{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2MVKW4CHTD65QGGOD4KRRLFOY2","short_pith_number":"pith:2MVKW4CH","canonical_record":{"source":{"id":"2506.02414","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-06-03T04:00:53Z","cross_cats_sorted":["cs.CL","cs.SD","eess.AS"],"title_canon_sha256":"14d4eb8719a5dc937915dba371847f61bc2c95ef4789685cb3ecf052f0c535af","abstract_canon_sha256":"2b6afb1c3e63999494729591b2c373508fdce8c1e489958ff5a42221e77046f5"},"schema_version":"1.0"},"canonical_sha256":"d32aab704798fdd818ce1f1518acaec6a064c9329cfbd234486564e1c4047733","source":{"kind":"arxiv","id":"2506.02414","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02414","created_at":"2026-07-05T11:14:38Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02414v1","created_at":"2026-07-05T11:14:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02414","created_at":"2026-07-05T11:14:38Z"},{"alias_kind":"pith_short_12","alias_value":"2MVKW4CHTD65","created_at":"2026-07-05T11:14:38Z"},{"alias_kind":"pith_short_16","alias_value":"2MVKW4CHTD65QGGO","created_at":"2026-07-05T11:14:38Z"},{"alias_kind":"pith_short_8","alias_value":"2MVKW4CH","created_at":"2026-07-05T11:14:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2MVKW4CHTD65QGGOD4KRRLFOY2","target":"record","payload":{"canonical_record":{"source":{"id":"2506.02414","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-06-03T04:00:53Z","cross_cats_sorted":["cs.CL","cs.SD","eess.AS"],"title_canon_sha256":"14d4eb8719a5dc937915dba371847f61bc2c95ef4789685cb3ecf052f0c535af","abstract_canon_sha256":"2b6afb1c3e63999494729591b2c373508fdce8c1e489958ff5a42221e77046f5"},"schema_version":"1.0"},"canonical_sha256":"d32aab704798fdd818ce1f1518acaec6a064c9329cfbd234486564e1c4047733","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:38.383044Z","signature_b64":"nWTCX6KSqwNg77Aqjl9weyouf8mQHHYVx5d8jbTtMGLa8ALP7vkYKLeAcRsJEK96Wv/nul6LciiZAl5H9uAgDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d32aab704798fdd818ce1f1518acaec6a064c9329cfbd234486564e1c4047733","last_reissued_at":"2026-07-05T11:14:38.382626Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:38.382626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.02414","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":"2026-07-05T11:14:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n6dIMSlLRO9VCE+1UVDqb0qWcIkG+8hdd9fcewWyPGDZqAmMFDHkQuTQl3SGGOqIs+sLVGCHHVjWc5ufnR0QDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:00:40.587141Z"},"content_sha256":"da1a8bca9ac510452dc6772bf51e49c4f04bdeee52b16fd0e03efd9a849d5545","schema_version":"1.0","event_id":"sha256:da1a8bca9ac510452dc6772bf51e49c4f04bdeee52b16fd0e03efd9a849d5545"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2MVKW4CHTD65QGGOD4KRRLFOY2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"StarVC: A Unified Auto-Regressive Framework for Joint Text and Speech Generation in Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Fengjin Li, Jian Luan, Jie Wang, Meng Meng, Yadong Niu, Yongqing Wang, Zhiyong Wu","submitted_at":"2025-06-03T04:00:53Z","abstract_excerpt":"Voice Conversion (VC) modifies speech to match a target speaker while preserving linguistic content. Traditional methods usually extract speaker information directly from speech while neglecting the explicit utilization of linguistic content. Since VC fundamentally involves disentangling speaker identity from linguistic content, leveraging structured semantic features could enhance conversion performance. However, previous attempts to incorporate semantic features into VC have shown limited effectiveness, motivating the integration of explicit text modeling. We propose StarVC, a unified autore"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02414","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/2506.02414/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":"2026-07-05T11:14:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8GH/lrwDpI2g+vBZQIdlsOYDA061ricBt+wH4BZcYeFQxNR7eTfbLQOmCXQBgXj4/a7+eI/ulXbVQ8N5SfEzCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:00:40.587691Z"},"content_sha256":"4ada84a1b65479354b6565865ff7df83a961d6a2abb1b17b2977dde81934a644","schema_version":"1.0","event_id":"sha256:4ada84a1b65479354b6565865ff7df83a961d6a2abb1b17b2977dde81934a644"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2MVKW4CHTD65QGGOD4KRRLFOY2/bundle.json","state_url":"https://pith.science/pith/2MVKW4CHTD65