{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AS3SNXIES2P7SS7L4RNH2Q2NXB","short_pith_number":"pith:AS3SNXIE","schema_version":"1.0","canonical_sha256":"04b726dd04969ff94bebe45a7d434db86c936999c36ed77576167db1b7e046d4","source":{"kind":"arxiv","id":"2412.08550","version":2},"attestation_state":"computed","paper":{"title":"Sketch2Sound: Controllable Audio Generation via Time-Varying Signals and Sonic Imitations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bryan Pardo, Hugo Flores Garc\\'ia, Justin Salamon, Oriol Nieto, Prem Seetharaman","submitted_at":"2024-12-11T17:11:21Z","abstract_excerpt":"We present Sketch2Sound, a generative audio model capable of creating high-quality sounds from a set of interpretable time-varying control signals: loudness, brightness, and pitch, as well as text prompts. Sketch2Sound can synthesize arbitrary sounds from sonic imitations (i.e.,~a vocal imitation or a reference sound-shape). Sketch2Sound can be implemented on top of any text-to-audio latent diffusion transformer (DiT), and requires only 40k steps of fine-tuning and a single linear layer per control, making it more lightweight than existing methods like ControlNet. To synthesize from sketchlike"},"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":"2412.08550","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-11T17:11:21Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"f91e0368a954cb6f375311c5ca764a7332afb36cddc6879c93124a2fa63dcd4c","abstract_canon_sha256":"bd77ef82c60b17dfe3f8a5115de484a16ff668ab2b22074bdd5383731c2a675c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:22.633596Z","signature_b64":"jhTo9R4okSfkEu6Q8YwELSR8fHbg7uwJRsBEzdkUtCmR6ZLRXzEtGJY2RZ+Gd1gajVxYRGXLACtq6XWbcaCzDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04b726dd04969ff94bebe45a7d434db86c936999c36ed77576167db1b7e046d4","last_reissued_at":"2026-07-05T10:48:22.633143Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:22.633143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sketch2Sound: Controllable Audio Generation via Time-Varying Signals and Sonic Imitations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bryan Pardo, Hugo Flores Garc\\'ia, Justin Salamon, Oriol Nieto, Prem Seetharaman","submitted_at":"2024-12-11T17:11:21Z","abstract_excerpt":"We present Sketch2Sound, a generative audio model capable of creating high-quality sounds from a set of interpretable time-varying control signals: loudness, brightness, and pitch, as well as text prompts. Sketch2Sound can synthesize arbitrary sounds from sonic imitations (i.e.,~a vocal imitation or a reference sound-shape). Sketch2Sound can be implemented on top of any text-to-audio latent diffusion transformer (DiT), and requires only 40k steps of fine-tuning and a single linear layer per control, making it more lightweight than existing methods like ControlNet. To synthesize from sketchlike"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08550","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/2412.08550/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":"2412.08550","created_at":"2026-07-05T10:48:22.633201+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.08550v2","created_at":"2026-07-05T10:48:22.633201+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08550","created_at":"2026-07-05T10:48:22.633201+00:00"},{"alias_kind":"pith_short_12","alias_value":"AS3SNXIES2P7","created_at":"2026-07-05T10:48:22.633201+00:00"},{"alias_kind":"pith_short_16","alias_value":"AS3SNXIES2P7SS7L","created_at":"2026-07-05T10:48:22.633201+00:00"},{"alias_kind":"pith_short_8","alias_value":"AS3SNXIE","created_at":"2026-07-05T10:48:22.633201+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.05256","citing_title":"Recomposer: Event-roll-guided generative audio editing","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AS3SNXIES2P7SS7L4RNH2Q2NXB","json":"https://pith.science/pith/AS3SNXIES2P7SS7L4RNH2Q2NXB.json","graph_json":"https://pith.science/api/pith-number/AS3SNXIES2P7SS7L4RNH2Q2NXB/graph.json","events_json":"https://pith.science/api/pith-number/AS3SNXIES2P7SS7L4RNH2Q2NXB/events.json","paper":"https://pith.science/paper/AS3SNXIE"},"agent_actions":{"view_html":"https://pith.science/pith/AS3SNXIES2P7SS7L4RNH2Q2NXB","download_json":"https://pith.science/pith/AS3SNXIES2P7SS7L4RNH2Q2NXB.json","view_paper":"https://pith.science/paper/AS3SNXIE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.08550&json=true","fetch_graph":"https://pith.science/api/pith-number/AS3SNXIES2P7SS7L4RNH2Q2NXB/graph.json","fetch_events":"https://pith.science/api/pith-number/AS3SNXIES2P7SS7L4RNH2Q2NXB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AS3SNXIES2P7SS7L4RNH2Q2NXB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AS3SNXIES2P7SS7L4RNH2Q2NXB/action/storage_attestation","attest_author":"https://pith.science/pith/AS3SNXIES2P7SS7L4RNH2Q2NXB/action/author_attestation","sign_citation":"https://pith.science/pith/AS3SNXIES2P7SS7L4RNH2Q2NXB/action/citation_signature","submit_replication":"https://pith.science/pith/AS3SNXIES2P7SS7L4RNH2Q2NXB/action/replication_record"}},"created_at":"2026-07-05T10:48:22.633201+00:00","updated_at":"2026-07-05T10:48:22.633201+00:00"}