{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BM7BAZZO2IKTG4QGLYJDLPJW5Q","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":"b42f6deec2f9c94828db59afdee3eb81341b708410efe356515a021933c9b75d","cross_cats_sorted":["cs.AI","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-03T20:50:05Z","title_canon_sha256":"8936995aab6ab488306b4d6cbb56b66e7ea9629f3f31afeaa917681d5914f480"},"schema_version":"1.0","source":{"id":"2502.01819","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01819","created_at":"2026-07-05T11:57:20Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01819v3","created_at":"2026-07-05T11:57:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01819","created_at":"2026-07-05T11:57:20Z"},{"alias_kind":"pith_short_12","alias_value":"BM7BAZZO2IKT","created_at":"2026-07-05T11:57:20Z"},{"alias_kind":"pith_short_16","alias_value":"BM7BAZZO2IKTG4QG","created_at":"2026-07-05T11:57:20Z"},{"alias_kind":"pith_short_8","alias_value":"BM7BAZZO","created_at":"2026-07-05T11:57:20Z"}],"graph_snapshots":[{"event_id":"sha256:ae217d1ca0d9afa930bdcc61cdfaa19b758b2d9b657479b7b8c7aa79ceefdfcc","target":"graph","created_at":"2026-07-05T11:57:20Z","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/2502.01819/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning from human feedback (RLHF), which aligns a diffusion model with input prompt, has become a crucial step in building reliable generative AI models. Most works in this area use a discrete-time formulation, which is prone to induced discretization errors, and often not applicable to models with higher-order/black-box solvers. The objective of this study is to develop a disciplined approach to fine-tune diffusion models using continuous-time RL, formulated as a stochastic control problem with a reward function that aligns the end result (terminal state) with input prompt. Th","authors_text":"David D. Yao, Hanyang Zhao, Haoxian Chen, Ji Zhang, Wenpin Tang","cross_cats":["cs.AI","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-03T20:50:05Z","title":"Score as Action: Fine-Tuning Diffusion Generative Models by Continuous-time Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01819","kind":"arxiv","version":3},"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":"sha256:099bbf2daf8b41a1f80db20627ea73cdf420dc22c20f6e870c38651262df06d6","target":"record","created_at":"2026-07-05T11:57:20Z","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":"b42f6deec2f9c94828db59afdee3eb81341b708410efe356515a021933c9b75d","cross_cats_sorted":["cs.AI","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-03T20:50:05Z","title_canon_sha256":"8936995aab6ab488306b4d6cbb56b66e7ea9629f3f31afeaa917681d5914f480"},"schema_version":"1.0","source":{"id":"2502.01819","kind":"arxiv","version":3}},"canonical_sha256":"0b3e10672ed2153372065e1235bd36ec273ee2c2ad6ac8fd199d6590531605df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b3e10672ed2153372065e1235bd36ec273ee2c2ad6ac8fd199d6590531605df","first_computed_at":"2026-07-05T11:57:20.018981Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:57:20.018981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rxJdNL55oq0LfyKQeK9wuOrIpHjFdwiN+EK3fAp1PoBZ606/axWiqmqXzPJEuYHMZeCty46CE/N3N9gvIolpBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:57:20.019479Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.01819","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:099bbf2daf8b41a1f80db20627ea73cdf420dc22c20f6e870c38651262df06d6","sha256:ae217d1ca0d9afa930bdcc61cdfaa19b758b2d9b657479b7b8c7aa79ceefdfcc"],"state_sha256":"a5d5be37e91f9290c89c61508ed6669e2070fa3dff7ade542f2f08e2e93df54b"}