{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5QP2ENRSYF7G7VEBL6MYS7NOBG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e584cccef9bf1f267168c74f9fe22a784f84c95b414ebc1b4c27ce6858782ae7","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-23T15:16:18Z","title_canon_sha256":"aaec4ef81c10fad142934fe0586273d66ccac9bc34ed1bacf49f7638a343e376"},"schema_version":"1.0","source":{"id":"2407.16564","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.16564","created_at":"2026-07-05T08:47:55Z"},{"alias_kind":"arxiv_version","alias_value":"2407.16564v2","created_at":"2026-07-05T08:47:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16564","created_at":"2026-07-05T08:47:55Z"},{"alias_kind":"pith_short_12","alias_value":"5QP2ENRSYF7G","created_at":"2026-07-05T08:47:55Z"},{"alias_kind":"pith_short_16","alias_value":"5QP2ENRSYF7G7VEB","created_at":"2026-07-05T08:47:55Z"},{"alias_kind":"pith_short_8","alias_value":"5QP2ENRS","created_at":"2026-07-05T08:47:55Z"}],"graph_snapshots":[{"event_id":"sha256:9a8a1bff2ba4d8d43e5658b083d041606f612195dca272482456f230d2396793","target":"graph","created_at":"2026-07-05T08:47:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.16564/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bo-Yu Chen, Fang-Duo Tsai, Hao-Chung Cheng, Haven Kim, Shih-Lun Wu, Yi-Hsuan Yang","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-23T15:16:18Z","title":"Audio Prompt Adapter: Unleashing Music Editing Abilities for Text-to-Music with Lightweight Finetuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16564","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ff36d932b0f6dc339d23d2834b1931a9ba007aaa3f02038f3eb5ae5193283deb","target":"record","created_at":"2026-07-05T08:47:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e584cccef9bf1f267168c74f9fe22a784f84c95b414ebc1b4c27ce6858782ae7","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-23T15:16:18Z","title_canon_sha256":"aaec4ef81c10fad142934fe0586273d66ccac9bc34ed1bacf49f7638a343e376"},"schema_version":"1.0","source":{"id":"2407.16564","kind":"arxiv","version":2}},"canonical_sha256":"ec1fa23632c17e6fd4815f99897dae098e2934ff0e9424a6a8983207ea4b6b03","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec1fa23632c17e6fd4815f99897dae098e2934ff0e9424a6a8983207ea4b6b03","first_computed_at":"2026-07-05T08:47:55.966713Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:47:55.966713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K37IlAvqk5GuelPFQjRMSdqW+RRRJIpJ2+CQLCseEmrv150Pn/F5HVdjZSwlqokm6GfeXtonUjjmnzfQo3ZmDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:47:55.967214Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.16564","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff36d932b0f6dc339d23d2834b1931a9ba007aaa3f02038f3eb5ae5193283deb","sha256:9a8a1bff2ba4d8d43e5658b083d041606f612195dca272482456f230d2396793"],"state_sha256":"aeeabcd9f7f4a55c8613f2973eb150795348dd53b99813a51fe793944eb2cc16"}