{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2Q6L6V7LVTK236KRNERDPF3YHE","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":"65bd61972a0f8c37c8600326413d56e23ee0ea96b2c17e10f067143e9a00317c","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-11-15T04:43:44Z","title_canon_sha256":"e3087406d7cbbfe5a1d59480973fd5034710931ba64e46973725ed7b2fb0155c"},"schema_version":"1.0","source":{"id":"2411.09943","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.09943","created_at":"2026-07-05T09:35:56Z"},{"alias_kind":"arxiv_version","alias_value":"2411.09943v1","created_at":"2026-07-05T09:35:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09943","created_at":"2026-07-05T09:35:56Z"},{"alias_kind":"pith_short_12","alias_value":"2Q6L6V7LVTK2","created_at":"2026-07-05T09:35:56Z"},{"alias_kind":"pith_short_16","alias_value":"2Q6L6V7LVTK236KR","created_at":"2026-07-05T09:35:56Z"},{"alias_kind":"pith_short_8","alias_value":"2Q6L6V7L","created_at":"2026-07-05T09:35:56Z"}],"graph_snapshots":[{"event_id":"sha256:44f959264a938ed0131f914114913c37e7745cf0b94da924b439985f774331b4","target":"graph","created_at":"2026-07-05T09:35:56Z","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/2411.09943/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Zero-shot voice conversion aims to transform a source speech utterance to match the timbre of a reference speech from an unseen speaker. Traditional approaches struggle with timbre leakage, insufficient timbre representation, and mismatches between training and inference tasks. We propose Seed-VC, a novel framework that addresses these issues by introducing an external timbre shifter during training to perturb the source speech timbre, mitigating leakage and aligning training with inference. Additionally, we employ a diffusion transformer that leverages the entire reference speech context, cap","authors_text":"Songting Liu","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-11-15T04:43:44Z","title":"Zero-shot Voice Conversion with Diffusion Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09943","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:c41639bb4c4c5c89fd316f79c9131fdf02c1fb7c7aa32d56852f569fd2755ea3","target":"record","created_at":"2026-07-05T09:35:56Z","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":"65bd61972a0f8c37c8600326413d56e23ee0ea96b2c17e10f067143e9a00317c","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-11-15T04:43:44Z","title_canon_sha256":"e3087406d7cbbfe5a1d59480973fd5034710931ba64e46973725ed7b2fb0155c"},"schema_version":"1.0","source":{"id":"2411.09943","kind":"arxiv","version":1}},"canonical_sha256":"d43cbf57ebacd5adf951692237977839163066db9297a9f543d5fbe150846a51","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d43cbf57ebacd5adf951692237977839163066db9297a9f543d5fbe150846a51","first_computed_at":"2026-07-05T09:35:56.074411Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:35:56.074411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BPlbIsZUbpsunEDMIaGFHVS1dkLbiC2QzKIr01fpMEsMk87Giv4cEz04grgDaC3kGyNz+OXH/FJkO5NujBCcAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:35:56.074948Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.09943","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c41639bb4c4c5c89fd316f79c9131fdf02c1fb7c7aa32d56852f569fd2755ea3","sha256:44f959264a938ed0131f914114913c37e7745cf0b94da924b439985f774331b4"],"state_sha256":"5851f32e117c0b03526c53453f1d3e9314425ca516f4959d5d0bcb4ce4f63921"}