{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UXKKMTXMV4UHZIWECP4XK3GD7Q","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":"5c094efccbcc950e1f6fff65030d8b4068048dd0bd2a8c757dac257b6d96d232","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-23T17:41:40Z","title_canon_sha256":"546f89a2b5da8c7aa90dbbcec85ae246a8d184ae6288e02da00fe49e010dfb19"},"schema_version":"1.0","source":{"id":"2501.13870","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.13870","created_at":"2026-07-05T10:04:35Z"},{"alias_kind":"arxiv_version","alias_value":"2501.13870v1","created_at":"2026-07-05T10:04:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13870","created_at":"2026-07-05T10:04:35Z"},{"alias_kind":"pith_short_12","alias_value":"UXKKMTXMV4UH","created_at":"2026-07-05T10:04:35Z"},{"alias_kind":"pith_short_16","alias_value":"UXKKMTXMV4UHZIWE","created_at":"2026-07-05T10:04:35Z"},{"alias_kind":"pith_short_8","alias_value":"UXKKMTXM","created_at":"2026-07-05T10:04:35Z"}],"graph_snapshots":[{"event_id":"sha256:d237b968ab670009fff425f4c93c5422137bcb1c73e24f877c7eeb64aaf03a96","target":"graph","created_at":"2026-07-05T10:04:35Z","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/2501.13870/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a unified framework for Singing Voice Synthesis (SVS) and Conversion (SVC), addressing the limitations of existing approaches in cross-domain SVS/SVC, poor output musicality, and scarcity of singing data. Our framework enables control over multiple aspects, including language content based on lyrics, performance attributes based on a musical score, singing style and vocal techniques based on a selector, and voice identity based on a speech sample. The proposed zero-shot learning paradigm consists of one SVS model and two SVC models, utilizing pre-trained content embeddings and a dif","authors_text":"Roger B. Dannenberg, Shuqi Dai, Yunyun Wang, Zeyu Jin","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-23T17:41:40Z","title":"Everyone-Can-Sing: Zero-Shot Singing Voice Synthesis and Conversion with Speech Reference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13870","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:f6c600d36cff6be0ceebb96a76af99c4562a8c72e2f11ac1e109f444391a72b9","target":"record","created_at":"2026-07-05T10:04:35Z","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":"5c094efccbcc950e1f6fff65030d8b4068048dd0bd2a8c757dac257b6d96d232","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-23T17:41:40Z","title_canon_sha256":"546f89a2b5da8c7aa90dbbcec85ae246a8d184ae6288e02da00fe49e010dfb19"},"schema_version":"1.0","source":{"id":"2501.13870","kind":"arxiv","version":1}},"canonical_sha256":"a5d4a64eecaf287ca2c413f9756cc3fc3517e39883dcb5f950fc0ff9e91f48d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a5d4a64eecaf287ca2c413f9756cc3fc3517e39883dcb5f950fc0ff9e91f48d5","first_computed_at":"2026-07-05T10:04:35.440786Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:04:35.440786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pFwS6rubsJTfCm3svEqEwGjoqN1sInrdZAJOyveBJylbcyiKGKEgptD5NcL3tzNZ0KDxu3UyYXdfbBlpE1TCDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:04:35.441122Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.13870","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6c600d36cff6be0ceebb96a76af99c4562a8c72e2f11ac1e109f444391a72b9","sha256:d237b968ab670009fff425f4c93c5422137bcb1c73e24f877c7eeb64aaf03a96"],"state_sha256":"68139dccdec690cc48ae395e6b2cfe7ed2060cdb7a1c801d9c8d7d5196d934bd"}