{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:N7SZM6RPHCSZ46Q7B24NQVKHLB","short_pith_number":"pith:N7SZM6RP","canonical_record":{"source":{"id":"2404.09313","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-04-14T18:00:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7a3aa3f354f3c39b75a611f90a99f67cd6bb09dcfce6f09dcb4a0a06de4f8a17","abstract_canon_sha256":"c2380d2b2a8625a0761324ac398a28d59141d0e3489d6c3c6d16beff403e9995"},"schema_version":"1.0"},"canonical_sha256":"6fe5967a2f38a59e7a1f0eb8d855475867866b263289d7d620b3b62e22090b97","source":{"kind":"arxiv","id":"2404.09313","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.09313","created_at":"2026-07-05T08:20:54Z"},{"alias_kind":"arxiv_version","alias_value":"2404.09313v3","created_at":"2026-07-05T08:20:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09313","created_at":"2026-07-05T08:20:54Z"},{"alias_kind":"pith_short_12","alias_value":"N7SZM6RPHCSZ","created_at":"2026-07-05T08:20:54Z"},{"alias_kind":"pith_short_16","alias_value":"N7SZM6RPHCSZ46Q7","created_at":"2026-07-05T08:20:54Z"},{"alias_kind":"pith_short_8","alias_value":"N7SZM6RP","created_at":"2026-07-05T08:20:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:N7SZM6RPHCSZ46Q7B24NQVKHLB","target":"record","payload":{"canonical_record":{"source":{"id":"2404.09313","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-04-14T18:00:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7a3aa3f354f3c39b75a611f90a99f67cd6bb09dcfce6f09dcb4a0a06de4f8a17","abstract_canon_sha256":"c2380d2b2a8625a0761324ac398a28d59141d0e3489d6c3c6d16beff403e9995"},"schema_version":"1.0"},"canonical_sha256":"6fe5967a2f38a59e7a1f0eb8d855475867866b263289d7d620b3b62e22090b97","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:20:54.059023Z","signature_b64":"sL42RggdeZJGv79pnRE2145sYOYhp/YAVTR/acYAeKpoHbvBLzKmm5BPPcqVaEP2GyVMzHZ3b76gXGmQf7dGCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fe5967a2f38a59e7a1f0eb8d855475867866b263289d7d620b3b62e22090b97","last_reissued_at":"2026-07-05T08:20:54.058488Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:20:54.058488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.09313","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:20:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W7f6MHKjUfUi+1n/54SLbfiaxJKWl0CPxrEd8TS0NZfRTlMs4LXnhWm9RrdEmwOc9QO1hxvq0lCMy1hifZTxCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T05:16:23.875391Z"},"content_sha256":"f8e2a5c2e8bc35e410b561624461ccd821c4b14e47ef38219b93bc2391856519","schema_version":"1.0","event_id":"sha256:f8e2a5c2e8bc35e410b561624461ccd821c4b14e47ef38219b93bc2391856519"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:N7SZM6RPHCSZ46Q7B24NQVKHLB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text-to-Song: Towards Controllable Music Generation Incorporating Vocals and Accompaniment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"eess.AS","authors_text":"Fuming You, Rongjie Huang, Ruiqi Li, Xize Cheng, Yongqi Wang, Zhimeng Zhang, Zhiqing Hong, Zhou Zhao","submitted_at":"2024-04-14T18:00:05Z","abstract_excerpt":"A song is a combination of singing voice and accompaniment. However, existing works focus on singing voice synthesis and music generation independently. Little attention was paid to explore song synthesis. In this work, we propose a novel task called text-to-song synthesis which incorporating both vocals and accompaniments generation. We develop Melodist, a two-stage text-to-song method that consists of singing voice synthesis (SVS) and vocal-to-accompaniment (V2A) synthesis. Melodist leverages tri-tower contrastive pretraining to learn more effective text representation for controllable V2A s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09313","kind":"arxiv","version":3},"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/2404.09313/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":"2026-07-05T08:20:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bm7iFSBAdJAPfsh6xUhMmOpP6AB/28Z+V4ZQ1ExvAN9MzoDIp5qW6oZWfJBcWQCllP3tB8PykCyUCEa4dnH+Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T05:16:23.875905Z"},"content_sha256":"dd2a72ac200d433689aeae878a95b237cfb2f31682a52f8dc99f4c199d9cf804","schema_version":"1.0","event_id":"sha256:dd2a72ac200d433689aeae878a95b237cfb2f31682a52f8dc99f4c199d9cf804"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N7SZM6RPHCSZ46Q7B24NQVKHLB/bundle.json","