{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DXUKLRVWW4EK7B5JSNWDH7POJH","short_pith_number":"pith:DXUKLRVW","schema_version":"1.0","canonical_sha256":"1de8a5c6b6b708af87a9936c33fdee49f923ce2e3f3159f36de97f4314c3acc9","source":{"kind":"arxiv","id":"2412.18164","version":4},"attestation_state":"computed","paper":{"title":"Stochastic Control for Fine-tuning Diffusion Models: Optimality, Regularity, and Convergence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Meisam Razaviyayn, Renyuan Xu, Yinbin Han","submitted_at":"2024-12-24T04:55:46Z","abstract_excerpt":"Diffusion models have emerged as powerful tools for generative modeling, demonstrating exceptional capability in capturing target data distributions from large datasets. However, fine-tuning these massive models for specific downstream tasks, constraints, and human preferences remains a critical challenge. While recent advances have leveraged reinforcement learning algorithms to tackle this problem, much of the progress has been empirical, with limited theoretical understanding. To bridge this gap, we propose a stochastic control framework for fine-tuning diffusion models. Building on denoisin"},"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":"2412.18164","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-24T04:55:46Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"5fad00402e81f217a1bfe5f27dcc636c7210a143b2f2a0d9ec6a696840b53b6c","abstract_canon_sha256":"647a0d75664c10769ab9de0c669745628c364a5d118a930cbe45e3b05f2f7298"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:20.317202Z","signature_b64":"Ce9luZg+uHI437Ixac5AJaQ8FsNKzrnkzpJgsiWaBgvMVtn3dmdXOF0S6qv3Pcbd7DRRBT9sl97MFPwbwfOIBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1de8a5c6b6b708af87a9936c33fdee49f923ce2e3f3159f36de97f4314c3acc9","last_reissued_at":"2026-07-05T12:01:20.316680Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:20.316680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Control for Fine-tuning Diffusion Models: Optimality, Regularity, and Convergence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Meisam Razaviyayn, Renyuan Xu, Yinbin Han","submitted_at":"2024-12-24T04:55:46Z","abstract_excerpt":"Diffusion models have emerged as powerful tools for generative modeling, demonstrating exceptional capability in capturing target data distributions from large datasets. However, fine-tuning these massive models for specific downstream tasks, constraints, and human preferences remains a critical challenge. While recent advances have leveraged reinforcement learning algorithms to tackle this problem, much of the progress has been empirical, with limited theoretical understanding. To bridge this gap, we propose a stochastic control framework for fine-tuning diffusion models. Building on denoisin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18164","kind":"arxiv","version":4},"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/2412.18164/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":"2412.18164","created_at":"2026-07-05T12:01:20.316743+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18164v4","created_at":"2026-07-05T12:01:20.316743+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18164","created_at":"2026-07-05T12:01:20.316743+00:00"},{"alias_kind":"pith_short_12","alias_value":"DXUKLRVWW4EK","created_at":"2026-07-05T12:01:20.316743+00:00"},{"alias_kind":"pith_short_16","alias_value":"DXUKLRVWW4EK7B5J","created_at":"2026-07-05T12:01:20.316743+00:00"},{"alias_kind":"pith_short_8","alias_value":"DXUKLRVW","created_at":"2026-07-05T12:01:20.316743+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.04297","citing_title":"Statistical guarantees for continuous-time policy evaluation: blessing of ellipticity and new tradeoffs","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DXUKLRVWW4EK7B5JSNWDH7POJH","json":"https://pith.science/pith/DXUKLRVWW4EK7B5JSNWDH7POJH.json","graph_json":"https://pith.science/api/pith-number/DXUKLRVWW4EK7B5JSNWDH7POJH/graph.json","events_json":"https://pith.science/api/pith-number/DXUKLRVWW4EK7B5JSNWDH7POJH/events.json","paper":"https://pith.science/paper/DXUKLRVW"},"agent_actions":{"view_html":"https://pith.science/pith/DXUKLRVWW4EK7B5JSNWDH7POJH","download_json":"https://pith.science/pith/DXUKLRVWW4EK7B5JSNWDH7POJH.json","view_paper":"https://pith.science/paper/DXUKLRVW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18164&json=true","fetch_graph":"https://pith.science/api/pith-number/DXUKLRVWW4EK7B5JSNWDH7POJH/graph.json","fetch_events":"https://pith.science/api/pith-number/DXUKLRVWW4EK7B5JSNWDH7POJH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DXUKLRVWW4EK7B5JSNWDH7POJH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DXUKLRVWW4EK7B5JSNWDH7POJH/action/storage_attestation","attest_author":"https://pith.science/pith/DXUKLRVWW4EK7B5JSNWDH7POJH/action/author_attestation","sign_citation":"https://pith.science/pith/DXUKLRVWW4EK7B5JSNWDH7POJH/action/citation_signature","submit_replication":"https://pith.science/pith/DXUKLRVWW4EK7B5JSNWDH7POJH/action/replication_record"}},"created_at":"2026-07-05T12:01:20.316743+00:00","updated_at":"2026-07-05T12:01:20.316743+00:00"}