{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KTRX56IMPTTSRHR2O7ERTXSVUP","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":"26e63f46c9a7e6f9461fbc2c48b53444baa7129d0d3df2dc914b4722ec6f045b","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-10-11T07:23:27Z","title_canon_sha256":"594c302f269b4704177b547b80b5215f383c6c701762b255911bd39b4d1cd06f"},"schema_version":"1.0","source":{"id":"2310.07246","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.07246","created_at":"2026-07-05T06:59:55Z"},{"alias_kind":"arxiv_version","alias_value":"2310.07246v2","created_at":"2026-07-05T06:59:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07246","created_at":"2026-07-05T06:59:55Z"},{"alias_kind":"pith_short_12","alias_value":"KTRX56IMPTTS","created_at":"2026-07-05T06:59:55Z"},{"alias_kind":"pith_short_16","alias_value":"KTRX56IMPTTSRHR2","created_at":"2026-07-05T06:59:55Z"},{"alias_kind":"pith_short_8","alias_value":"KTRX56IM","created_at":"2026-07-05T06:59:55Z"}],"graph_snapshots":[{"event_id":"sha256:5eefdd77fb538b90f401ebeff0802d90e454e1e20e164f6c37d7e6de94b0a5b6","target":"graph","created_at":"2026-07-05T06:59:55Z","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/2310.07246/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models (LMs) have recently flourished in natural language processing and computer vision, generating high-fidelity texts or images in various tasks. In contrast, the current speech generative models are still struggling regarding speech quality and task generalization. This paper presents Vec-Tok Speech, an extensible framework that resembles multiple speech generation tasks, generating expressive and high-fidelity speech. Specifically, we propose a novel speech codec based on speech vectors and semantic tokens. Speech vectors contain acoustic details contributing to high-fidelity spe","authors_text":"Heng Lu, Hongbin Zhou, Lei Xie, Tao Li, Wendi He, Xinfa Zhu, Yi Lei, Yuanjun Lv","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-10-11T07:23:27Z","title":"Vec-Tok Speech: speech vectorization and tokenization for neural speech generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07246","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":"sha256:1e3328afb8ef836a106ef283f332de05cd180e137daf1c1da98c88b4d9c1f88b","target":"record","created_at":"2026-07-05T06:59:55Z","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":"26e63f46c9a7e6f9461fbc2c48b53444baa7129d0d3df2dc914b4722ec6f045b","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-10-11T07:23:27Z","title_canon_sha256":"594c302f269b4704177b547b80b5215f383c6c701762b255911bd39b4d1cd06f"},"schema_version":"1.0","source":{"id":"2310.07246","kind":"arxiv","version":2}},"canonical_sha256":"54e37ef90c7ce7289e3a77c919de55a3f7d7b30d05b067c3ea9952dfdc7dfb61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54e37ef90c7ce7289e3a77c919de55a3f7d7b30d05b067c3ea9952dfdc7dfb61","first_computed_at":"2026-07-05T06:59:55.234659Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:59:55.234659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rIsNXThXQ9QJ+CHQUQg7CccqdI3hgUx6MKXJSTa6O6HjTLV6kgdn6lIq5XH8PVkE+ks8nJ8IGS29ItA6IK7fDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:59:55.235262Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.07246","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e3328afb8ef836a106ef283f332de05cd180e137daf1c1da98c88b4d9c1f88b","sha256:5eefdd77fb538b90f401ebeff0802d90e454e1e20e164f6c37d7e6de94b0a5b6"],"state_sha256":"c3c7fa564e098900049086fdd41b6cb60698a595b8481ebfb6b193f28102a2f2"}