{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T6DQ2IZF422BR6BQ3SYSF7RNFJ","short_pith_number":"pith:T6DQ2IZF","schema_version":"1.0","canonical_sha256":"9f870d2325e6b418f830dcb122fe2d2a4cc910af5a73310cd00f5ba4ed2a975d","source":{"kind":"arxiv","id":"2404.14743","version":2},"attestation_state":"computed","paper":{"title":"Gradient Guidance for Diffusion Models: An Optimization Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Hui Yuan, Mengdi Wang, Minshuo Chen, Yingqing Guo, Yukang Yang","submitted_at":"2024-04-23T04:51:02Z","abstract_excerpt":"Diffusion models have demonstrated empirical successes in various applications and can be adapted to task-specific needs via guidance. This paper studies a form of gradient guidance for adapting a pre-trained diffusion model towards optimizing user-specified objectives. We establish a mathematical framework for guided diffusion to systematically study its optimization theory and algorithmic design. Our theoretical analysis spots a strong link between guided diffusion models and optimization: gradient-guided diffusion models are essentially sampling solutions to a regularized optimization probl"},"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":"2404.14743","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-04-23T04:51:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a01c4a40ae5c369fa717857d5cb72dfa5ee1e80e014e2020b62f26785de587a4","abstract_canon_sha256":"893af19b7e6e139225a3e4d8ecc798bb806c287c32836adb418256e9fd2a7ced"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:03.811449Z","signature_b64":"EuOEGc8aaW1L05gjPZ5Ir8Iq4T5O5LzLrrTTDLlbP4NnDD4sgboDIgbTug6Y1lqwFpWiyps5k5jdeiFdcE+IDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f870d2325e6b418f830dcb122fe2d2a4cc910af5a73310cd00f5ba4ed2a975d","last_reissued_at":"2026-07-05T09:21:03.810945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:03.810945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradient Guidance for Diffusion Models: An Optimization Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Hui Yuan, Mengdi Wang, Minshuo Chen, Yingqing Guo, Yukang Yang","submitted_at":"2024-04-23T04:51:02Z","abstract_excerpt":"Diffusion models have demonstrated empirical successes in various applications and can be adapted to task-specific needs via guidance. This paper studies a form of gradient guidance for adapting a pre-trained diffusion model towards optimizing user-specified objectives. We establish a mathematical framework for guided diffusion to systematically study its optimization theory and algorithmic design. Our theoretical analysis spots a strong link between guided diffusion models and optimization: gradient-guided diffusion models are essentially sampling solutions to a regularized optimization probl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.14743","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/2404.14743/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":"2404.14743","created_at":"2026-07-05T09:21:03.811007+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.14743v2","created_at":"2026-07-05T09:21:03.811007+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.14743","created_at":"2026-07-05T09:21:03.811007+00:00"},{"alias_kind":"pith_short_12","alias_value":"T6DQ2IZF422B","created_at":"2026-07-05T09:21:03.811007+00:00"},{"alias_kind":"pith_short_16","alias_value":"T6DQ2IZF422BR6BQ","created_at":"2026-07-05T09:21:03.811007+00:00"},{"alias_kind":"pith_short_8","alias_value":"T6DQ2IZF","created_at":"2026-07-05T09:21:03.811007+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01628","citing_title":"Demystifying Multimodal Biomolecular Co-design With Intrinsic Geodesic Coupling","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2411.13443","citing_title":"Nonlinear Assimilation via Score-based Sequential Langevin Sampling","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2505.15809","citing_title":"MMaDA: Multimodal Large Diffusion Language Models","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2412.06264","citing_title":"Flow Matching Guide and Code","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T6DQ2IZF422BR6BQ3SYSF7RNFJ","json":"https://pith.science/pith/T6DQ2IZF422BR6BQ3SYSF7RNFJ.json","graph_json":"https://pith.science/api/pith-number/T6DQ2IZF422BR6BQ3SYSF7RNFJ/graph.json","events_json":"https://pith.science/api/pith-number/T6DQ2IZF422BR6BQ3SYSF7RNFJ/events.json","paper":"https://pith.science/paper/T6DQ2IZF"},"agent_actions":{"view_html":"https://pith.science/pith/T6DQ2IZF422BR6BQ3SYSF7RNFJ","download_json":"https://pith.science/pith/T6DQ2IZF422BR6BQ3SYSF7RNFJ.json","view_paper":"https://pith.science/paper/T6DQ2IZF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.14743&json=true","fetch_graph":"https://pith.science/api/pith-number/T6DQ2IZF422BR6BQ3SYSF7RNFJ/graph.json","fetch_events":"https://pith.science/api/pith-number/T6DQ2IZF422BR6BQ3SYSF7RNFJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T6DQ2IZF422BR6BQ3SYSF7RNFJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T6DQ2IZF422BR6BQ3SYSF7RNFJ/action/storage_attestation","attest_author":"https://pith.science/pith/T6DQ2IZF422BR6BQ3SYSF7RNFJ/action/author_attestation","sign_citation":"https://pith.science/pith/T6DQ2IZF422BR6BQ3SYSF7RNFJ/action/citation_signature","submit_replication":"https://pith.science/pith/T6DQ2IZF422BR6BQ3SYSF7RNFJ/action/replication_record"}},"created_at":"2026-07-05T09:21:03.811007+00:00","updated_at":"2026-07-05T09:21:03.811007+00:00"}