{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JTUKI6DZ34DYQRYWYICCDNEJ6E","short_pith_number":"pith:JTUKI6DZ","schema_version":"1.0","canonical_sha256":"4ce8a47879df07884716c20421b489f13774cc9a6d178af9fe2c48d969fac53d","source":{"kind":"arxiv","id":"2305.15719","version":1},"attestation_state":"computed","paper":{"title":"Efficient Neural Music Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jitong Chen, Max W. Y. Lam, Mingbo Ma, Ming Tu, Qiao Tian, Rui Xia, Siyuan Feng, Tang Li, Xuchen Song, Yuliang Ji, Yuping Wang, Yuxuan Wang, Zongyu Yin","submitted_at":"2023-05-25T05:02:35Z","abstract_excerpt":"Recent progress in music generation has been remarkably advanced by the state-of-the-art MusicLM, which comprises a hierarchy of three LMs, respectively, for semantic, coarse acoustic, and fine acoustic modelings. Yet, sampling with the MusicLM requires processing through these LMs one by one to obtain the fine-grained acoustic tokens, making it computationally expensive and prohibitive for a real-time generation. Efficient music generation with a quality on par with MusicLM remains a significant challenge. In this paper, we present MeLoDy (M for music; L for LM; D for diffusion), an LM-guided"},"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":"2305.15719","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-05-25T05:02:35Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"title_canon_sha256":"4ccdeb3db1172da8579273f00eaccbced672668e5e5ed4dcf743ce2660c79727","abstract_canon_sha256":"3d0bd6b89fbc1a6f1fd0c842b5b604bf3fe78898a2d96c51b4bd2a1bf5d0978b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:43.828670Z","signature_b64":"q36JiOBSDFznWy9PIPc8yaaSPpqrgK2fl5OwRHzMYTNlU4IkDJVWsy7/mdouPhZPAeTmFXLNuurUDfoEFgZyBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ce8a47879df07884716c20421b489f13774cc9a6d178af9fe2c48d969fac53d","last_reissued_at":"2026-07-05T06:13:43.828256Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:43.828256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Neural Music Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jitong Chen, Max W. Y. Lam, Mingbo Ma, Ming Tu, Qiao Tian, Rui Xia, Siyuan Feng, Tang Li, Xuchen Song, Yuliang Ji, Yuping Wang, Yuxuan Wang, Zongyu Yin","submitted_at":"2023-05-25T05:02:35Z","abstract_excerpt":"Recent progress in music generation has been remarkably advanced by the state-of-the-art MusicLM, which comprises a hierarchy of three LMs, respectively, for semantic, coarse acoustic, and fine acoustic modelings. Yet, sampling with the MusicLM requires processing through these LMs one by one to obtain the fine-grained acoustic tokens, making it computationally expensive and prohibitive for a real-time generation. Efficient music generation with a quality on par with MusicLM remains a significant challenge. In this paper, we present MeLoDy (M for music; L for LM; D for diffusion), an LM-guided"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15719","kind":"arxiv","version":1},"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/2305.15719/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":"2305.15719","created_at":"2026-07-05T06:13:43.828313+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.15719v1","created_at":"2026-07-05T06:13:43.828313+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15719","created_at":"2026-07-05T06:13:43.828313+00:00"},{"alias_kind":"pith_short_12","alias_value":"JTUKI6DZ34DY","created_at":"2026-07-05T06:13:43.828313+00:00"},{"alias_kind":"pith_short_16","alias_value":"JTUKI6DZ34DYQRYW","created_at":"2026-07-05T06:13:43.828313+00:00"},{"alias_kind":"pith_short_8","alias_value":"JTUKI6DZ","created_at":"2026-07-05T06:13:43.828313+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.20880","citing_title":"JAM: A Tiny Flow-based Song Generator with Fine-grained Controllability and Aesthetic Alignment","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JTUKI6DZ34DYQRYWYICCDNEJ6E","json":"https://pith.science/pith/JTUKI6DZ34DYQRYWYICCDNEJ6E.json","graph_json":"https://pith.science/api/pith-number/JTUKI6DZ34DYQRYWYICCDNEJ6E/graph.json","events_json":"https://pith.science/api/pith-number/JTUKI6DZ34DYQRYWYICCDNEJ6E/events.json","paper":"https://pith.science/paper/JTUKI6DZ"},"agent_actions":{"view_html":"https://pith.science/pith/JTUKI6DZ34DYQRYWYICCDNEJ6E","download_json":"https://pith.science/pith/JTUKI6DZ34DYQRYWYICCDNEJ6E.json","view_paper":"https://pith.science/paper/JTUKI6DZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.15719&json=true","fetch_graph":"https://pith.science/api/pith-number/JTUKI6DZ34DYQRYWYICCDNEJ6E/graph.json","fetch_events":"https://pith.science/api/pith-number/JTUKI6DZ34DYQRYWYICCDNEJ6E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JTUKI6DZ34DYQRYWYICCDNEJ6E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JTUKI6DZ34DYQRYWYICCDNEJ6E/action/storage_attestation","attest_author":"https://pith.science/pith/JTUKI6DZ34DYQRYWYICCDNEJ6E/action/author_attestation","sign_citation":"https://pith.science/pith/JTUKI6DZ34DYQRYWYICCDNEJ6E/action/citation_signature","submit_replication":"https://pith.science/pith/JTUKI6DZ34DYQRYWYICCDNEJ6E/action/replication_record"}},"created_at":"2026-07-05T06:13:43.828313+00:00","updated_at":"2026-07-05T06:13:43.828313+00:00"}