{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4UZWBKRGMFUT7TUD5K76UY2N53","short_pith_number":"pith:4UZWBKRG","schema_version":"1.0","canonical_sha256":"e53360aa2661693fce83eabfea634deef70a99666d5c826c00cf9e55eadb3d7c","source":{"kind":"arxiv","id":"2402.17785","version":2},"attestation_state":"computed","paper":{"title":"ByteComposer: a Human-like Melody Composition Method based on Language Model Agent","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bilei Zhu, Jiaju Lin, Pei Zou, Xia Liang, Xingjian Du, Yuan Wan","submitted_at":"2024-02-24T04:35:07Z","abstract_excerpt":"Large Language Models (LLM) have shown encouraging progress in multimodal understanding and generation tasks. However, how to design a human-aligned and interpretable melody composition system is still under-explored. To solve this problem, we propose ByteComposer, an agent framework emulating a human's creative pipeline in four separate steps : \"Conception Analysis - Draft Composition - Self-Evaluation and Modification - Aesthetic Selection\". This framework seamlessly blends the interactive and knowledge-understanding features of LLMs with existing symbolic music generation models, thereby ac"},"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":"2402.17785","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-02-24T04:35:07Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"75dba4a3857fb6e23587aa4200ff9eedbf6151d8e8ff5600776ba507c459f9d2","abstract_canon_sha256":"3825f95a19bffc95b3f0c6a976d3b106bfffa6ad5732ea4a71cd264e2652d7ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:15.122560Z","signature_b64":"K03t2d8x52xCJbVXHN6z88NLiYdsOdnPL9ZU51n4AF3r4YT4IheMVZxgOz0UCQWkA0/gYmdsksOI0mWvH0QjAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e53360aa2661693fce83eabfea634deef70a99666d5c826c00cf9e55eadb3d7c","last_reissued_at":"2026-07-05T07:53:15.122002Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:15.122002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ByteComposer: a Human-like Melody Composition Method based on Language Model Agent","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bilei Zhu, Jiaju Lin, Pei Zou, Xia Liang, Xingjian Du, Yuan Wan","submitted_at":"2024-02-24T04:35:07Z","abstract_excerpt":"Large Language Models (LLM) have shown encouraging progress in multimodal understanding and generation tasks. However, how to design a human-aligned and interpretable melody composition system is still under-explored. To solve this problem, we propose ByteComposer, an agent framework emulating a human's creative pipeline in four separate steps : \"Conception Analysis - Draft Composition - Self-Evaluation and Modification - Aesthetic Selection\". This framework seamlessly blends the interactive and knowledge-understanding features of LLMs with existing symbolic music generation models, thereby ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17785","kind":"arxiv","version":2},"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/2402.17785/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":"2402.17785","created_at":"2026-07-05T07:53:15.122076+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.17785v2","created_at":"2026-07-05T07:53:15.122076+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17785","created_at":"2026-07-05T07:53:15.122076+00:00"},{"alias_kind":"pith_short_12","alias_value":"4UZWBKRGMFUT","created_at":"2026-07-05T07:53:15.122076+00:00"},{"alias_kind":"pith_short_16","alias_value":"4UZWBKRGMFUT7TUD","created_at":"2026-07-05T07:53:15.122076+00:00"},{"alias_kind":"pith_short_8","alias_value":"4UZWBKRG","created_at":"2026-07-05T07:53:15.122076+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13431","citing_title":"Text2Score: Generating Sheet Music From Textual Prompts","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4UZWBKRGMFUT7TUD5K76UY2N53","json":"https://pith.science/pith/4UZWBKRGMFUT7TUD5K76UY2N53.json","graph_json":"https://pith.science/api/pith-number/4UZWBKRGMFUT7TUD5K76UY2N53/graph.json","events_json":"https://pith.science/api/pith-number/4UZWBKRGMFUT7TUD5K76UY2N53/events.json","paper":"https://pith.science/paper/4UZWBKRG"},"agent_actions":{"view_html":"https://pith.science/pith/4UZWBKRGMFUT7TUD5K76UY2N53","download_json":"https://pith.science/pith/4UZWBKRGMFUT7TUD5K76UY2N53.json","view_paper":"https://pith.science/paper/4UZWBKRG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.17785&json=true","fetch_graph":"https://pith.science/api/pith-number/4UZWBKRGMFUT7TUD5K76UY2N53/graph.json","fetch_events":"https://pith.science/api/pith-number/4UZWBKRGMFUT7TUD5K76UY2N53/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4UZWBKRGMFUT7TUD5K76UY2N53/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4UZWBKRGMFUT7TUD5K76UY2N53/action/storage_attestation","attest_author":"https://pith.science/pith/4UZWBKRGMFUT7TUD5K76UY2N53/action/author_attestation","sign_citation":"https://pith.science/pith/4UZWBKRGMFUT7TUD5K76UY2N53/action/citation_signature","submit_replication":"https://pith.science/pith/4UZWBKRGMFUT7TUD5K76UY2N53/action/replication_record"}},"created_at":"2026-07-05T07:53:15.122076+00:00","updated_at":"2026-07-05T07:53:15.122076+00:00"}