{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YWKYAY3OEI2MXHIAPHZR35UZX2","short_pith_number":"pith:YWKYAY3O","schema_version":"1.0","canonical_sha256":"c59580636e2234cb9d0079f31df699be88bd0fd0e642e59eca7e58e5db0f243d","source":{"kind":"arxiv","id":"2402.09508","version":3},"attestation_state":"computed","paper":{"title":"Arrange, Inpaint, and Refine: Steerable Long-term Music Audio Generation and Editing via Content-based Controls","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Gus Xia, Junyan Jiang, Liwei Lin, Yixiao Zhang","submitted_at":"2024-02-14T19:00:01Z","abstract_excerpt":"Controllable music generation plays a vital role in human-AI music co-creation. While Large Language Models (LLMs) have shown promise in generating high-quality music, their focus on autoregressive generation limits their utility in music editing tasks. To address this gap, we propose a novel approach leveraging a parameter-efficient heterogeneous adapter combined with a masking training scheme. This approach enables autoregressive language models to seamlessly address music inpainting tasks. Additionally, our method integrates frame-level content-based controls, facilitating track-conditioned"},"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":"2402.09508","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-02-14T19:00:01Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"ce1a3b23d4967f4bf07dd8620394445797a6116765a6845914a280f0e9122f68","abstract_canon_sha256":"d32ac4886cb4361c66e71d3e9ca73020f119432e082db1946542f3b5ebce3fc1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:12.701269Z","signature_b64":"s4l/tORlYckmzeU2GZT1yl4JerXLUro6MXznUHXHsCtY0a4/o+GK5PBRGOsT5Nme436GwrhRd7SeljFvjzTmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c59580636e2234cb9d0079f31df699be88bd0fd0e642e59eca7e58e5db0f243d","last_reissued_at":"2026-07-05T09:16:12.700836Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:12.700836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Arrange, Inpaint, and Refine: Steerable Long-term Music Audio Generation and Editing via Content-based Controls","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Gus Xia, Junyan Jiang, Liwei Lin, Yixiao Zhang","submitted_at":"2024-02-14T19:00:01Z","abstract_excerpt":"Controllable music generation plays a vital role in human-AI music co-creation. While Large Language Models (LLMs) have shown promise in generating high-quality music, their focus on autoregressive generation limits their utility in music editing tasks. To address this gap, we propose a novel approach leveraging a parameter-efficient heterogeneous adapter combined with a masking training scheme. This approach enables autoregressive language models to seamlessly address music inpainting tasks. Additionally, our method integrates frame-level content-based controls, facilitating track-conditioned"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09508","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/2402.09508/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":"2402.09508","created_at":"2026-07-05T09:16:12.700901+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.09508v3","created_at":"2026-07-05T09:16:12.700901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09508","created_at":"2026-07-05T09:16:12.700901+00:00"},{"alias_kind":"pith_short_12","alias_value":"YWKYAY3OEI2M","created_at":"2026-07-05T09:16:12.700901+00:00"},{"alias_kind":"pith_short_16","alias_value":"YWKYAY3OEI2MXHIA","created_at":"2026-07-05T09:16:12.700901+00:00"},{"alias_kind":"pith_short_8","alias_value":"YWKYAY3O","created_at":"2026-07-05T09:16:12.700901+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.19127","citing_title":"Steering Autoregressive Music Generation with Recursive Feature Machines","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YWKYAY3OEI2MXHIAPHZR35UZX2","json":"https://pith.science/pith/YWKYAY3OEI2MXHIAPHZR35UZX2.json","graph_json":"https://pith.science/api/pith-number/YWKYAY3OEI2MXHIAPHZR35UZX2/graph.json","events_json":"https://pith.science/api/pith-number/YWKYAY3OEI2MXHIAPHZR35UZX2/events.json","paper":"https://pith.science/paper/YWKYAY3O"},"agent_actions":{"view_html":"https://pith.science/pith/YWKYAY3OEI2MXHIAPHZR35UZX2","download_json":"https://pith.science/pith/YWKYAY3OEI2MXHIAPHZR35UZX2.json","view_paper":"https://pith.science/paper/YWKYAY3O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.09508&json=true","fetch_graph":"https://pith.science/api/pith-number/YWKYAY3OEI2MXHIAPHZR35UZX2/graph.json","fetch_events":"https://pith.science/api/pith-number/YWKYAY3OEI2MXHIAPHZR35UZX2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YWKYAY3OEI2MXHIAPHZR35UZX2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YWKYAY3OEI2MXHIAPHZR35UZX2/action/storage_attestation","attest_author":"https://pith.science/pith/YWKYAY3OEI2MXHIAPHZR35UZX2/action/author_attestation","sign_citation":"https://pith.science/pith/YWKYAY3OEI2MXHIAPHZR35UZX2/action/citation_signature","submit_replication":"https://pith.science/pith/YWKYAY3OEI2MXHIAPHZR35UZX2/action/replication_record"}},"created_at":"2026-07-05T09:16:12.700901+00:00","updated_at":"2026-07-05T09:16:12.700901+00:00"}