{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RUSDF3FZYLFKVEOZTHLVS3B65B","short_pith_number":"pith:RUSDF3FZ","canonical_record":{"source":{"id":"2502.04519","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-02-06T21:40:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fdd6e24ce31847c2844104f0ee0504e4a05a13b11c5e2918cc20ea157337762a","abstract_canon_sha256":"3c1cb1c011894d12c7795a9b58fd00c99bdd1e0ae70603996bef53100949e262"},"schema_version":"1.0"},"canonical_sha256":"8d2432ecb9c2caaa91d999d7596c3ee849f6eeef6231a70ae04ca47ed95d5ece","source":{"kind":"arxiv","id":"2502.04519","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04519","created_at":"2026-07-05T11:56:43Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04519v2","created_at":"2026-07-05T11:56:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04519","created_at":"2026-07-05T11:56:43Z"},{"alias_kind":"pith_short_12","alias_value":"RUSDF3FZYLFK","created_at":"2026-07-05T11:56:43Z"},{"alias_kind":"pith_short_16","alias_value":"RUSDF3FZYLFKVEOZ","created_at":"2026-07-05T11:56:43Z"},{"alias_kind":"pith_short_8","alias_value":"RUSDF3FZ","created_at":"2026-07-05T11:56:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RUSDF3FZYLFKVEOZTHLVS3B65B","target":"record","payload":{"canonical_record":{"source":{"id":"2502.04519","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-02-06T21:40:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fdd6e24ce31847c2844104f0ee0504e4a05a13b11c5e2918cc20ea157337762a","abstract_canon_sha256":"3c1cb1c011894d12c7795a9b58fd00c99bdd1e0ae70603996bef53100949e262"},"schema_version":"1.0"},"canonical_sha256":"8d2432ecb9c2caaa91d999d7596c3ee849f6eeef6231a70ae04ca47ed95d5ece","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:43.467732Z","signature_b64":"L1JMcOdXPgKIJMzI1Y2whtADo2NQO/2UVQ2s1q7S0tVR1SIzXamjEXRRKSamzOo+S0e5KhXyLlw1Ur78eHy6Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d2432ecb9c2caaa91d999d7596c3ee849f6eeef6231a70ae04ca47ed95d5ece","last_reissued_at":"2026-07-05T11:56:43.467177Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:43.467177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.04519","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:56:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RQ8Wj6ap5kbmfbKbLSkj05PDw2b3fuO/NfeQMhfHBabWB2VWBlfPEs2SA/0ZX3Bhj5lPzFoufqC7jie5dkT3CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T09:47:49.394962Z"},"content_sha256":"fdff98d1298947ca92f1a79e0b12f43ba58f7d65a41419d49a811ddd77f32c8d","schema_version":"1.0","event_id":"sha256:fdff98d1298947ca92f1a79e0b12f43ba58f7d65a41419d49a811ddd77f32c8d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RUSDF3FZYLFKVEOZTHLVS3B65B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GenVC: Self-Supervised Zero-Shot Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.AS","authors_text":"Ashi Garg, Henry Li Xinyuan, Kevin Duh, Leibny Paola Garc\\'ia-Perera, Matthew Wiesner, Nicholas Andrews, Sanjeev Khudanpur, Zexin Cai","submitted_at":"2025-02-06T21:40:09Z","abstract_excerpt":"Most current zero-shot voice conversion methods rely on externally supervised components, particularly speaker encoders, for training. To explore alternatives that eliminate this dependency, this paper introduces GenVC, a novel framework that disentangles speaker identity and linguistic content from speech signals in a self-supervised manner. GenVC leverages speech tokenizers and an autoregressive, Transformer-based language model as its backbone for speech generation. This design supports large-scale training while enhancing both source speaker privacy protection and target speaker cloning fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04519","kind":"arxiv","version":2},"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/2502.04519/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":"2026-07-05T11:56:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HiasUKAnntHZATbLUgaDanFs+N6MohqlEGcgFfDwdt4L669zgTvQ2uXqZPHKS3UPhU0PuNj58Pji+9vld+08Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T09:47:49.395371Z"},"content_sha256":"675c94fafb822fc161426c57c4ef2b89473d3bcbb2a8c823005f3c237eb14024","schema_version":"1.0","event_id":"sha256:675c94fafb822fc161426c57c4ef2b89473d3bcbb2a8c823005f3c237eb14024"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RUSDF3FZYLFKVEOZTHLVS3B65B/bundle.json","state_url":"https://