{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BQRKYGZPTMCHFEQURWNZ5IDSRN","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":"55a5ca6d7dc458c08056ab7f9e661a260b16217442ef7248034d0629b593b803","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-12T21:12:21Z","title_canon_sha256":"47c507b5ce44b15c3c74d7ca1ab5f36ee5960d4d4c5a2a1d5a77a828e90ff647"},"schema_version":"1.0","source":{"id":"2409.08400","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.08400","created_at":"2026-07-05T09:06:30Z"},{"alias_kind":"arxiv_version","alias_value":"2409.08400v1","created_at":"2026-07-05T09:06:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08400","created_at":"2026-07-05T09:06:30Z"},{"alias_kind":"pith_short_12","alias_value":"BQRKYGZPTMCH","created_at":"2026-07-05T09:06:30Z"},{"alias_kind":"pith_short_16","alias_value":"BQRKYGZPTMCHFEQU","created_at":"2026-07-05T09:06:30Z"},{"alias_kind":"pith_short_8","alias_value":"BQRKYGZP","created_at":"2026-07-05T09:06:30Z"}],"graph_snapshots":[{"event_id":"sha256:779255b0fb9133793b2982af6a956eb2b4a0f0b6d2bf6c33dbe4e3e599998da2","target":"graph","created_at":"2026-07-05T09:06:30Z","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/2409.08400/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning from human feedback (RLHF) has been shown a promising direction for aligning generative models with human intent and has also been explored in recent works for alignment of diffusion generative models. In this work, we provide a rigorous treatment by formulating the task of fine-tuning diffusion models, with reward functions learned from human feedback, as an exploratory continuous-time stochastic control problem. Our key idea lies in treating the score-matching functions as controls/actions, and upon this, we develop a unified framework from a continuous-time perspectiv","authors_text":"David D. Yao, Hanyang Zhao, Haoxian Chen, Ji Zhang, Wenpin Tang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-12T21:12:21Z","title":"Scores as Actions: a framework of fine-tuning diffusion models by continuous-time reinforcement learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08400","kind":"arxiv","version":1},"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:ba933b2dc91cb7ca4ec19a1030d184334eaa53de77649cf8e2b3fdf52b4e9bb2","target":"record","created_at":"2026-07-05T09:06:30Z","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":"55a5ca6d7dc458c08056ab7f9e661a260b16217442ef7248034d0629b593b803","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-12T21:12:21Z","title_canon_sha256":"47c507b5ce44b15c3c74d7ca1ab5f36ee5960d4d4c5a2a1d5a77a828e90ff647"},"schema_version":"1.0","source":{"id":"2409.08400","kind":"arxiv","version":1}},"canonical_sha256":"0c22ac1b2f9b047292148d9b9ea0728b53efed9ecf88a7da5f237960e8fe1a08","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c22ac1b2f9b047292148d9b9ea0728b53efed9ecf88a7da5f237960e8fe1a08","first_computed_at":"2026-07-05T09:06:30.569571Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:06:30.569571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O+EMsrFMfMNJbQ6mCWoOmH0TZPKtveeFScBg97LG3gJgFjj+WnuvLHaLNyX3BgdLKk6KqA1P2TckzGKH78/pDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:06:30.570086Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.08400","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba933b2dc91cb7ca4ec19a1030d184334eaa53de77649cf8e2b3fdf52b4e9bb2","sha256:779255b0fb9133793b2982af6a956eb2b4a0f0b6d2bf6c33dbe4e3e599998da2"],"state_sha256":"8da79ccf1a66a87e7b631daef7fc12feb3013ddebdf3793738fb9b70e8688eef"}