{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Y7EZTROBCZG2W5PNCHZDFTB7B7","short_pith_number":"pith:Y7EZTROB","canonical_record":{"source":{"id":"2403.03100","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-03-05T16:35:25Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"156635f6bc1afa00667493496dcbc18826ab03eeb0154c5d324c9ff0a34daa31","abstract_canon_sha256":"d354b3d922fc26a0ebbe569c925ec2be8a4b9991857202705ce84dbe5c2715f8"},"schema_version":"1.0"},"canonical_sha256":"c7c999c5c1164dab75ed11f232cc3f0ff66b09cf3a2d18159b76fb98d680f168","source":{"kind":"arxiv","id":"2403.03100","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.03100","created_at":"2026-07-05T08:11:02Z"},{"alias_kind":"arxiv_version","alias_value":"2403.03100v3","created_at":"2026-07-05T08:11:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03100","created_at":"2026-07-05T08:11:02Z"},{"alias_kind":"pith_short_12","alias_value":"Y7EZTROBCZG2","created_at":"2026-07-05T08:11:02Z"},{"alias_kind":"pith_short_16","alias_value":"Y7EZTROBCZG2W5PN","created_at":"2026-07-05T08:11:02Z"},{"alias_kind":"pith_short_8","alias_value":"Y7EZTROB","created_at":"2026-07-05T08:11:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Y7EZTROBCZG2W5PNCHZDFTB7B7","target":"record","payload":{"canonical_record":{"source":{"id":"2403.03100","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-03-05T16:35:25Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"156635f6bc1afa00667493496dcbc18826ab03eeb0154c5d324c9ff0a34daa31","abstract_canon_sha256":"d354b3d922fc26a0ebbe569c925ec2be8a4b9991857202705ce84dbe5c2715f8"},"schema_version":"1.0"},"canonical_sha256":"c7c999c5c1164dab75ed11f232cc3f0ff66b09cf3a2d18159b76fb98d680f168","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:02.277578Z","signature_b64":"t3p+2hR1DxncLYZ7HKi5VdHGL+WL2XLm68EBY5GX4GTGXCnQz3s0yi5pjv4+HnBewsllJZCRuhKfzNZWQfP2BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7c999c5c1164dab75ed11f232cc3f0ff66b09cf3a2d18159b76fb98d680f168","last_reissued_at":"2026-07-05T08:11:02.277137Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:02.277137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.03100","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:11:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+tqzaR1dIA6l48eKfDeXmEepMkWn1qyNLMuReI4SAgSPcG6w3+pToUZRoa4mEnAqXMOO2rDVgbt2+qmaq5BYBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:22:44.603932Z"},"content_sha256":"98106713fd315c6c04f69c01d1366a548d9a7439b0af826a713ba1a396586195","schema_version":"1.0","event_id":"sha256:98106713fd315c6c04f69c01d1366a548d9a7439b0af826a713ba1a396586195"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Y7EZTROBCZG2W5PNCHZDFTB7B7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Detai Xin, Dongchao Yang, Jiang Bian, Jinyu Li, Kai Shen, Kaitao Song, Lei He, Sheng Zhao, Shikun Zhang, Siliang Tang, Tao Qin, Wei Ye, Xiang-Yang Li, Xu Tan, Yanqing Liu, Yichong Leng, Yuancheng Wang, Zeqian Ju, Zhizheng Wu","submitted_at":"2024-03-05T16:35:25Z","abstract_excerpt":"While recent large-scale text-to-speech (TTS) models have achieved significant progress, they still fall short in speech quality, similarity, and prosody. Considering speech intricately encompasses various attributes (e.g., content, prosody, timbre, and acoustic details) that pose significant challenges for generation, a natural idea is to factorize speech into individual subspaces representing different attributes and generate them individually. Motivated by it, we propose NaturalSpeech 3, a TTS system with novel factorized diffusion models to generate natural speech in a zero-shot way. Speci"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03100","kind":"arxiv","version":3},"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/2403.03100/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":"2026-07-05T08:11:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NmSrcQwK41E11n/vhvl/Urgyeoq+u5VnOv8AU+7VxKccqt6UL5gjX070DWBojtsMoB9F6cNqGXjsu82NHyadDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:22:44.604598Z"},"content_sha256":"ddde8ec8296c72508dff65d8caed7ec36f226829f761ad9f8fd61e775ca97286","schema_version":"1.0","event_id":"sha256:ddde8ec8296c72508dff65d8caed7ec36f226829f761ad9f8fd61e775ca97286"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y7EZTROBCZG2W5PNCHZDFTB7B7/bundle.json","state_url":"https://pith.science/pith/Y7EZTROBCZG2W5PNCHZDFTB7