{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SD2UXZEWUSTH2SXDCOJ7JC2D4Y","short_pith_number":"pith:SD2UXZEW","canonical_record":{"source":{"id":"2502.07243","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-11T04:18:33Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"dd595bf6d81b31036c84af9b977beac4c61930b0d12a8a9cc70d2d3ad775da33","abstract_canon_sha256":"bcc49175262608cf6236f8ae65487d5a99cf3d1baa9169696ed04d87bf5da65c"},"schema_version":"1.0"},"canonical_sha256":"90f54be496a4a67d4ae31393f48b43e63347f2656eb7527cf98b9d48b54679d8","source":{"kind":"arxiv","id":"2502.07243","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07243","created_at":"2026-07-05T10:40:30Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07243v1","created_at":"2026-07-05T10:40:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07243","created_at":"2026-07-05T10:40:30Z"},{"alias_kind":"pith_short_12","alias_value":"SD2UXZEWUSTH","created_at":"2026-07-05T10:40:30Z"},{"alias_kind":"pith_short_16","alias_value":"SD2UXZEWUSTH2SXD","created_at":"2026-07-05T10:40:30Z"},{"alias_kind":"pith_short_8","alias_value":"SD2UXZEW","created_at":"2026-07-05T10:40:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SD2UXZEWUSTH2SXDCOJ7JC2D4Y","target":"record","payload":{"canonical_record":{"source":{"id":"2502.07243","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-11T04:18:33Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"dd595bf6d81b31036c84af9b977beac4c61930b0d12a8a9cc70d2d3ad775da33","abstract_canon_sha256":"bcc49175262608cf6236f8ae65487d5a99cf3d1baa9169696ed04d87bf5da65c"},"schema_version":"1.0"},"canonical_sha256":"90f54be496a4a67d4ae31393f48b43e63347f2656eb7527cf98b9d48b54679d8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:30.871900Z","signature_b64":"4zyPu7j3MIwzjLQ0KlKwGNeixT3HYSXywlqnJoaIcFgtNGkn+0HX3C5NRb50nzmQub5vPjFYTRIzldGMDy/eAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90f54be496a4a67d4ae31393f48b43e63347f2656eb7527cf98b9d48b54679d8","last_reissued_at":"2026-07-05T10:40:30.871450Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:30.871450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.07243","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":"2026-07-05T10:40:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j3m4mlSYQu5ML1EO209m94znGjTpSVaHH3J4XZwlu9+nfGufBlMZK4dOU3xLaSmbfAny+0438ia6+WLMBSf7BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:50:12.432809Z"},"content_sha256":"b7efa076e2a7bf3b4c7396b7c674c45cda5a56e1798d9c120709abd8c9a110b9","schema_version":"1.0","event_id":"sha256:b7efa076e2a7bf3b4c7396b7c674c45cda5a56e1798d9c120709abd8c9a110b9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SD2UXZEWUSTH2SXDCOJ7JC2D4Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vevo: Controllable Zero-Shot Voice Imitation with Self-Supervised Disentanglement","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dangna Li, Jeff Hwang, Julian Chan, Kainan Peng, Mingbo Ma, Vimal Manohar, Xiaohui Zhang, Xueyao Zhang, Yingru Liu, Yuan Huang, Yuhao Wang, Zhenyu Tang, Zhizheng Wu","submitted_at":"2025-02-11T04:18:33Z","abstract_excerpt":"The imitation of voice, targeted on specific speech attributes such as timbre and speaking style, is crucial in speech generation. However, existing methods rely heavily on annotated data, and struggle with effectively disentangling timbre and style, leading to challenges in achieving controllable generation, especially in zero-shot scenarios. To address these issues, we propose Vevo, a versatile zero-shot voice imitation framework with controllable timbre and style. Vevo operates in two core stages: (1) Content-Style Modeling: Given either text or speech's content tokens as input, we utilize "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07243","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/2502.07243/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":"2026-07-05T10:40:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G2Q1j0DzcG5QXhFEI1izpy49HtaQTZKHLfa9KnnYBmTRg9mQsesdGh1E1PKg4P0HOCaIWLUMv0QyotFWX7BhAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:50:12.433390Z"},"content_sha256":"90c735012079214e424a0df6c31f8b1e65a63bdc9bb33a36db87cb304b6998f5","schema_version":"1.0","event_id":"sha256:90c735012079214e424a0df6c31f8b1e65a63bdc9bb33a36db87cb304b6998f5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SD2UXZEWUSTH2SXDCOJ7JC2D4Y/bundle.json","state_url":"https://pith.science/pith/SD2UXZEWUSTH2SXDCOJ7JC2D4Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SD2UXZEWUSTH2SXDCOJ7JC2D4Y/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":"2026-08-06T15:50:12Z","links":{"resolver":"https://pith.science/pith/SD2UXZEWUSTH2SXDCOJ7JC2D4Y","bundle":"https://pith.science/pith/SD2UXZEWUSTH2SXDCOJ7JC2D4Y/bundle.json","state":"https://pith.science/pith/SD2UXZEWUSTH2SXDCOJ7JC2D4Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SD2UXZEWUSTH2SXDCOJ7JC2D4Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SD2UXZEWUSTH2SXDCOJ7JC2D4Y","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":"bcc49175262608cf6236f8ae65487d5a99cf3d1baa9169696ed04d87bf5da65c","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-11T04:18:33Z","title_canon_sha256":"dd595bf6d81b31036c84af9b977beac4c61930b0d12a8a9cc70d2d3ad775da33"},"schema_version":"1.0","source":{"id":"2502.07243","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07243","created_at":"2026-07-05T10:40:30Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07243v1","created_at":"2026-07-05T10:40:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07243","created_at":"2026-07-05T10:40:30Z"},{"alias_kind":"pith_short_12","alias_value":"SD2UXZEWUSTH","created_at":"2026-07-05T10:40:30Z"},{"alias_kind":"pith_short_16","alias_value":"SD2UXZEWUSTH2SXD","created_at":"2026-07-05T10:40:30Z"},{"alias_kind":"pith_short_8","alias_value":"SD2UXZEW","created_at":"2026-07-05T10:40:30Z"}],"graph_snapshots":[{"event_id":"sha256:90c735012079214e424a0df6c31f8b1e65a63bdc9bb33a36db87cb304b6998f5","target":"graph","created_at":"2026-07-05T10:40:30Z","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/2502.07243/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The imitation of voice, targeted on specific speech attributes such as timbre and speaking style, is crucial in speech generation. However, existing methods rely heavily on annotated data, and struggle with effectively disentangling timbre and style, leading to challenges in achieving controllable generation, especially in zero-shot scenarios. To address these issues, we propose Vevo, a versatile zero-shot voice imitation framework with controllable timbre and style. Vevo operates in two core stages: (1) Content-Style Modeling: Given either text or speech's content tokens as input, we utilize ","authors_text":"Dangna Li, Jeff Hwang, Julian Chan, Kainan Peng, Mingbo Ma, Vimal Manohar, Xiaohui Zhang, Xueyao Zhang, Yingru Liu, Yuan Huang, Yuhao Wang, Zhenyu Tang, Zhizheng Wu","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-11T04:18:33Z","title":"Vevo: Controllable Zero-Shot Voice Imitation with Self-Supervised Disentanglement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07243","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:b7efa076e2a7bf3b4c7396b7c674c45cda5a56e1798d9c120709abd8c9a110b9","target":"record","created_at":"2026-07-05T10:40:30Z","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":"bcc49175262608cf6236f8ae65487d5a99cf3d1baa9169696ed04d87bf5da65c","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-11T04:18:33Z","title_canon_sha256":"dd595bf6d81b31036c84af9b977beac4c61930b0d12a8a9cc70d2d3ad775da33"},"schema_version":"1.0","source":{"id":"2502.07243","kind":"arxiv","version":1}},"canonical_sha256":"90f54be496a4a67d4ae31393f48b43e63347f2656eb7527cf98b9d48b54679d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"90f54be496a4a67d4ae31393f48b43e63347f2656eb7527cf98b9d48b54679d8","first_computed_at":"2026-07-05T10:40:30.871450Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:40:30.871450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4zyPu7j3MIwzjLQ0KlKwGNeixT3HYSXywlqnJoaIcFgtNGkn+0HX3C5NRb50nzmQub5vPjFYTRIzldGMDy/eAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:40:30.871900Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.07243","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7efa076e2a7bf3b4c7396b7c674c45cda5a56e1798d9c120709abd8c9a110b9","sha256:90c735012079214e424a0df6c31f8b1e65a63bdc9bb33a36db87cb304b6998f5"],"state_sha256":"fb7673f8e370d38bf0fd5e22cdd162bb24b62288dbd40debfd75529bf4c3ff15"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wbmaPjEsh8seWWZz7ztZHqnHk5EpM2o76tuX3TgWmgtZZGMXmOiWVQoyxe/ejIgdUUXAV+GkYplrqb6GCsznBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T15:50:12.437598Z","bundle_sha256":"f94c38de2b88f98a3da99029252bf1c69bca374534be518732b0144b24ac0d9d"}}