{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2YOQGCEIXKPSN4CRRM27JKDADY","short_pith_number":"pith:2YOQGCEI","schema_version":"1.0","canonical_sha256":"d61d030888ba9f26f0518b35f4a8601e3fc270433448a3799c0da9a26fae1ed4","source":{"kind":"arxiv","id":"2509.05256","version":1},"attestation_state":"computed","paper":{"title":"Recomposer: Event-roll-guided generative audio editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Aren Jansen, Daniel P. W. Ellis, Eduardo Fonseca, Hakan Erdogan, John R. Hershey, Kevin Wilson, Manoj Plakal, R. Channing Moore, Ron J. Weiss, Scott Wisdom","submitted_at":"2025-09-05T17:14:29Z","abstract_excerpt":"Editing complex real-world sound scenes is difficult because individual sound sources overlap in time. Generative models can fill-in missing or corrupted details based on their strong prior understanding of the data domain. We present a system for editing individual sound events within complex scenes able to delete, insert, and enhance individual sound events based on textual edit descriptions (e.g., ``enhance Door'') and a graphical representation of the event timing derived from an ``event roll'' transcription. We present an encoder-decoder transformer working on SoundStream representations,"},"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":"2509.05256","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-09-05T17:14:29Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"title_canon_sha256":"b49f5573d0a7ff3d2dff21500347e9d82fa7b716116a7d19f8f4404331b5ff24","abstract_canon_sha256":"76488b02d6dfa1dbebd84c26ea0740205ea6057b978c3b71c751c4b4ca1c50d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:38.333635Z","signature_b64":"ieIwvsKnM3aKJZdEo+t1QggTwXsqTsaEbtSSG8e3eZh2B+AXVHZGRMCX04/ucnkPUErr+eRPuHbeGRBkXnHNAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d61d030888ba9f26f0518b35f4a8601e3fc270433448a3799c0da9a26fae1ed4","last_reissued_at":"2026-07-05T12:05:38.333123Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:38.333123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recomposer: Event-roll-guided generative audio editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Aren Jansen, Daniel P. W. Ellis, Eduardo Fonseca, Hakan Erdogan, John R. Hershey, Kevin Wilson, Manoj Plakal, R. Channing Moore, Ron J. Weiss, Scott Wisdom","submitted_at":"2025-09-05T17:14:29Z","abstract_excerpt":"Editing complex real-world sound scenes is difficult because individual sound sources overlap in time. Generative models can fill-in missing or corrupted details based on their strong prior understanding of the data domain. We present a system for editing individual sound events within complex scenes able to delete, insert, and enhance individual sound events based on textual edit descriptions (e.g., ``enhance Door'') and a graphical representation of the event timing derived from an ``event roll'' transcription. We present an encoder-decoder transformer working on SoundStream representations,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05256","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/2509.05256/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":"2509.05256","created_at":"2026-07-05T12:05:38.333184+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.05256v1","created_at":"2026-07-05T12:05:38.333184+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05256","created_at":"2026-07-05T12:05:38.333184+00:00"},{"alias_kind":"pith_short_12","alias_value":"2YOQGCEIXKPS","created_at":"2026-07-05T12:05:38.333184+00:00"},{"alias_kind":"pith_short_16","alias_value":"2YOQGCEIXKPSN4CR","created_at":"2026-07-05T12:05:38.333184+00:00"},{"alias_kind":"pith_short_8","alias_value":"2YOQGCEI","created_at":"2026-07-05T12:05:38.333184+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07229","citing_title":"MMAE: A Massive Multitask Audio Editing Benchmark","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2YOQGCEIXKPSN4CRRM27JKDADY","json":"https://pith.science/pith/2YOQGCEIXKPSN4CRRM27JKDADY.json","graph_json":"https://pith.science/api/pith-number/2YOQGCEIXKPSN4CRRM27JKDADY/graph.json","events_json":"https://pith.science/api/pith-number/2YOQGCEIXKPSN4CRRM27JKDADY/events.json","paper":"https://pith.science/paper/2YOQGCEI"},"agent_actions":{"view_html":"https://pith.science/pith/2YOQGCEIXKPSN4CRRM27JKDADY","download_json":"https://pith.science/pith/2YOQGCEIXKPSN4CRRM27JKDADY.json","view_paper":"https://pith.science/paper/2YOQGCEI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.05256&json=true","fetch_graph":"https://pith.science/api/pith-number/2YOQGCEIXKPSN4CRRM27JKDADY/graph.json","fetch_events":"https://pith.science/api/pith-number/2YOQGCEIXKPSN4CRRM27JKDADY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2YOQGCEIXKPSN4CRRM27JKDADY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2YOQGCEIXKPSN4CRRM27JKDADY/action/storage_attestation","attest_author":"https://pith.science/pith/2YOQGCEIXKPSN4CRRM27JKDADY/action/author_attestation","sign_citation":"https://pith.science/pith/2YOQGCEIXKPSN4CRRM27JKDADY/action/citation_signature","submit_replication":"https://pith.science/pith/2YOQGCEIXKPSN4CRRM27JKDADY/action/replication_record"}},"created_at":"2026-07-05T12:05:38.333184+00:00","updated_at":"2026-07-05T12:05:38.333184+00:00"}