF2","bundle":"https://pith.science/pith/I32UCBHIJVS6NN2B5ZEAURLQF2/bundle.json","state":"https://pith.science/pith/I32UCBHIJVS6NN2B5ZEAURLQF2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I32UCBHIJVS6NN2B5ZEAURLQF2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:I32UCBHIJVS6NN2B5ZEAURLQF2","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":"56cb271e7823fbbf527f314d834b9117f804d1edadd4039f8d8a85b9a693c952","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T04:03:27Z","title_canon_sha256":"fd5723c81a2f986e32990d7c816d39ae9f2675fb097ebff5a4c3d4567857d011"},"schema_version":"1.0","source":{"id":"2505.17446","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17446","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17446v2","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17446","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"pith_short_12","alias_value":"I32UCBHIJVS6","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"pith_short_16","alias_value":"I32UCBHIJVS6NN2B","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"pith_short_8","alias_value":"I32UCBHI","created_at":"2026-07-05T11:13:26Z"}],"graph_snapshots":[{"event_id":"sha256:a34f53195b73b6876800c737830ffdc99e32a56be3c92bd97cc5e4ea04348c3b","target":"graph","created_at":"2026-07-05T11:13:26Z","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/2505.17446/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The purpose of speech tokenization is to transform a speech signal into a sequence of discrete representations, serving as the foundation for speech language models (SLMs). While speech tokenization has many options, their effect on the performance of SLMs remains unclear. This paper investigates two key aspects of speech tokenization: the segmentation width and the cluster size of discrete units. First, we segment speech signals into fixed/variable widths and pooled representations. We then train K-means models in multiple cluster sizes. Through the evaluation on zero-shot spoken language und","authors_text":"Shinnosuke Takamichi, Shunsuke Kando, Yusuke Miyao","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T04:03:27Z","title":"Exploring the Effect of Segmentation and Vocabulary Size on Speech Tokenization for Speech Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17446","kind":"arxiv","version":2},"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:bd7f5009e87b0b693bfbf1e4a5ba88a218ab571bb1b525cfee5ad1da02b261cd","target":"record","created_at":"2026-07-05T11:13:26Z","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":"56cb271e7823fbbf527f314d834b9117f804d1edadd4039f8d8a85b9a693c952","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T04:03:27Z","title_canon_sha256":"fd5723c81a2f986e32990d7c816d39ae9f2675fb097ebff5a4c3d4567857d011"},"schema_version":"1.0","source":{"id":"2505.17446","kind":"arxiv","version":2}},"canonical_sha256":"46f54104e84d65e6b741ee480a45702ebba335cf975f9068834a260be7ab5c75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"46f54104e84d65e6b741ee480a45702ebba335cf975f9068834a260be7ab5c75","first_computed_at":"2026-07-05T11:13:26.400582Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:26.400582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t3P71j/+Z2Yu0uL55rU7QtocqX3L86/1JJsG9hYQGEld2pCdI8fVzPlgKeQgzPjGp6Synl8Z+Vl0zoLPc+QaDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:26.401008Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17446","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd7f5009e87b0b693bfbf1e4a5ba88a218ab571bb1b525cfee5ad1da02b261cd","sha256:a34f53195b73b6876800c737830ffdc99e32a56be3c92bd97cc5e4ea04348c3b"],"state_sha256":"73ed4d5cd87dd5d3f4278e8804039d214fce72dfe64f556f7690dcbdafeb1bb1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZAby0b9omvA1gzUXRpzP/zkijWPmlMsXqNMCe6FO45xriOex9iOdQsXjM4Ea2VTIgjhC2c2gmwcRXUfpnZpDCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:38:38.391987Z","bundle_sha256":"ca77d0e15289df265b62a14ecbbbe6584a8c96dd13f5ee0f8afdf902d7d79504"}}