{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VDHPDHEJUHJPVTIOJ75F7NEXJB","short_pith_number":"pith:VDHPDHEJ","canonical_record":{"source":{"id":"2608.11737","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-12T07:23:54Z","cross_cats_sorted":[],"title_canon_sha256":"18531b11d99f3cfccfd0fe945eb1f809e56e8d61522121afee0cffaad419c7ac","abstract_canon_sha256":"257e5903daef31cf07d2af03fa353fd83280403b4335abdfe69d917c0d463ba2"},"schema_version":"1.0"},"canonical_sha256":"a8cef19c89a1d2facd0e4ffa5fb497486921688d4e9262ae6978a54d47ab9e04","source":{"kind":"arxiv","id":"2608.11737","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.11737","created_at":"2026-08-13T01:27:58Z"},{"alias_kind":"arxiv_version","alias_value":"2608.11737v1","created_at":"2026-08-13T01:27:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11737","created_at":"2026-08-13T01:27:58Z"},{"alias_kind":"pith_short_12","alias_value":"VDHPDHEJUHJP","created_at":"2026-08-13T01:27:58Z"},{"alias_kind":"pith_short_16","alias_value":"VDHPDHEJUHJPVTIO","created_at":"2026-08-13T01:27:58Z"},{"alias_kind":"pith_short_8","alias_value":"VDHPDHEJ","created_at":"2026-08-13T01:27:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VDHPDHEJUHJPVTIOJ75F7NEXJB","target":"record","payload":{"canonical_record":{"source":{"id":"2608.11737","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-12T07:23:54Z","cross_cats_sorted":[],"title_canon_sha256":"18531b11d99f3cfccfd0fe945eb1f809e56e8d61522121afee0cffaad419c7ac","abstract_canon_sha256":"257e5903daef31cf07d2af03fa353fd83280403b4335abdfe69d917c0d463ba2"},"schema_version":"1.0"},"canonical_sha256":"a8cef19c89a1d2facd0e4ffa5fb497486921688d4e9262ae6978a54d47ab9e04","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-13T01:27:58.077271Z","signature_b64":"YHHAa5OBSHCBsWzeBOKcsphxVTmEbwHV04NEdRWpUgYndSzSzXi38XdsAIRIeQsgjGQUJMH7t69n29onADdWCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8cef19c89a1d2facd0e4ffa5fb497486921688d4e9262ae6978a54d47ab9e04","last_reissued_at":"2026-08-13T01:27:58.074193Z","signature_status":"signed_v1","first_computed_at":"2026-08-13T01:27:58.074193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.11737","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":"2026-08-13T01:27:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/nlEkfQjdd+f9XmfBxTCvK39/+VZeXoSusxilgWXQJMhj2AMEaMPER2JgVAz7aEUfuHWXCDevfaYck20+EJTAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T04:47:21.445252Z"},"content_sha256":"e8213bbaa5ec025c95172478632f3dc1fe6f5767d0da24f5bd18b34488ba1d0b","schema_version":"1.0","event_id":"sha256:e8213bbaa5ec025c95172478632f3dc1fe6f5767d0da24f5bd18b34488ba1d0b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VDHPDHEJUHJPVTIOJ75F7NEXJB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Phoenix TTS: High-Fidelity Synthesis and Voice Conversion via Flow-Matching-Driven Speech Tokenization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Daiyu Huang, Hua Chai, Junbo Li, Jun Fang, Naiqiang Tan, Peijie Chen, Qingyang Hong, Weijie Wu, Yiming Liu, Zhipeng Nie, Zhuanling Zha","submitted_at":"2026-08-12T07:23:54Z","abstract_excerpt":"In current zero-shot text-to-speech systems, conventional semantic tokenizers are typically optimized using supervised automatic speech recognition or self-supervised learning objectives. However, due to the inherent nature of speech, semantic and acoustic information cannot be completely decoupled, and ASR-based tokenizers discard acoustic details to focus on linguistic content; models relying on them usually struggle to achieve optimal speaker similarity. Furthermore, these tokenizers are optimized independently and lack direct supervision from downstream acoustic generation tasks. This isol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11737","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/2608.11737/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":"2026-08-13T01:27:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EMxyP8qAZBqDW5E1yk2jIS8G4q8UJtHK7/IAzILw4ksFmq2vZcxOqAEfxpzR8N+NoVRaBXHF+b7UxN7lN2rKCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T04:47:21.445846Z"},"content_sha256":"a72d3f16a88e36231d7e408a1f0e9934cabcd2f3e7df7c3c25ec87f493acbd9a","schema_version":"1.0","event_id":"sha256:a72d3f16a88e36231d7e408a1f0e9934cabcd2f3e7df7c3c25ec87f493acbd9a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VDHPDHEJUHJPVTIOJ75F7NEXJB/bundle.json","state_url":"https://