{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FZLZBBCQ4TQ3LXU3TN5DY4RJMO","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":"c89f4ffe584124e775b9f7bc6bb58d023bd9ca0961b5375b711e567aaa6241eb","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-22T08:42:46Z","title_canon_sha256":"40aef761559b411b309bb39e2f24a0374f5a44b7c793db9bdc5e7a47efa41836"},"schema_version":"1.0","source":{"id":"2311.13231","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.13231","created_at":"2026-07-05T07:59:57Z"},{"alias_kind":"arxiv_version","alias_value":"2311.13231v3","created_at":"2026-07-05T07:59:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13231","created_at":"2026-07-05T07:59:57Z"},{"alias_kind":"pith_short_12","alias_value":"FZLZBBCQ4TQ3","created_at":"2026-07-05T07:59:57Z"},{"alias_kind":"pith_short_16","alias_value":"FZLZBBCQ4TQ3LXU3","created_at":"2026-07-05T07:59:57Z"},{"alias_kind":"pith_short_8","alias_value":"FZLZBBCQ","created_at":"2026-07-05T07:59:57Z"}],"graph_snapshots":[{"event_id":"sha256:873f3b8e9c14b74fc31c65126f0b24387c92610644031182b747ec50733fbfb8","target":"graph","created_at":"2026-07-05T07:59:57Z","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/2311.13231/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Using reinforcement learning with human feedback (RLHF) has shown significant promise in fine-tuning diffusion models. Previous methods start by training a reward model that aligns with human preferences, then leverage RL techniques to fine-tune the underlying models. However, crafting an efficient reward model demands extensive datasets, optimal architecture, and manual hyperparameter tuning, making the process both time and cost-intensive. The direct preference optimization (DPO) method, effective in fine-tuning large language models, eliminates the necessity for a reward model. However, the","authors_text":"Chunjiang Ge, Jiafei Lyu, Jian Tao, Jiaxin Chen, Kai Yang, Qimai Li, Weihan Shen, Xiaolong Zhu, Xiu Li","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-22T08:42:46Z","title":"Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13231","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:fc98f0879d8659fde0a1e4df57cfda76024091521f138f2dac16ee2bcde9a818","target":"record","created_at":"2026-07-05T07:59:57Z","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":"c89f4ffe584124e775b9f7bc6bb58d023bd9ca0961b5375b711e567aaa6241eb","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-22T08:42:46Z","title_canon_sha256":"40aef761559b411b309bb39e2f24a0374f5a44b7c793db9bdc5e7a47efa41836"},"schema_version":"1.0","source":{"id":"2311.13231","kind":"arxiv","version":3}},"canonical_sha256":"2e57908450e4e1b5de9b9b7a3c722963928e2b08a3def3ca960b4ce1375400b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e57908450e4e1b5de9b9b7a3c722963928e2b08a3def3ca960b4ce1375400b3","first_computed_at":"2026-07-05T07:59:57.679786Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:59:57.679786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LVG2klJINvZjBAGXnynqZ6SecXiN6RWhCfSAvAwm2gNe3R/v3BU/RKziB5nyHuzhB5/WyNIjcZ1IxCtxAMEvBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:59:57.680280Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.13231","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc98f0879d8659fde0a1e4df57cfda76024091521f138f2dac16ee2bcde9a818","sha256:873f3b8e9c14b74fc31c65126f0b24387c92610644031182b747ec50733fbfb8"],"state_sha256":"4e994c38d39ede3dd67be63f984b11a613903ff36a3f77f6a8cf9aeaa2bb4e26"}