{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AS3SNXIES2P7SS7L4RNH2Q2NXB","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":"bd77ef82c60b17dfe3f8a5115de484a16ff668ab2b22074bdd5383731c2a675c","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-11T17:11:21Z","title_canon_sha256":"f91e0368a954cb6f375311c5ca764a7332afb36cddc6879c93124a2fa63dcd4c"},"schema_version":"1.0","source":{"id":"2412.08550","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08550","created_at":"2026-07-05T10:48:22Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08550v2","created_at":"2026-07-05T10:48:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08550","created_at":"2026-07-05T10:48:22Z"},{"alias_kind":"pith_short_12","alias_value":"AS3SNXIES2P7","created_at":"2026-07-05T10:48:22Z"},{"alias_kind":"pith_short_16","alias_value":"AS3SNXIES2P7SS7L","created_at":"2026-07-05T10:48:22Z"},{"alias_kind":"pith_short_8","alias_value":"AS3SNXIE","created_at":"2026-07-05T10:48:22Z"}],"graph_snapshots":[{"event_id":"sha256:e1aca74db89488fbf6b13638e6c69fea4518ed54826fdf4d6a983a219bc16baa","target":"graph","created_at":"2026-07-05T10:48:22Z","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/2412.08550/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bryan Pardo, Hugo Flores Garc\\'ia, Justin Salamon, Oriol Nieto, Prem Seetharaman","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-11T17:11:21Z","title":"Sketch2Sound: Controllable Audio Generation via Time-Varying Signals and Sonic Imitations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08550","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":"sha256:462ad9c0e04d9922a10f0732711f325cc844f84be1d1136c6d4219c9bab947c2","target":"record","created_at":"2026-07-05T10:48:22Z","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":"bd77ef82c60b17dfe3f8a5115de484a16ff668ab2b22074bdd5383731c2a675c","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-11T17:11:21Z","title_canon_sha256":"f91e0368a954cb6f375311c5ca764a7332afb36cddc6879c93124a2fa63dcd4c"},"schema_version":"1.0","source":{"id":"2412.08550","kind":"arxiv","version":2}},"canonical_sha256":"04b726dd04969ff94bebe45a7d434db86c936999c36ed77576167db1b7e046d4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04b726dd04969ff94bebe45a7d434db86c936999c36ed77576167db1b7e046d4","first_computed_at":"2026-07-05T10:48:22.633143Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:48:22.633143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jhTo9R4okSfkEu6Q8YwELSR8fHbg7uwJRsBEzdkUtCmR6ZLRXzEtGJY2RZ+Gd1gajVxYRGXLACtq6XWbcaCzDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:48:22.633596Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.08550","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:462ad9c0e04d9922a10f0732711f325cc844f84be1d1136c6d4219c9bab947c2","sha256:e1aca74db89488fbf6b13638e6c69fea4518ed54826fdf4d6a983a219bc16baa"],"state_sha256":"2a9461c939e3aa51b8732f4c506eba474358a01aec3258aca0b16dae0296f208"}