pith.science/pith/RUSDF3FZYLFKVEOZTHLVS3B65B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RUSDF3FZYLFKVEOZTHLVS3B65B/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":"2026-07-10T09:47:49Z","links":{"resolver":"https://pith.science/pith/RUSDF3FZYLFKVEOZTHLVS3B65B","bundle":"https://pith.science/pith/RUSDF3FZYLFKVEOZTHLVS3B65B/bundle.json","state":"https://pith.science/pith/RUSDF3FZYLFKVEOZTHLVS3B65B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RUSDF3FZYLFKVEOZTHLVS3B65B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RUSDF3FZYLFKVEOZTHLVS3B65B","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":"3c1cb1c011894d12c7795a9b58fd00c99bdd1e0ae70603996bef53100949e262","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-02-06T21:40:09Z","title_canon_sha256":"fdd6e24ce31847c2844104f0ee0504e4a05a13b11c5e2918cc20ea157337762a"},"schema_version":"1.0","source":{"id":"2502.04519","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04519","created_at":"2026-07-05T11:56:43Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04519v2","created_at":"2026-07-05T11:56:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04519","created_at":"2026-07-05T11:56:43Z"},{"alias_kind":"pith_short_12","alias_value":"RUSDF3FZYLFK","created_at":"2026-07-05T11:56:43Z"},{"alias_kind":"pith_short_16","alias_value":"RUSDF3FZYLFKVEOZ","created_at":"2026-07-05T11:56:43Z"},{"alias_kind":"pith_short_8","alias_value":"RUSDF3FZ","created_at":"2026-07-05T11:56:43Z"}],"graph_snapshots":[{"event_id":"sha256:675c94fafb822fc161426c57c4ef2b89473d3bcbb2a8c823005f3c237eb14024","target":"graph","created_at":"2026-07-05T11:56:43Z","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/2502.04519/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most current zero-shot voice conversion methods rely on externally supervised components, particularly speaker encoders, for training. To explore alternatives that eliminate this dependency, this paper introduces GenVC, a novel framework that disentangles speaker identity and linguistic content from speech signals in a self-supervised manner. GenVC leverages speech tokenizers and an autoregressive, Transformer-based language model as its backbone for speech generation. This design supports large-scale training while enhancing both source speaker privacy protection and target speaker cloning fi","authors_text":"Ashi Garg, Henry Li Xinyuan, Kevin Duh, Leibny Paola Garc\\'ia-Perera, Matthew Wiesner, Nicholas Andrews, Sanjeev Khudanpur, Zexin Cai","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-02-06T21:40:09Z","title":"GenVC: Self-Supervised Zero-Shot Voice Conversion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04519","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:fdff98d1298947ca92f1a79e0b12f43ba58f7d65a41419d49a811ddd77f32c8d","target":"record","created_at":"2026-07-05T11:56:43Z","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":"3c1cb1c011894d12c7795a9b58fd00c99bdd1e0ae70603996bef53100949e262","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-02-06T21:40:09Z","title_canon_sha256":"fdd6e24ce31847c2844104f0ee0504e4a05a13b11c5e2918cc20ea157337762a"},"schema_version":"1.0","source":{"id":"2502.04519","kind":"arxiv","version":2}},"canonical_sha256":"8d2432ecb9c2caaa91d999d7596c3ee849f6eeef6231a70ae04ca47ed95d5ece","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d2432ecb9c2caaa91d999d7596c3ee849f6eeef6231a70ae04ca47ed95d5ece","first_computed_at":"2026-07-05T11:56:43.467177Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:56:43.467177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L1JMcOdXPgKIJMzI1Y2whtADo2NQO/2UVQ2s1q7S0tVR1SIzXamjEXRRKSamzOo+S0e5KhXyLlw1Ur78eHy6Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:56:43.467732Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.04519","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fdff98d1298947ca92f1a79e0b12f43ba58f7d65a41419d49a811ddd77f32c8d","sha256:675c94fafb822fc161426c57c4ef2b89473d3bcbb2a8c823005f3c237eb14024"],"state_sha256":"27747a457289e3ae1483fbe8c6978dc040d124a59851ec925606ecab658e9e62"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FCpkFwHD5uE5jS1vdO37Rl7kXl1rUM5VyA5iUKtnqoPwO7rgQwPR2C//CdrxJ/JxyhTTPkeosFt02Qcqx24FCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T09:47:49.397390Z","bundle_sha256":"8a5d8771b1168daf4077ab7892fb32ef308676ab6fc2781c6f0e57650050cff7"}}