pith.science/pith/VDHPDHEJUHJPVTIOJ75F7NEXJB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VDHPDHEJUHJPVTIOJ75F7NEXJB/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":"2026-08-18T04:47:21Z","links":{"resolver":"https://pith.science/pith/VDHPDHEJUHJPVTIOJ75F7NEXJB","bundle":"https://pith.science/pith/VDHPDHEJUHJPVTIOJ75F7NEXJB/bundle.json","state":"https://pith.science/pith/VDHPDHEJUHJPVTIOJ75F7NEXJB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VDHPDHEJUHJPVTIOJ75F7NEXJB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VDHPDHEJUHJPVTIOJ75F7NEXJB","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":"257e5903daef31cf07d2af03fa353fd83280403b4335abdfe69d917c0d463ba2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-12T07:23:54Z","title_canon_sha256":"18531b11d99f3cfccfd0fe945eb1f809e56e8d61522121afee0cffaad419c7ac"},"schema_version":"1.0","source":{"id":"2608.11737","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.11737","created_at":"2026-08-13T01:27:58Z"},{"alias_kind":"arxiv_version","alias_value":"2608.11737v1","created_at":"2026-08-13T01:27:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11737","created_at":"2026-08-13T01:27:58Z"},{"alias_kind":"pith_short_12","alias_value":"VDHPDHEJUHJP","created_at":"2026-08-13T01:27:58Z"},{"alias_kind":"pith_short_16","alias_value":"VDHPDHEJUHJPVTIO","created_at":"2026-08-13T01:27:58Z"},{"alias_kind":"pith_short_8","alias_value":"VDHPDHEJ","created_at":"2026-08-13T01:27:58Z"}],"graph_snapshots":[{"event_id":"sha256:a72d3f16a88e36231d7e408a1f0e9934cabcd2f3e7df7c3c25ec87f493acbd9a","target":"graph","created_at":"2026-08-13T01:27:58Z","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/2608.11737/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In current zero-shot text-to-speech systems, conventional semantic tokenizers are typically optimized using supervised automatic speech recognition or self-supervised learning objectives. However, due to the inherent nature of speech, semantic and acoustic information cannot be completely decoupled, and ASR-based tokenizers discard acoustic details to focus on linguistic content; models relying on them usually struggle to achieve optimal speaker similarity. Furthermore, these tokenizers are optimized independently and lack direct supervision from downstream acoustic generation tasks. This isol","authors_text":"Daiyu Huang, Hua Chai, Junbo Li, Jun Fang, Naiqiang Tan, Peijie Chen, Qingyang Hong, Weijie Wu, Yiming Liu, Zhipeng Nie, Zhuanling Zha","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-12T07:23:54Z","title":"Phoenix TTS: High-Fidelity Synthesis and Voice Conversion via Flow-Matching-Driven Speech Tokenization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11737","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:e8213bbaa5ec025c95172478632f3dc1fe6f5767d0da24f5bd18b34488ba1d0b","target":"record","created_at":"2026-08-13T01:27:58Z","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":"257e5903daef31cf07d2af03fa353fd83280403b4335abdfe69d917c0d463ba2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-12T07:23:54Z","title_canon_sha256":"18531b11d99f3cfccfd0fe945eb1f809e56e8d61522121afee0cffaad419c7ac"},"schema_version":"1.0","source":{"id":"2608.11737","kind":"arxiv","version":1}},"canonical_sha256":"a8cef19c89a1d2facd0e4ffa5fb497486921688d4e9262ae6978a54d47ab9e04","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8cef19c89a1d2facd0e4ffa5fb497486921688d4e9262ae6978a54d47ab9e04","first_computed_at":"2026-08-13T01:27:58.074193Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-13T01:27:58.074193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YHHAa5OBSHCBsWzeBOKcsphxVTmEbwHV04NEdRWpUgYndSzSzXi38XdsAIRIeQsgjGQUJMH7t69n29onADdWCw==","signature_status":"signed_v1","signed_at":"2026-08-13T01:27:58.077271Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.11737","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8213bbaa5ec025c95172478632f3dc1fe6f5767d0da24f5bd18b34488ba1d0b","sha256:a72d3f16a88e36231d7e408a1f0e9934cabcd2f3e7df7c3c25ec87f493acbd9a"],"state_sha256":"9d7c491b0875b3af727459d408a09a505eff98c97c1ca8cc3d2e93f705067002"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R8JwwYHNo4r7OzJT5BFffWm3/yvYHJrw/jfdwZysGxKjaf0zboWKe3lmaPvJE5z/V1KIRtqlnLx3HElqmJeHAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T04:47:21.450063Z","bundle_sha256":"7f65dbe812063824ef649c1be97ddda6addf066ef5cfae31239664afa894260f"}}