{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZBOFHCM3M6GC3AXSO2NFXVUALM","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":"507b6fa610cd55c2b9fb791d9a9f50b3082ecf69e5463fb1eb3dde3ecde9f9cf","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-28T10:26:19Z","title_canon_sha256":"9c3d1b8b770302ca88be18e97921ad1d38dbe0006ecbfbf52c49c6add27795ab"},"schema_version":"1.0","source":{"id":"2410.20898","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.20898","created_at":"2026-07-05T11:16:30Z"},{"alias_kind":"arxiv_version","alias_value":"2410.20898v3","created_at":"2026-07-05T11:16:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20898","created_at":"2026-07-05T11:16:30Z"},{"alias_kind":"pith_short_12","alias_value":"ZBOFHCM3M6GC","created_at":"2026-07-05T11:16:30Z"},{"alias_kind":"pith_short_16","alias_value":"ZBOFHCM3M6GC3AXS","created_at":"2026-07-05T11:16:30Z"},{"alias_kind":"pith_short_8","alias_value":"ZBOFHCM3","created_at":"2026-07-05T11:16:30Z"}],"graph_snapshots":[{"event_id":"sha256:df8592c0a7e02884d2f44b64e4e28a9c9932700264b39d0e0ce848f879f7ca1c","target":"graph","created_at":"2026-07-05T11:16:30Z","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/2410.20898/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Diff-Instruct* (DI*), a data-efficient post-training approach for one-step text-to-image generative models to improve its human preferences without requiring image data. Our method frames alignment as online reinforcement learning from human feedback (RLHF), which optimizes the one-step model to maximize human reward functions while being regularized to be kept close to a reference diffusion process. Unlike traditional RLHF approaches, which rely on the Kullback-Leibler divergence as the regularization, we introduce a novel general score-based divergence regularization that substant","authors_text":"Colin Zhang, Debing Zhang, Weijian Luo, Zhengyang Geng","cross_cats":["cs.AI","cs.LG","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-28T10:26:19Z","title":"David and Goliath: Small One-step Model Beats Large Diffusion with Score Post-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20898","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:c9078e0d3f6d27fd69f5a1e2f5385e2492ea52293c10563922d4368b3ce01c08","target":"record","created_at":"2026-07-05T11:16:30Z","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":"507b6fa610cd55c2b9fb791d9a9f50b3082ecf69e5463fb1eb3dde3ecde9f9cf","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-28T10:26:19Z","title_canon_sha256":"9c3d1b8b770302ca88be18e97921ad1d38dbe0006ecbfbf52c49c6add27795ab"},"schema_version":"1.0","source":{"id":"2410.20898","kind":"arxiv","version":3}},"canonical_sha256":"c85c53899b678c2d82f2769a5bd6805b215f9b01e3cf7f154d02baa74cc943b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c85c53899b678c2d82f2769a5bd6805b215f9b01e3cf7f154d02baa74cc943b8","first_computed_at":"2026-07-05T11:16:30.241464Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:30.241464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"giPZC9HcmVXK/TAPNkf4k+DNtu+yRjx59kAVtRFLewg9XrsmfKw4M9/PogdMX4FPBhsA2pd+3IQ2nBb05LHDDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:30.242013Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.20898","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c9078e0d3f6d27fd69f5a1e2f5385e2492ea52293c10563922d4368b3ce01c08","sha256:df8592c0a7e02884d2f44b64e4e28a9c9932700264b39d0e0ce848f879f7ca1c"],"state_sha256":"2f8465ac8a5c3abf442b3511424a204a287f8421e635b892963cadf4cb00c471"}