{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QVUVDA5HZ5SS572W2JPFV5NWRG","short_pith_number":"pith:QVUVDA5H","canonical_record":{"source":{"id":"2506.01014","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-01T13:53:28Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"896a864ad8b4961d366f7aa83f1881f668c26410bd0d66dd7bb54c3fd992a1bb","abstract_canon_sha256":"3af5b7a58530442e742c6b259daf1941b17e3441ce8c8cc418ddeddfbec46fa4"},"schema_version":"1.0"},"canonical_sha256":"85695183a7cf652eff56d25e5af5b689bfe9b170c0e35336a08dd8712a865efb","source":{"kind":"arxiv","id":"2506.01014","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01014","created_at":"2026-07-05T11:13:44Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01014v1","created_at":"2026-07-05T11:13:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01014","created_at":"2026-07-05T11:13:44Z"},{"alias_kind":"pith_short_12","alias_value":"QVUVDA5HZ5SS","created_at":"2026-07-05T11:13:44Z"},{"alias_kind":"pith_short_16","alias_value":"QVUVDA5HZ5SS572W","created_at":"2026-07-05T11:13:44Z"},{"alias_kind":"pith_short_8","alias_value":"QVUVDA5H","created_at":"2026-07-05T11:13:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QVUVDA5HZ5SS572W2JPFV5NWRG","target":"record","payload":{"canonical_record":{"source":{"id":"2506.01014","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-01T13:53:28Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"896a864ad8b4961d366f7aa83f1881f668c26410bd0d66dd7bb54c3fd992a1bb","abstract_canon_sha256":"3af5b7a58530442e742c6b259daf1941b17e3441ce8c8cc418ddeddfbec46fa4"},"schema_version":"1.0"},"canonical_sha256":"85695183a7cf652eff56d25e5af5b689bfe9b170c0e35336a08dd8712a865efb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:44.537732Z","signature_b64":"0z5VvaI24KICub8FF+SaVIYKPGKq2rE5rf6YMxa7oyrJJMNcdpiLO4AnSVMf/E7IvKG1LbyuJskY2S9lkFjRAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85695183a7cf652eff56d25e5af5b689bfe9b170c0e35336a08dd8712a865efb","last_reissued_at":"2026-07-05T11:13:44.537235Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:44.537235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.01014","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":"2026-07-05T11:13:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4F8u47nberS7oTwYO6LmTz9DgtHVMCjhXVmgp2mAxPebtQSoqjdlcbEijTM9990WBzimqQF+ttszye5L8y9UDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:10:09.725074Z"},"content_sha256":"94989d7261ba85f276ebc20bd10557e278a23219e0b71e47050f62e345d45771","schema_version":"1.0","event_id":"sha256:94989d7261ba85f276ebc20bd10557e278a23219e0b71e47050f62e345d45771"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QVUVDA5HZ5SS572W2JPFV5NWRG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rhythm Controllable and Efficient Zero-Shot Voice Conversion via Shortcut Flow Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chen Feiyang, Jialong Zuo, Minghui Fang, Mingze Li, Shengpeng Ji, Xiaoda Yang, Xinyu Duan, Xize Cheng, Zhou Zhao, Ziyue Jiang","submitted_at":"2025-06-01T13:53:28Z","abstract_excerpt":"Zero-Shot Voice Conversion (VC) aims to transform the source speaker's timbre into an arbitrary unseen one while retaining speech content. Most prior work focuses on preserving the source's prosody, while fine-grained timbre information may leak through prosody, and transferring target prosody to synthesized speech is rarely studied. In light of this, we propose R-VC, a rhythm-controllable and efficient zero-shot voice conversion model. R-VC employs data perturbation techniques and discretize source speech into Hubert content tokens, eliminating much content-irrelevant information. By leveragi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01014","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/2506.01014/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":"2026-07-05T11:13:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yFf8DBFBLRltpW6k1t4aelaIsqYpEwqaoldnoOS4TbZcAu1CVidgBwx/LmRujsqj5uA211xkL6YSa7culQ+uDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:10:09.725581Z"},"content_sha256":"8f70391d9788169d55bc5760421575de37fc7006b7b0782bcd3d93e9eeaa3f9a","schema_version":"1.0","event_id":"sha256:8f70391d9788169d55bc5760421575de37fc7006b7b0782bcd3d93e9eeaa3f9a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QVUVDA5HZ5SS572W2JPFV5NWRG/bundle.json","state_url":"https://pith.