state_url":"https://pith.science/pith/N7SZM6RPHCSZ46Q7B24NQVKHLB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N7SZM6RPHCSZ46Q7B24NQVKHLB/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":"2026-08-10T05:16:23Z","links":{"resolver":"https://pith.science/pith/N7SZM6RPHCSZ46Q7B24NQVKHLB","bundle":"https://pith.science/pith/N7SZM6RPHCSZ46Q7B24NQVKHLB/bundle.json","state":"https://pith.science/pith/N7SZM6RPHCSZ46Q7B24NQVKHLB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N7SZM6RPHCSZ46Q7B24NQVKHLB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:N7SZM6RPHCSZ46Q7B24NQVKHLB","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":"c2380d2b2a8625a0761324ac398a28d59141d0e3489d6c3c6d16beff403e9995","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-04-14T18:00:05Z","title_canon_sha256":"7a3aa3f354f3c39b75a611f90a99f67cd6bb09dcfce6f09dcb4a0a06de4f8a17"},"schema_version":"1.0","source":{"id":"2404.09313","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.09313","created_at":"2026-07-05T08:20:54Z"},{"alias_kind":"arxiv_version","alias_value":"2404.09313v3","created_at":"2026-07-05T08:20:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09313","created_at":"2026-07-05T08:20:54Z"},{"alias_kind":"pith_short_12","alias_value":"N7SZM6RPHCSZ","created_at":"2026-07-05T08:20:54Z"},{"alias_kind":"pith_short_16","alias_value":"N7SZM6RPHCSZ46Q7","created_at":"2026-07-05T08:20:54Z"},{"alias_kind":"pith_short_8","alias_value":"N7SZM6RP","created_at":"2026-07-05T08:20:54Z"}],"graph_snapshots":[{"event_id":"sha256:dd2a72ac200d433689aeae878a95b237cfb2f31682a52f8dc99f4c199d9cf804","target":"graph","created_at":"2026-07-05T08:20:54Z","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/2404.09313/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A song is a combination of singing voice and accompaniment. However, existing works focus on singing voice synthesis and music generation independently. Little attention was paid to explore song synthesis. In this work, we propose a novel task called text-to-song synthesis which incorporating both vocals and accompaniments generation. We develop Melodist, a two-stage text-to-song method that consists of singing voice synthesis (SVS) and vocal-to-accompaniment (V2A) synthesis. Melodist leverages tri-tower contrastive pretraining to learn more effective text representation for controllable V2A s","authors_text":"Fuming You, Rongjie Huang, Ruiqi Li, Xize Cheng, Yongqi Wang, Zhimeng Zhang, Zhiqing Hong, Zhou Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-04-14T18:00:05Z","title":"Text-to-Song: Towards Controllable Music Generation Incorporating Vocals and Accompaniment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09313","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:f8e2a5c2e8bc35e410b561624461ccd821c4b14e47ef38219b93bc2391856519","target":"record","created_at":"2026-07-05T08:20:54Z","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":"c2380d2b2a8625a0761324ac398a28d59141d0e3489d6c3c6d16beff403e9995","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-04-14T18:00:05Z","title_canon_sha256":"7a3aa3f354f3c39b75a611f90a99f67cd6bb09dcfce6f09dcb4a0a06de4f8a17"},"schema_version":"1.0","source":{"id":"2404.09313","kind":"arxiv","version":3}},"canonical_sha256":"6fe5967a2f38a59e7a1f0eb8d855475867866b263289d7d620b3b62e22090b97","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6fe5967a2f38a59e7a1f0eb8d855475867866b263289d7d620b3b62e22090b97","first_computed_at":"2026-07-05T08:20:54.058488Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:20:54.058488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sL42RggdeZJGv79pnRE2145sYOYhp/YAVTR/acYAeKpoHbvBLzKmm5BPPcqVaEP2GyVMzHZ3b76gXGmQf7dGCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:20:54.059023Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.09313","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8e2a5c2e8bc35e410b561624461ccd821c4b14e47ef38219b93bc2391856519","sha256:dd2a72ac200d433689aeae878a95b237cfb2f31682a52f8dc99f4c199d9cf804"],"state_sha256":"0fe2b513dc8c826a400ef57b871af5cd2490c9c70dc8627f6986ecf21f601f09"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7CeGC2vzfD6vleFuMiAO/fjKP5NEWGGiyl/Is40dbrLJsn9d+eb4WnPxw6uXWJuM42gobjTftPDtSjS4DNJ1Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T05:16:23.879344Z","bundle_sha256":"2346bc0c2bfe5617075bf6a6fddb7bbe2f357319b48215b3481403af3a0dcb2f"}}