{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EW5W5VPM4G3GZW73KJPK5U2FAQ","short_pith_number":"pith:EW5W5VPM","canonical_record":{"source":{"id":"2403.00529","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-03-01T13:39:56Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"2f2d8793b2c749bee0379a07ab62d9b8574e5eb43fec3d22678e6fe8aa4553cd","abstract_canon_sha256":"0b448b7bd8ee678e2122418aa5a474316d0bd427ebd7bfb7bbcbd8bacdcf6c46"},"schema_version":"1.0"},"canonical_sha256":"25bb6ed5ece1b66cdbfb525eaed345041fbfe7038626e6758537b329bba9166b","source":{"kind":"arxiv","id":"2403.00529","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.00529","created_at":"2026-07-05T07:51:05Z"},{"alias_kind":"arxiv_version","alias_value":"2403.00529v1","created_at":"2026-07-05T07:51:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00529","created_at":"2026-07-05T07:51:05Z"},{"alias_kind":"pith_short_12","alias_value":"EW5W5VPM4G3G","created_at":"2026-07-05T07:51:05Z"},{"alias_kind":"pith_short_16","alias_value":"EW5W5VPM4G3GZW73","created_at":"2026-07-05T07:51:05Z"},{"alias_kind":"pith_short_8","alias_value":"EW5W5VPM","created_at":"2026-07-05T07:51:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EW5W5VPM4G3GZW73KJPK5U2FAQ","target":"record","payload":{"canonical_record":{"source":{"id":"2403.00529","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-03-01T13:39:56Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"2f2d8793b2c749bee0379a07ab62d9b8574e5eb43fec3d22678e6fe8aa4553cd","abstract_canon_sha256":"0b448b7bd8ee678e2122418aa5a474316d0bd427ebd7bfb7bbcbd8bacdcf6c46"},"schema_version":"1.0"},"canonical_sha256":"25bb6ed5ece1b66cdbfb525eaed345041fbfe7038626e6758537b329bba9166b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:05.436075Z","signature_b64":"2TF3DDo/UIbPGiXChCwSbkKIlLUOJ4Z9WfCMGsfptVKSAlGyhEEjD3spY/VvzzY4GbtpOagAImxTalAVpgWtCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25bb6ed5ece1b66cdbfb525eaed345041fbfe7038626e6758537b329bba9166b","last_reissued_at":"2026-07-05T07:51:05.435629Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:05.435629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.00529","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":"2026-07-05T07:51:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rXLQGpTJ3D5i9e5AC2OfMF+Zvb4wf5NunqpNSOuyXHx1xMcINcgrVsXca8OMIoTD7l8hb+Tac9utSSUhcQbBBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:04:17.074959Z"},"content_sha256":"a26e456eaaf717b2863868b1729f17d0eb511db174d92900ad87a97c7afc08cf","schema_version":"1.0","event_id":"sha256:a26e456eaaf717b2863868b1729f17d0eb511db174d92900ad87a97c7afc08cf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EW5W5VPM4G3GZW73KJPK5U2FAQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VoxGenesis: Unsupervised Discovery of Latent Speaker Manifold for Speech Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chenhang He, Jiachen Lian, Kong Aik Lee, Man-Wai Mak, Weiwei Lin","submitted_at":"2024-03-01T13:39:56Z","abstract_excerpt":"Achieving nuanced and accurate emulation of human voice has been a longstanding goal in artificial intelligence. Although significant progress has been made in recent years, the mainstream of speech synthesis models still relies on supervised speaker modeling and explicit reference utterances. However, there are many aspects of human voice, such as emotion, intonation, and speaking style, for which it is hard to obtain accurate labels. In this paper, we propose VoxGenesis, a novel unsupervised speech synthesis framework that can discover a latent speaker manifold and meaningful voice editing d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00529","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/2403.00529/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":"2026-07-05T07:51:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JgTnU61B9i4tN2nqxPpQin5t8fTEv9nt6jzPTRNEJmnSsFCXbo2pTEYg58kJnKfqQ/TE+OitR/s6iTy9QFXTBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:04:17.075358Z"},"content_sha256":"e85959785c02b28977ff39c59a90e97e8122e2cddc2db4e7b57d6c654e5c8a20","schema_version":"1.0","event_id":"sha256:e85959785c02b28977ff39c59a90e97e8122e2cddc2db4e7b57d6c654e5c8a20"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EW5W5VPM4G3GZW73KJPK5U2FAQ/bundle.json","state_url":"https://pith