science/pith/QVUVDA5HZ5SS572W2JPFV5NWRG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QVUVDA5HZ5SS572W2JPFV5NWRG/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":"2026-08-08T20:10:09Z","links":{"resolver":"https://pith.science/pith/QVUVDA5HZ5SS572W2JPFV5NWRG","bundle":"https://pith.science/pith/QVUVDA5HZ5SS572W2JPFV5NWRG/bundle.json","state":"https://pith.science/pith/QVUVDA5HZ5SS572W2JPFV5NWRG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QVUVDA5HZ5SS572W2JPFV5NWRG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QVUVDA5HZ5SS572W2JPFV5NWRG","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":"3af5b7a58530442e742c6b259daf1941b17e3441ce8c8cc418ddeddfbec46fa4","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-01T13:53:28Z","title_canon_sha256":"896a864ad8b4961d366f7aa83f1881f668c26410bd0d66dd7bb54c3fd992a1bb"},"schema_version":"1.0","source":{"id":"2506.01014","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01014","created_at":"2026-07-05T11:13:44Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01014v1","created_at":"2026-07-05T11:13:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01014","created_at":"2026-07-05T11:13:44Z"},{"alias_kind":"pith_short_12","alias_value":"QVUVDA5HZ5SS","created_at":"2026-07-05T11:13:44Z"},{"alias_kind":"pith_short_16","alias_value":"QVUVDA5HZ5SS572W","created_at":"2026-07-05T11:13:44Z"},{"alias_kind":"pith_short_8","alias_value":"QVUVDA5H","created_at":"2026-07-05T11:13:44Z"}],"graph_snapshots":[{"event_id":"sha256:8f70391d9788169d55bc5760421575de37fc7006b7b0782bcd3d93e9eeaa3f9a","target":"graph","created_at":"2026-07-05T11:13:44Z","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/2506.01014/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Zero-Shot Voice Conversion (VC) aims to transform the source speaker's timbre into an arbitrary unseen one while retaining speech content. Most prior work focuses on preserving the source's prosody, while fine-grained timbre information may leak through prosody, and transferring target prosody to synthesized speech is rarely studied. In light of this, we propose R-VC, a rhythm-controllable and efficient zero-shot voice conversion model. R-VC employs data perturbation techniques and discretize source speech into Hubert content tokens, eliminating much content-irrelevant information. By leveragi","authors_text":"Chen Feiyang, Jialong Zuo, Minghui Fang, Mingze Li, Shengpeng Ji, Xiaoda Yang, Xinyu Duan, Xize Cheng, Zhou Zhao, Ziyue Jiang","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-01T13:53:28Z","title":"Rhythm Controllable and Efficient Zero-Shot Voice Conversion via Shortcut Flow Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01014","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":"sha256:94989d7261ba85f276ebc20bd10557e278a23219e0b71e47050f62e345d45771","target":"record","created_at":"2026-07-05T11:13:44Z","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":"3af5b7a58530442e742c6b259daf1941b17e3441ce8c8cc418ddeddfbec46fa4","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-01T13:53:28Z","title_canon_sha256":"896a864ad8b4961d366f7aa83f1881f668c26410bd0d66dd7bb54c3fd992a1bb"},"schema_version":"1.0","source":{"id":"2506.01014","kind":"arxiv","version":1}},"canonical_sha256":"85695183a7cf652eff56d25e5af5b689bfe9b170c0e35336a08dd8712a865efb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85695183a7cf652eff56d25e5af5b689bfe9b170c0e35336a08dd8712a865efb","first_computed_at":"2026-07-05T11:13:44.537235Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:44.537235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0z5VvaI24KICub8FF+SaVIYKPGKq2rE5rf6YMxa7oyrJJMNcdpiLO4AnSVMf/E7IvKG1LbyuJskY2S9lkFjRAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:44.537732Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.01014","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:94989d7261ba85f276ebc20bd10557e278a23219e0b71e47050f62e345d45771","sha256:8f70391d9788169d55bc5760421575de37fc7006b7b0782bcd3d93e9eeaa3f9a"],"state_sha256":"ad73d05c583574393444d4cec41c3c2b8d59d5bb551b5e53a0c1ae1d3e352c99"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KK5hzt+uV+txFg2RBfRZSQgFX14nRIOgV4ByuYRKyQFxCWo8okviBkpKEIaEshLgIM6JowSjN/qKZuT/wDQPCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:10:09.729835Z","bundle_sha256":"c6cd76220bc729c6bb43d629f57f5caa7be18194a5d02b3ae63654d11a310494"}}