B7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y7EZTROBCZG2W5PNCHZDFTB7B7/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":"2026-07-07T07:22:44Z","links":{"resolver":"https://pith.science/pith/Y7EZTROBCZG2W5PNCHZDFTB7B7","bundle":"https://pith.science/pith/Y7EZTROBCZG2W5PNCHZDFTB7B7/bundle.json","state":"https://pith.science/pith/Y7EZTROBCZG2W5PNCHZDFTB7B7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y7EZTROBCZG2W5PNCHZDFTB7B7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y7EZTROBCZG2W5PNCHZDFTB7B7","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":"d354b3d922fc26a0ebbe569c925ec2be8a4b9991857202705ce84dbe5c2715f8","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-03-05T16:35:25Z","title_canon_sha256":"156635f6bc1afa00667493496dcbc18826ab03eeb0154c5d324c9ff0a34daa31"},"schema_version":"1.0","source":{"id":"2403.03100","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.03100","created_at":"2026-07-05T08:11:02Z"},{"alias_kind":"arxiv_version","alias_value":"2403.03100v3","created_at":"2026-07-05T08:11:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03100","created_at":"2026-07-05T08:11:02Z"},{"alias_kind":"pith_short_12","alias_value":"Y7EZTROBCZG2","created_at":"2026-07-05T08:11:02Z"},{"alias_kind":"pith_short_16","alias_value":"Y7EZTROBCZG2W5PN","created_at":"2026-07-05T08:11:02Z"},{"alias_kind":"pith_short_8","alias_value":"Y7EZTROB","created_at":"2026-07-05T08:11:02Z"}],"graph_snapshots":[{"event_id":"sha256:ddde8ec8296c72508dff65d8caed7ec36f226829f761ad9f8fd61e775ca97286","target":"graph","created_at":"2026-07-05T08:11:02Z","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/2403.03100/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While recent large-scale text-to-speech (TTS) models have achieved significant progress, they still fall short in speech quality, similarity, and prosody. Considering speech intricately encompasses various attributes (e.g., content, prosody, timbre, and acoustic details) that pose significant challenges for generation, a natural idea is to factorize speech into individual subspaces representing different attributes and generate them individually. Motivated by it, we propose NaturalSpeech 3, a TTS system with novel factorized diffusion models to generate natural speech in a zero-shot way. Speci","authors_text":"Detai Xin, Dongchao Yang, Jiang Bian, Jinyu Li, Kai Shen, Kaitao Song, Lei He, Sheng Zhao, Shikun Zhang, Siliang Tang, Tao Qin, Wei Ye, Xiang-Yang Li, Xu Tan, Yanqing Liu, Yichong Leng, Yuancheng Wang, Zeqian Ju, Zhizheng Wu","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-03-05T16:35:25Z","title":"NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03100","kind":"arxiv","version":3},"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":"sha256:98106713fd315c6c04f69c01d1366a548d9a7439b0af826a713ba1a396586195","target":"record","created_at":"2026-07-05T08:11:02Z","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":"d354b3d922fc26a0ebbe569c925ec2be8a4b9991857202705ce84dbe5c2715f8","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-03-05T16:35:25Z","title_canon_sha256":"156635f6bc1afa00667493496dcbc18826ab03eeb0154c5d324c9ff0a34daa31"},"schema_version":"1.0","source":{"id":"2403.03100","kind":"arxiv","version":3}},"canonical_sha256":"c7c999c5c1164dab75ed11f232cc3f0ff66b09cf3a2d18159b76fb98d680f168","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7c999c5c1164dab75ed11f232cc3f0ff66b09cf3a2d18159b76fb98d680f168","first_computed_at":"2026-07-05T08:11:02.277137Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:11:02.277137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t3p+2hR1DxncLYZ7HKi5VdHGL+WL2XLm68EBY5GX4GTGXCnQz3s0yi5pjv4+HnBewsllJZCRuhKfzNZWQfP2BA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:11:02.277578Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.03100","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98106713fd315c6c04f69c01d1366a548d9a7439b0af826a713ba1a396586195","sha256:ddde8ec8296c72508dff65d8caed7ec36f226829f761ad9f8fd61e775ca97286"],"state_sha256":"68a6e4584a214745aed55342993f25b0c77a797e390b89508baebb024c4391e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8sQkdx2UxV0usUbdQGrCOn8rfCAwpL1XiRyEIg3QattRhI3v9qAn6uo67REnGAHRtMXEGkWQDTgyv7oX4+/cAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:22:44.608234Z","bundle_sha256":"d909ef3e27a6968e0b3591fce962f792fbc85d8c1d721ff249235e52dcecbfd5"}}