.science/pith/EW5W5VPM4G3GZW73KJPK5U2FAQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EW5W5VPM4G3GZW73KJPK5U2FAQ/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":"2026-07-06T15:04:17Z","links":{"resolver":"https://pith.science/pith/EW5W5VPM4G3GZW73KJPK5U2FAQ","bundle":"https://pith.science/pith/EW5W5VPM4G3GZW73KJPK5U2FAQ/bundle.json","state":"https://pith.science/pith/EW5W5VPM4G3GZW73KJPK5U2FAQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EW5W5VPM4G3GZW73KJPK5U2FAQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EW5W5VPM4G3GZW73KJPK5U2FAQ","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":"0b448b7bd8ee678e2122418aa5a474316d0bd427ebd7bfb7bbcbd8bacdcf6c46","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-03-01T13:39:56Z","title_canon_sha256":"2f2d8793b2c749bee0379a07ab62d9b8574e5eb43fec3d22678e6fe8aa4553cd"},"schema_version":"1.0","source":{"id":"2403.00529","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.00529","created_at":"2026-07-05T07:51:05Z"},{"alias_kind":"arxiv_version","alias_value":"2403.00529v1","created_at":"2026-07-05T07:51:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00529","created_at":"2026-07-05T07:51:05Z"},{"alias_kind":"pith_short_12","alias_value":"EW5W5VPM4G3G","created_at":"2026-07-05T07:51:05Z"},{"alias_kind":"pith_short_16","alias_value":"EW5W5VPM4G3GZW73","created_at":"2026-07-05T07:51:05Z"},{"alias_kind":"pith_short_8","alias_value":"EW5W5VPM","created_at":"2026-07-05T07:51:05Z"}],"graph_snapshots":[{"event_id":"sha256:e85959785c02b28977ff39c59a90e97e8122e2cddc2db4e7b57d6c654e5c8a20","target":"graph","created_at":"2026-07-05T07:51:05Z","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/2403.00529/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Achieving nuanced and accurate emulation of human voice has been a longstanding goal in artificial intelligence. Although significant progress has been made in recent years, the mainstream of speech synthesis models still relies on supervised speaker modeling and explicit reference utterances. However, there are many aspects of human voice, such as emotion, intonation, and speaking style, for which it is hard to obtain accurate labels. In this paper, we propose VoxGenesis, a novel unsupervised speech synthesis framework that can discover a latent speaker manifold and meaningful voice editing d","authors_text":"Chenhang He, Jiachen Lian, Kong Aik Lee, Man-Wai Mak, Weiwei Lin","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-03-01T13:39:56Z","title":"VoxGenesis: Unsupervised Discovery of Latent Speaker Manifold for Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00529","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:a26e456eaaf717b2863868b1729f17d0eb511db174d92900ad87a97c7afc08cf","target":"record","created_at":"2026-07-05T07:51:05Z","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":"0b448b7bd8ee678e2122418aa5a474316d0bd427ebd7bfb7bbcbd8bacdcf6c46","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-03-01T13:39:56Z","title_canon_sha256":"2f2d8793b2c749bee0379a07ab62d9b8574e5eb43fec3d22678e6fe8aa4553cd"},"schema_version":"1.0","source":{"id":"2403.00529","kind":"arxiv","version":1}},"canonical_sha256":"25bb6ed5ece1b66cdbfb525eaed345041fbfe7038626e6758537b329bba9166b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25bb6ed5ece1b66cdbfb525eaed345041fbfe7038626e6758537b329bba9166b","first_computed_at":"2026-07-05T07:51:05.435629Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:51:05.435629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2TF3DDo/UIbPGiXChCwSbkKIlLUOJ4Z9WfCMGsfptVKSAlGyhEEjD3spY/VvzzY4GbtpOagAImxTalAVpgWtCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:51:05.436075Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.00529","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a26e456eaaf717b2863868b1729f17d0eb511db174d92900ad87a97c7afc08cf","sha256:e85959785c02b28977ff39c59a90e97e8122e2cddc2db4e7b57d6c654e5c8a20"],"state_sha256":"3d596c6c8f6fe470f7d8f2d182a7abf725de8e14044815c42955877cf7332142"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wvlvZHE2WmfMX2u8QBNJfxbs1bdQYzF5y2LI4idf+hPUYgaZHYYnMLS/YsnPJDC47PC9R5C2p2BZfahomzxCAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T15:04:17.077422Z","bundle_sha256":"e84ea89c25c0ee5ed3cba6985b78948946c79bf7981e673a3217950a75d292a0"}}