{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5C2EDHDMVKVKRQA3MXG32YZNWB","short_pith_number":"pith:5C2EDHDM","schema_version":"1.0","canonical_sha256":"e8b4419c6caaaaa8c01b65cdbd632db07a0209e4b6f92bcf65692184a6c37cee","source":{"kind":"arxiv","id":"2605.29948","version":1},"attestation_state":"computed","paper":{"title":"HoliTok:A Coutinuous Holistic Tokenization with Robust Dual Capabilities of Speech Generation and Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bohan Li, Colin Zhang, Da Zheng, Hankun Wang, Kai Yu, Shi Lian, Yiwei Guo, Yu Xi, Zhihan Li","submitted_at":"2026-05-28T13:55:19Z","abstract_excerpt":"Unified speech foundation models require a holistic tokenization space that is both learnable by language models and decodable into high-quality waveforms. Existing speech tokenizers, however, often fail to satisfy these requirements simultaneously, leading to increased architectural complexity and more involved training designs. We propose HoliTok, a continuous Holistic speech Tokenization model designed for unified generation-understanding modeling. HoliTok encodes 48~kHz speech into a compact 25~Hz sequence of 128-dimensional latents. It is trained with a progressive strategy that jointly p"},"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":"2605.29948","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-05-28T13:55:19Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"c7db9f7077b6cdc89b76f33842a698d4508162238cec8ed75e77140a69033e7e","abstract_canon_sha256":"f85cf0fcaba4b1a5bb6419a01fe7696060431ae1e6b42bb27a8cdd2055ba33a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:02.892178Z","signature_b64":"FTOtyzGjrIcpmdoXBuN6M64iKBGwbWwP64R8VxzvWG9cygWScs4zWwASiQfqD7ZUfaFU35W6o3BZeD+JN9twCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8b4419c6caaaaa8c01b65cdbd632db07a0209e4b6f92bcf65692184a6c37cee","last_reissued_at":"2026-05-29T02:06:02.891416Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:02.891416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HoliTok:A Coutinuous Holistic Tokenization with Robust Dual Capabilities of Speech Generation and Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bohan Li, Colin Zhang, Da Zheng, Hankun Wang, Kai Yu, Shi Lian, Yiwei Guo, Yu Xi, Zhihan Li","submitted_at":"2026-05-28T13:55:19Z","abstract_excerpt":"Unified speech foundation models require a holistic tokenization space that is both learnable by language models and decodable into high-quality waveforms. Existing speech tokenizers, however, often fail to satisfy these requirements simultaneously, leading to increased architectural complexity and more involved training designs. We propose HoliTok, a continuous Holistic speech Tokenization model designed for unified generation-understanding modeling. HoliTok encodes 48~kHz speech into a compact 25~Hz sequence of 128-dimensional latents. It is trained with a progressive strategy that jointly p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29948","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/2605.29948/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":"2605.29948","created_at":"2026-05-29T02:06:02.891551+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29948v1","created_at":"2026-05-29T02:06:02.891551+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29948","created_at":"2026-05-29T02:06:02.891551+00:00"},{"alias_kind":"pith_short_12","alias_value":"5C2EDHDMVKVK","created_at":"2026-05-29T02:06:02.891551+00:00"},{"alias_kind":"pith_short_16","alias_value":"5C2EDHDMVKVKRQA3","created_at":"2026-05-29T02:06:02.891551+00:00"},{"alias_kind":"pith_short_8","alias_value":"5C2EDHDM","created_at":"2026-05-29T02:06:02.891551+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/5C2EDHDMVKVKRQA3MXG32YZNWB","json":"https://pith.science/pith/5C2EDHDMVKVKRQA3MXG32YZNWB.json","graph_json":"https://pith.science/api/pith-number/5C2EDHDMVKVKRQA3MXG32YZNWB/graph.json","events_json":"https://pith.science/api/pith-number/5C2EDHDMVKVKRQA3MXG32YZNWB/events.json","paper":"https://pith.science/paper/5C2EDHDM"},"agent_actions":{"view_html":"https://pith.science/pith/5C2EDHDMVKVKRQA3MXG32YZNWB","download_json":"https://pith.science/pith/5C2EDHDMVKVKRQA3MXG32YZNWB.json","view_paper":"https://pith.science/paper/5C2EDHDM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29948&json=true","fetch_graph":"https://pith.science/api/pith-number/5C2EDHDMVKVKRQA3MXG32YZNWB/graph.json","fetch_events":"https://pith.science/api/pith-number/5C2EDHDMVKVKRQA3MXG32YZNWB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5C2EDHDMVKVKRQA3MXG32YZNWB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5C2EDHDMVKVKRQA3MXG32YZNWB/action/storage_attestation","attest_author":"https://pith.science/pith/5C2EDHDMVKVKRQA3MXG32YZNWB/action/author_attestation","sign_citation":"https://pith.science/pith/5C2EDHDMVKVKRQA3MXG32YZNWB/action/citation_signature","submit_replication":"https://pith.science/pith/5C2EDHDMVKVKRQA3MXG32YZNWB/action/replication_record"}},"created_at":"2026-05-29T02:06:02.891551+00:00","updated_at":"2026-05-29T02:06:02.891551+00:00"}