{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AJ34KW2E27CF3XCUFZIFTE27VA","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":"01e46b2105038a98cafde86c5d562fb49395fdbae3c9e756969c316d98348137","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-03-18T13:39:05Z","title_canon_sha256":"19e5b8840b8414629cf787abafd6746e648e70c2142ba47391db69864b648508"},"schema_version":"1.0","source":{"id":"2403.11780","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.11780","created_at":"2026-07-05T09:57:19Z"},{"alias_kind":"arxiv_version","alias_value":"2403.11780v3","created_at":"2026-07-05T09:57:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11780","created_at":"2026-07-05T09:57:19Z"},{"alias_kind":"pith_short_12","alias_value":"AJ34KW2E27CF","created_at":"2026-07-05T09:57:19Z"},{"alias_kind":"pith_short_16","alias_value":"AJ34KW2E27CF3XCU","created_at":"2026-07-05T09:57:19Z"},{"alias_kind":"pith_short_8","alias_value":"AJ34KW2E","created_at":"2026-07-05T09:57:19Z"}],"graph_snapshots":[{"event_id":"sha256:72515130a1ab85dfe343c673bb47c38e8e560bd3c4e43d54ad53a8296631984f","target":"graph","created_at":"2026-07-05T09:57:19Z","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/2403.11780/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent singing-voice-synthesis (SVS) methods have achieved remarkable audio quality and naturalness, yet they lack the capability to control the style attributes of the synthesized singing explicitly. We propose Prompt-Singer, the first SVS method that enables attribute controlling on singer gender, vocal range and volume with natural language. We adopt a model architecture based on a decoder-only transformer with a multi-scale hierarchy, and design a range-melody decoupled pitch representation that enables text-conditioned vocal range control while keeping melodic accuracy. Furthermore, we ex","authors_text":"Fuming You, Rongjie Huang, Ruiqi Li, Ruofan Hu, Tao Jin, Wenrui Liu, Yongqi Wang, Zhiqing Hong, Zhou Zhao","cross_cats":["cs.AI","cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-03-18T13:39:05Z","title":"Prompt-Singer: Controllable Singing-Voice-Synthesis with Natural Language Prompt"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11780","kind":"arxiv","version":3},"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:e00a995bb99448fdcc9fd982ca44ebd0553262ce84a42e1835c5d15618f68377","target":"record","created_at":"2026-07-05T09:57:19Z","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":"01e46b2105038a98cafde86c5d562fb49395fdbae3c9e756969c316d98348137","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-03-18T13:39:05Z","title_canon_sha256":"19e5b8840b8414629cf787abafd6746e648e70c2142ba47391db69864b648508"},"schema_version":"1.0","source":{"id":"2403.11780","kind":"arxiv","version":3}},"canonical_sha256":"0277c55b44d7c45ddc542e5059935fa81817d0d560db10f3f2696d489f45fa96","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0277c55b44d7c45ddc542e5059935fa81817d0d560db10f3f2696d489f45fa96","first_computed_at":"2026-07-05T09:57:19.701380Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:57:19.701380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2tCNqHXoCo2SpgVgCB+xmDzCMxOB6iyKwpFkgw31Q0ox+v/XcrxBozeoIXvLyLO5zMo9z7hSM9kT7NSI9E+kCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:57:19.701902Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.11780","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e00a995bb99448fdcc9fd982ca44ebd0553262ce84a42e1835c5d15618f68377","sha256:72515130a1ab85dfe343c673bb47c38e8e560bd3c4e43d54ad53a8296631984f"],"state_sha256":"ec4f4d15e04fca637b67e4a0b7bff15967cb16c5bf2f25a746bd9d519cd10a8c"}