{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:74JRSHOCGNR5HTHAVTDJJP4ADN","short_pith_number":"pith:74JRSHOC","schema_version":"1.0","canonical_sha256":"ff13191dc23363d3cce0acc694bf801b7c4fff1b6f0c939edc85c8f4e13f4d13","source":{"kind":"arxiv","id":"2405.20289","version":1},"attestation_state":"computed","paper":{"title":"DITTO-2: Distilled Diffusion Inference-Time T-Optimization for Music Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SD","authors_text":"Julian McAuley, Nicholas Bryan, Taylor Berg-Kirkpatrick, Zachary Novack","submitted_at":"2024-05-30T17:40:11Z","abstract_excerpt":"Controllable music generation methods are critical for human-centered AI-based music creation, but are currently limited by speed, quality, and control design trade-offs. Diffusion Inference-Time T-optimization (DITTO), in particular, offers state-of-the-art results, but is over 10x slower than real-time, limiting practical use. We propose Distilled Diffusion Inference-Time T -Optimization (or DITTO-2), a new method to speed up inference-time optimization-based control and unlock faster-than-real-time generation for a wide-variety of applications such as music inpainting, outpainting, intensit"},"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":"2405.20289","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-05-30T17:40:11Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"aa7399ab18fa5fe22ec8ffc34204a3e4fbd007afc8947fd3c2a2e843330f3373","abstract_canon_sha256":"86f0e6f022ac8a9892594a33d76818f0d3874cc4d6c065a3ddd3dc6157acbf2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:18.481521Z","signature_b64":"VYMh622DW3XiFwCjnCQpZ7ELFAozN1JxmBEiCmFJsIQo67TnLK9/bk07FnkHuJfjSCbV7B4sGCN+LpVvH5y0Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff13191dc23363d3cce0acc694bf801b7c4fff1b6f0c939edc85c8f4e13f4d13","last_reissued_at":"2026-07-05T08:25:18.481046Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:18.481046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DITTO-2: Distilled Diffusion Inference-Time T-Optimization for Music Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SD","authors_text":"Julian McAuley, Nicholas Bryan, Taylor Berg-Kirkpatrick, Zachary Novack","submitted_at":"2024-05-30T17:40:11Z","abstract_excerpt":"Controllable music generation methods are critical for human-centered AI-based music creation, but are currently limited by speed, quality, and control design trade-offs. Diffusion Inference-Time T-optimization (DITTO), in particular, offers state-of-the-art results, but is over 10x slower than real-time, limiting practical use. We propose Distilled Diffusion Inference-Time T -Optimization (or DITTO-2), a new method to speed up inference-time optimization-based control and unlock faster-than-real-time generation for a wide-variety of applications such as music inpainting, outpainting, intensit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20289","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/2405.20289/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":"2405.20289","created_at":"2026-07-05T08:25:18.481103+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.20289v1","created_at":"2026-07-05T08:25:18.481103+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20289","created_at":"2026-07-05T08:25:18.481103+00:00"},{"alias_kind":"pith_short_12","alias_value":"74JRSHOCGNR5","created_at":"2026-07-05T08:25:18.481103+00:00"},{"alias_kind":"pith_short_16","alias_value":"74JRSHOCGNR5HTHA","created_at":"2026-07-05T08:25:18.481103+00:00"},{"alias_kind":"pith_short_8","alias_value":"74JRSHOC","created_at":"2026-07-05T08:25:18.481103+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.18729","citing_title":"MuseControlLite: Multifunctional Music Generation with Lightweight Conditioners","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/74JRSHOCGNR5HTHAVTDJJP4ADN","json":"https://pith.science/pith/74JRSHOCGNR5HTHAVTDJJP4ADN.json","graph_json":"https://pith.science/api/pith-number/74JRSHOCGNR5HTHAVTDJJP4ADN/graph.json","events_json":"https://pith.science/api/pith-number/74JRSHOCGNR5HTHAVTDJJP4ADN/events.json","paper":"https://pith.science/paper/74JRSHOC"},"agent_actions":{"view_html":"https://pith.science/pith/74JRSHOCGNR5HTHAVTDJJP4ADN","download_json":"https://pith.science/pith/74JRSHOCGNR5HTHAVTDJJP4ADN.json","view_paper":"https://pith.science/paper/74JRSHOC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.20289&json=true","fetch_graph":"https://pith.science/api/pith-number/74JRSHOCGNR5HTHAVTDJJP4ADN/graph.json","fetch_events":"https://pith.science/api/pith-number/74JRSHOCGNR5HTHAVTDJJP4ADN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/74JRSHOCGNR5HTHAVTDJJP4ADN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/74JRSHOCGNR5HTHAVTDJJP4ADN/action/storage_attestation","attest_author":"https://pith.science/pith/74JRSHOCGNR5HTHAVTDJJP4ADN/action/author_attestation","sign_citation":"https://pith.science/pith/74JRSHOCGNR5HTHAVTDJJP4ADN/action/citation_signature","submit_replication":"https://pith.science/pith/74JRSHOCGNR5HTHAVTDJJP4ADN/action/replication_record"}},"created_at":"2026-07-05T08:25:18.481103+00:00","updated_at":"2026-07-05T08:25:18.481103+00:00"}