{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5QP2ENRSYF7G7VEBL6MYS7NOBG","short_pith_number":"pith:5QP2ENRS","schema_version":"1.0","canonical_sha256":"ec1fa23632c17e6fd4815f99897dae098e2934ff0e9424a6a8983207ea4b6b03","source":{"kind":"arxiv","id":"2407.16564","version":2},"attestation_state":"computed","paper":{"title":"Audio Prompt Adapter: Unleashing Music Editing Abilities for Text-to-Music with Lightweight Finetuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bo-Yu Chen, Fang-Duo Tsai, Hao-Chung Cheng, Haven Kim, Shih-Lun Wu, Yi-Hsuan Yang","submitted_at":"2024-07-23T15:16:18Z","abstract_excerpt":"Text-to-music models allow users to generate nearly realistic musical audio with textual commands. However, editing music audios remains challenging due to the conflicting desiderata of performing fine-grained alterations on the audio while maintaining a simple user interface. To address this challenge, we propose Audio Prompt Adapter (or AP-Adapter), a lightweight addition to pretrained text-to-music models. We utilize AudioMAE to extract features from the input audio, and construct attention-based adapters to feedthese features into the internal layers of AudioLDM2, a diffusion-based text-to"},"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":"2407.16564","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-23T15:16:18Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"aaec4ef81c10fad142934fe0586273d66ccac9bc34ed1bacf49f7638a343e376","abstract_canon_sha256":"e584cccef9bf1f267168c74f9fe22a784f84c95b414ebc1b4c27ce6858782ae7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:47:55.967214Z","signature_b64":"K37IlAvqk5GuelPFQjRMSdqW+RRRJIpJ2+CQLCseEmrv150Pn/F5HVdjZSwlqokm6GfeXtonUjjmnzfQo3ZmDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec1fa23632c17e6fd4815f99897dae098e2934ff0e9424a6a8983207ea4b6b03","last_reissued_at":"2026-07-05T08:47:55.966713Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:47:55.966713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio Prompt Adapter: Unleashing Music Editing Abilities for Text-to-Music with Lightweight Finetuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bo-Yu Chen, Fang-Duo Tsai, Hao-Chung Cheng, Haven Kim, Shih-Lun Wu, Yi-Hsuan Yang","submitted_at":"2024-07-23T15:16:18Z","abstract_excerpt":"Text-to-music models allow users to generate nearly realistic musical audio with textual commands. However, editing music audios remains challenging due to the conflicting desiderata of performing fine-grained alterations on the audio while maintaining a simple user interface. To address this challenge, we propose Audio Prompt Adapter (or AP-Adapter), a lightweight addition to pretrained text-to-music models. We utilize AudioMAE to extract features from the input audio, and construct attention-based adapters to feedthese features into the internal layers of AudioLDM2, a diffusion-based text-to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16564","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/2407.16564/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":"2407.16564","created_at":"2026-07-05T08:47:55.966772+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.16564v2","created_at":"2026-07-05T08:47:55.966772+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16564","created_at":"2026-07-05T08:47:55.966772+00:00"},{"alias_kind":"pith_short_12","alias_value":"5QP2ENRSYF7G","created_at":"2026-07-05T08:47:55.966772+00:00"},{"alias_kind":"pith_short_16","alias_value":"5QP2ENRSYF7G7VEB","created_at":"2026-07-05T08:47:55.966772+00:00"},{"alias_kind":"pith_short_8","alias_value":"5QP2ENRS","created_at":"2026-07-05T08:47:55.966772+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04939","citing_title":"UAT: Unified Audio-Text Diffusion for Audio Generation, Editing, and Captioning","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31053","citing_title":"AnchorSteer: Self-Discovered Concept Injection for Structure-Preserving Music Editing","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2505.08203","citing_title":"Not that Groove: Zero-Shot Symbolic Music Editing","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2602.22029","citing_title":"MIDI-Informed Singing Accompaniment Generation in a Compositional Song Pipeline","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5QP2ENRSYF7G7VEBL6MYS7NOBG","json":"https://pith.science/pith/5QP2ENRSYF7G7VEBL6MYS7NOBG.json","graph_json":"https://pith.science/api/pith-number/5QP2ENRSYF7G7VEBL6MYS7NOBG/graph.json","events_json":"https://pith.science/api/pith-number/5QP2ENRSYF7G7VEBL6MYS7NOBG/events.json","paper":"https://pith.science/paper/5QP2ENRS"},"agent_actions":{"view_html":"https://pith.science/pith/5QP2ENRSYF7G7VEBL6MYS7NOBG","download_json":"https://pith.science/pith/5QP2ENRSYF7G7VEBL6MYS7NOBG.json","view_paper":"https://pith.science/paper/5QP2ENRS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.16564&json=true","fetch_graph":"https://pith.science/api/pith-number/5QP2ENRSYF7G7VEBL6MYS7NOBG/graph.json","fetch_events":"https://pith.science/api/pith-number/5QP2ENRSYF7G7VEBL6MYS7NOBG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5QP2ENRSYF7G7VEBL6MYS7NOBG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5QP2ENRSYF7G7VEBL6MYS7NOBG/action/storage_attestation","attest_author":"https://pith.science/pith/5QP2ENRSYF7G7VEBL6MYS7NOBG/action/author_attestation","sign_citation":"https://pith.science/pith/5QP2ENRSYF7G7VEBL6MYS7NOBG/action/citation_signature","submit_replication":"https://pith.science/pith/5QP2ENRSYF7G7VEBL6MYS7NOBG/action/replication_record"}},"created_at":"2026-07-05T08:47:55.966772+00:00","updated_at":"2026-07-05T08:47:55.966772+00:00"}