QGGOD4KRRLFOY2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2MVKW4CHTD65QGGOD4KRRLFOY2/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":"2026-08-09T14:00:40Z","links":{"resolver":"https://pith.science/pith/2MVKW4CHTD65QGGOD4KRRLFOY2","bundle":"https://pith.science/pith/2MVKW4CHTD65QGGOD4KRRLFOY2/bundle.json","state":"https://pith.science/pith/2MVKW4CHTD65QGGOD4KRRLFOY2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2MVKW4CHTD65QGGOD4KRRLFOY2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2MVKW4CHTD65QGGOD4KRRLFOY2","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":"2b6afb1c3e63999494729591b2c373508fdce8c1e489958ff5a42221e77046f5","cross_cats_sorted":["cs.CL","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-06-03T04:00:53Z","title_canon_sha256":"14d4eb8719a5dc937915dba371847f61bc2c95ef4789685cb3ecf052f0c535af"},"schema_version":"1.0","source":{"id":"2506.02414","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02414","created_at":"2026-07-05T11:14:38Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02414v1","created_at":"2026-07-05T11:14:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02414","created_at":"2026-07-05T11:14:38Z"},{"alias_kind":"pith_short_12","alias_value":"2MVKW4CHTD65","created_at":"2026-07-05T11:14:38Z"},{"alias_kind":"pith_short_16","alias_value":"2MVKW4CHTD65QGGO","created_at":"2026-07-05T11:14:38Z"},{"alias_kind":"pith_short_8","alias_value":"2MVKW4CH","created_at":"2026-07-05T11:14:38Z"}],"graph_snapshots":[{"event_id":"sha256:4ada84a1b65479354b6565865ff7df83a961d6a2abb1b17b2977dde81934a644","target":"graph","created_at":"2026-07-05T11:14:38Z","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/2506.02414/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Voice Conversion (VC) modifies speech to match a target speaker while preserving linguistic content. Traditional methods usually extract speaker information directly from speech while neglecting the explicit utilization of linguistic content. Since VC fundamentally involves disentangling speaker identity from linguistic content, leveraging structured semantic features could enhance conversion performance. However, previous attempts to incorporate semantic features into VC have shown limited effectiveness, motivating the integration of explicit text modeling. We propose StarVC, a unified autore","authors_text":"Fengjin Li, Jian Luan, Jie Wang, Meng Meng, Yadong Niu, Yongqing Wang, Zhiyong Wu","cross_cats":["cs.CL","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-06-03T04:00:53Z","title":"StarVC: A Unified Auto-Regressive Framework for Joint Text and Speech Generation in Voice Conversion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02414","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:da1a8bca9ac510452dc6772bf51e49c4f04bdeee52b16fd0e03efd9a849d5545","target":"record","created_at":"2026-07-05T11:14:38Z","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":"2b6afb1c3e63999494729591b2c373508fdce8c1e489958ff5a42221e77046f5","cross_cats_sorted":["cs.CL","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-06-03T04:00:53Z","title_canon_sha256":"14d4eb8719a5dc937915dba371847f61bc2c95ef4789685cb3ecf052f0c535af"},"schema_version":"1.0","source":{"id":"2506.02414","kind":"arxiv","version":1}},"canonical_sha256":"d32aab704798fdd818ce1f1518acaec6a064c9329cfbd234486564e1c4047733","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d32aab704798fdd818ce1f1518acaec6a064c9329cfbd234486564e1c4047733","first_computed_at":"2026-07-05T11:14:38.382626Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:38.382626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nWTCX6KSqwNg77Aqjl9weyouf8mQHHYVx5d8jbTtMGLa8ALP7vkYKLeAcRsJEK96Wv/nul6LciiZAl5H9uAgDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:38.383044Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02414","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da1a8bca9ac510452dc6772bf51e49c4f04bdeee52b16fd0e03efd9a849d5545","sha256:4ada84a1b65479354b6565865ff7df83a961d6a2abb1b17b2977dde81934a644"],"state_sha256":"56094740f7c37905e1586eac46d1cc0f40b4cfa647fdf56203d5d6e334d1914f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6OOsDhsqmmRDiR+07GvjWW7MelA6m99l51GZ6+82rYZOo6LXVgc/jl+qHOG7X+8smks9uEMEh5KHhuLqqfipDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T14:00:40.593171Z","bundle_sha256":"703b837b887fa26343b605cd3bbbc510c0bb5ec4583a3183ae4cb867c23ca4be"}}