{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5C2EDHDMVKVKRQA3MXG32YZNWB","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":"f85cf0fcaba4b1a5bb6419a01fe7696060431ae1e6b42bb27a8cdd2055ba33a8","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-05-28T13:55:19Z","title_canon_sha256":"c7db9f7077b6cdc89b76f33842a698d4508162238cec8ed75e77140a69033e7e"},"schema_version":"1.0","source":{"id":"2605.29948","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29948","created_at":"2026-05-29T02:06:02Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29948v1","created_at":"2026-05-29T02:06:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29948","created_at":"2026-05-29T02:06:02Z"},{"alias_kind":"pith_short_12","alias_value":"5C2EDHDMVKVK","created_at":"2026-05-29T02:06:02Z"},{"alias_kind":"pith_short_16","alias_value":"5C2EDHDMVKVKRQA3","created_at":"2026-05-29T02:06:02Z"},{"alias_kind":"pith_short_8","alias_value":"5C2EDHDM","created_at":"2026-05-29T02:06:02Z"}],"graph_snapshots":[{"event_id":"sha256:c14aa147d36889cbcc0d886984a597fd34727316bc6cf0bdacf992d096d55e18","target":"graph","created_at":"2026-05-29T02:06:02Z","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/2605.29948/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bohan Li, Colin Zhang, Da Zheng, Hankun Wang, Kai Yu, Shi Lian, Yiwei Guo, Yu Xi, Zhihan Li","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-05-28T13:55:19Z","title":"HoliTok:A Coutinuous Holistic Tokenization with Robust Dual Capabilities of Speech Generation and Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29948","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":"sha256:3f801c75c4bce391ef62787456abaa37258f107d508f6d3c39bded4190966a9e","target":"record","created_at":"2026-05-29T02:06:02Z","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":"f85cf0fcaba4b1a5bb6419a01fe7696060431ae1e6b42bb27a8cdd2055ba33a8","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-05-28T13:55:19Z","title_canon_sha256":"c7db9f7077b6cdc89b76f33842a698d4508162238cec8ed75e77140a69033e7e"},"schema_version":"1.0","source":{"id":"2605.29948","kind":"arxiv","version":1}},"canonical_sha256":"e8b4419c6caaaaa8c01b65cdbd632db07a0209e4b6f92bcf65692184a6c37cee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8b4419c6caaaaa8c01b65cdbd632db07a0209e4b6f92bcf65692184a6c37cee","first_computed_at":"2026-05-29T02:06:02.891416Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:06:02.891416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FTOtyzGjrIcpmdoXBuN6M64iKBGwbWwP64R8VxzvWG9cygWScs4zWwASiQfqD7ZUfaFU35W6o3BZeD+JN9twCA==","signature_status":"signed_v1","signed_at":"2026-05-29T02:06:02.892178Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29948","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f801c75c4bce391ef62787456abaa37258f107d508f6d3c39bded4190966a9e","sha256:c14aa147d36889cbcc0d886984a597fd34727316bc6cf0bdacf992d096d55e18"],"state_sha256":"0b54ac7f6fde57f01cf4620bf91c76ca6bac5545a7d44f9cf9cf348e81386438"}