{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CFK7CUILPM665TAS7V6SW3HQA6","short_pith_number":"pith:CFK7CUIL","schema_version":"1.0","canonical_sha256":"1155f1510b7b3deecc12fd7d2b6cf007b2c5ec1db799b6b9faa729dc18e8a309","source":{"kind":"arxiv","id":"2409.20196","version":4},"attestation_state":"computed","paper":{"title":"Melody-Guided Music Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Gang Kou, Haoyu Wang, Manzhen Wei, Shaopeng Wei, Yu Zhao","submitted_at":"2024-09-30T11:13:35Z","abstract_excerpt":"We present the Melody-Guided Music Generation (MG2) model, a novel approach using melody to guide the text-to-music generation that, despite a simple method and limited resources, achieves excellent performance. Specifically, we first align the text with audio waveforms and their associated melodies using the newly proposed Contrastive Language-Music Pretraining, enabling the learned text representation fused with implicit melody information. Subsequently, we condition the retrieval-augmented diffusion module on both text prompt and retrieved melody. This allows MG2 to generate music that refl"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2409.20196","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-30T11:13:35Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"e663546232b663c5350d9036c3d60494a5e356a1d029c7ccb0db7485453d8c64","abstract_canon_sha256":"139c8127bac87b1a99bfc16f101b71ecf3f0d49ba95340205374d47d869005a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:13.001190Z","signature_b64":"uiiirdgt7BJX+PI0Pur9EzkRURURoeHALwxWw7E7woeWuobuEcxceTAjNqQHzxSPyzXnxaitoTNsRts6HiEHCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1155f1510b7b3deecc12fd7d2b6cf007b2c5ec1db799b6b9faa729dc18e8a309","last_reissued_at":"2026-07-05T09:55:13.000646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:13.000646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Melody-Guided Music Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Gang Kou, Haoyu Wang, Manzhen Wei, Shaopeng Wei, Yu Zhao","submitted_at":"2024-09-30T11:13:35Z","abstract_excerpt":"We present the Melody-Guided Music Generation (MG2) model, a novel approach using melody to guide the text-to-music generation that, despite a simple method and limited resources, achieves excellent performance. Specifically, we first align the text with audio waveforms and their associated melodies using the newly proposed Contrastive Language-Music Pretraining, enabling the learned text representation fused with implicit melody information. Subsequently, we condition the retrieval-augmented diffusion module on both text prompt and retrieved melody. This allows MG2 to generate music that refl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.20196","kind":"arxiv","version":4},"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/2409.20196/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2409.20196","created_at":"2026-07-05T09:55:13.000704+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.20196v4","created_at":"2026-07-05T09:55:13.000704+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.20196","created_at":"2026-07-05T09:55:13.000704+00:00"},{"alias_kind":"pith_short_12","alias_value":"CFK7CUILPM66","created_at":"2026-07-05T09:55:13.000704+00:00"},{"alias_kind":"pith_short_16","alias_value":"CFK7CUILPM665TAS","created_at":"2026-07-05T09:55:13.000704+00:00"},{"alias_kind":"pith_short_8","alias_value":"CFK7CUIL","created_at":"2026-07-05T09:55:13.000704+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CFK7CUILPM665TAS7V6SW3HQA6","json":"https://pith.science/pith/CFK7CUILPM665TAS7V6SW3HQA6.json","graph_json":"https://pith.science/api/pith-number/CFK7CUILPM665TAS7V6SW3HQA6/graph.json","events_json":"https://pith.science/api/pith-number/CFK7CUILPM665TAS7V6SW3HQA6/events.json","paper":"https://pith.science/paper/CFK7CUIL"},"agent_actions":{"view_html":"https://pith.science/pith/CFK7CUILPM665TAS7V6SW3HQA6","download_json":"https://pith.science/pith/CFK7CUILPM665TAS7V6SW3HQA6.json","view_paper":"https://pith.science/paper/CFK7CUIL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.20196&json=true","fetch_graph":"https://pith.science/api/pith-number/CFK7CUILPM665TAS7V6SW3HQA6/graph.json","fetch_events":"https://pith.science/api/pith-number/CFK7CUILPM665TAS7V6SW3HQA6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CFK7CUILPM665TAS7V6SW3HQA6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CFK7CUILPM665TAS7V6SW3HQA6/action/storage_attestation","attest_author":"https://pith.science/pith/CFK7CUILPM665TAS7V6SW3HQA6/action/author_attestation","sign_citation":"https://pith.science/pith/CFK7CUILPM665TAS7V6SW3HQA6/action/citation_signature","submit_replication":"https://pith.science/pith/CFK7CUILPM665TAS7V6SW3HQA6/action/replication_record"}},"created_at":"2026-07-05T09:55:13.000704+00:00","updated_at":"2026-07-05T09:55:13.000704+00:00"}