{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZS3O5LMH2GEJU6J575TBK2Q22K","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":"5a988d4837a35569a8243bb0361f4768d1921719bdd3e48b1884355d8813fdb4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T08:00:20Z","title_canon_sha256":"57c679ab75ae40afa5bb877e5b5de7473abe21746dc007f89dc0a45fccd45602"},"schema_version":"1.0","source":{"id":"2411.15247","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.15247","created_at":"2026-07-05T10:28:26Z"},{"alias_kind":"arxiv_version","alias_value":"2411.15247v3","created_at":"2026-07-05T10:28:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15247","created_at":"2026-07-05T10:28:26Z"},{"alias_kind":"pith_short_12","alias_value":"ZS3O5LMH2GEJ","created_at":"2026-07-05T10:28:26Z"},{"alias_kind":"pith_short_16","alias_value":"ZS3O5LMH2GEJU6J5","created_at":"2026-07-05T10:28:26Z"},{"alias_kind":"pith_short_8","alias_value":"ZS3O5LMH","created_at":"2026-07-05T10:28:26Z"}],"graph_snapshots":[{"event_id":"sha256:9d6e9d48b82880b40e0f6c57428048111cdf6eb43d729749a01f498970e71eda","target":"graph","created_at":"2026-07-05T10:28:26Z","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/2411.15247/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent research has shown that fine-tuning diffusion models (DMs) with arbitrary rewards, including non-differentiable ones, is feasible with reinforcement learning (RL) techniques, enabling flexible model alignment. However, applying existing RL methods to step-distilled DMs is challenging for ultra-fast ($\\le2$-step) image generation. Our analysis suggests several limitations of policy-based RL methods such as PPO or DPO toward this goal. Based on the insights, we propose fine-tuning DMs with learned differentiable surrogate rewards. Our method, named LaSRO, learns surrogate reward models in","authors_text":"Gengdai Liu, Huixi Zhao, Yuesong Nan, Zhiwei Jia","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T08:00:20Z","title":"Reward Fine-Tuning Two-Step Diffusion Models via Learning Differentiable Latent-Space Surrogate Reward"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15247","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":"sha256:43697c6cdb6245576ae13f59cf39ac9e77cc73e9ab8d856ee5522f8b5b49c3da","target":"record","created_at":"2026-07-05T10:28:26Z","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":"5a988d4837a35569a8243bb0361f4768d1921719bdd3e48b1884355d8813fdb4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T08:00:20Z","title_canon_sha256":"57c679ab75ae40afa5bb877e5b5de7473abe21746dc007f89dc0a45fccd45602"},"schema_version":"1.0","source":{"id":"2411.15247","kind":"arxiv","version":3}},"canonical_sha256":"ccb6eead87d1889a793dff66156a1ad2b65fc36c431eb9cae9f90964bf31b990","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ccb6eead87d1889a793dff66156a1ad2b65fc36c431eb9cae9f90964bf31b990","first_computed_at":"2026-07-05T10:28:26.799288Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:28:26.799288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eKEoHr8DtHfUf80AIFCEZW4Mg5Tejs4igffb3cpxqHwhIn7IyrsKewn1diqpiOzn3f/zQgoa80wKxLvkTuFiDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:28:26.799794Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.15247","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43697c6cdb6245576ae13f59cf39ac9e77cc73e9ab8d856ee5522f8b5b49c3da","sha256:9d6e9d48b82880b40e0f6c57428048111cdf6eb43d729749a01f498970e71eda"],"state_sha256":"a0e82b67a9d0b27a0943d65fd7caf0558c552cfe331f07e5036e8fa4b81ca8d9"}