{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DQWEP5F5TEQZN2EZHRMGCB4YQT","short_pith_number":"pith:DQWEP5F5","schema_version":"1.0","canonical_sha256":"1c2c47f4bd992196e8993c5861079884e588a0af632633e510b48d6565fa0e63","source":{"kind":"arxiv","id":"2401.12179","version":2},"attestation_state":"computed","paper":{"title":"DITTO: Diffusion Inference-Time T-Optimization for Music Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Julian McAuley, Nicholas J. Bryan, Taylor Berg-Kirkpatrick, Zachary Novack","submitted_at":"2024-01-22T18:10:10Z","abstract_excerpt":"We propose Diffusion Inference-Time T-Optimization (DITTO), a general-purpose frame-work for controlling pre-trained text-to-music diffusion models at inference-time via optimizing initial noise latents. Our method can be used to optimize through any differentiable feature matching loss to achieve a target (stylized) output and leverages gradient checkpointing for memory efficiency. We demonstrate a surprisingly wide-range of applications for music generation including inpainting, outpainting, and looping as well as intensity, melody, and musical structure control - all without ever fine-tunin"},"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":"2401.12179","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-01-22T18:10:10Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"title_canon_sha256":"0a1c3c165b999b2bc6b5e867929444f7bc21b6352dc56852cb067460091df6e7","abstract_canon_sha256":"468492482dfe96db6d6f59347f9ce3563a0e0a149b09cdb2d6868125098bd4b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:18.065015Z","signature_b64":"/FqJMsDzVVzy5XWdfjD3f8FurpjJya5r8T1+/2Oe9/tN3tTivUf53/BVNC9oRElES1UMfK28wJ9FOHAhG3+NBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c2c47f4bd992196e8993c5861079884e588a0af632633e510b48d6565fa0e63","last_reissued_at":"2026-07-05T08:26:18.064535Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:18.064535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DITTO: Diffusion Inference-Time T-Optimization for Music Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Julian McAuley, Nicholas J. Bryan, Taylor Berg-Kirkpatrick, Zachary Novack","submitted_at":"2024-01-22T18:10:10Z","abstract_excerpt":"We propose Diffusion Inference-Time T-Optimization (DITTO), a general-purpose frame-work for controlling pre-trained text-to-music diffusion models at inference-time via optimizing initial noise latents. Our method can be used to optimize through any differentiable feature matching loss to achieve a target (stylized) output and leverages gradient checkpointing for memory efficiency. We demonstrate a surprisingly wide-range of applications for music generation including inpainting, outpainting, and looping as well as intensity, melody, and musical structure control - all without ever fine-tunin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12179","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/2401.12179/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":"2401.12179","created_at":"2026-07-05T08:26:18.064593+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.12179v2","created_at":"2026-07-05T08:26:18.064593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12179","created_at":"2026-07-05T08:26:18.064593+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQWEP5F5TEQZ","created_at":"2026-07-05T08:26:18.064593+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQWEP5F5TEQZN2EZ","created_at":"2026-07-05T08:26:18.064593+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQWEP5F5","created_at":"2026-07-05T08:26:18.064593+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2501.09732","citing_title":"Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17986","citing_title":"Latent Fourier Transform","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07253","citing_title":"LENS: Low-Frequency Eigen Noise Shaping for Efficient Diffusion Sampling","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DQWEP5F5TEQZN2EZHRMGCB4YQT","json":"https://pith.science/pith/DQWEP5F5TEQZN2EZHRMGCB4YQT.json","graph_json":"https://pith.science/api/pith-number/DQWEP5F5TEQZN2EZHRMGCB4YQT/graph.json","events_json":"https://pith.science/api/pith-number/DQWEP5F5TEQZN2EZHRMGCB4YQT/events.json","paper":"https://pith.science/paper/DQWEP5F5"},"agent_actions":{"view_html":"https://pith.science/pith/DQWEP5F5TEQZN2EZHRMGCB4YQT","download_json":"https://pith.science/pith/DQWEP5F5TEQZN2EZHRMGCB4YQT.json","view_paper":"https://pith.science/paper/DQWEP5F5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.12179&json=true","fetch_graph":"https://pith.science/api/pith-number/DQWEP5F5TEQZN2EZHRMGCB4YQT/graph.json","fetch_events":"https://pith.science/api/pith-number/DQWEP5F5TEQZN2EZHRMGCB4YQT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQWEP5F5TEQZN2EZHRMGCB4YQT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQWEP5F5TEQZN2EZHRMGCB4YQT/action/storage_attestation","attest_author":"https://pith.science/pith/DQWEP5F5TEQZN2EZHRMGCB4YQT/action/author_attestation","sign_citation":"https://pith.science/pith/DQWEP5F5TEQZN2EZHRMGCB4YQT/action/citation_signature","submit_replication":"https://pith.science/pith/DQWEP5F5TEQZN2EZHRMGCB4YQT/action/replication_record"}},"created_at":"2026-07-05T08:26:18.064593+00:00","updated_at":"2026-07-05T08:26:18.064593+00:00"}