{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EO63BI7RVRSQA7CUSM72GTAXP7","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":"71ccc7f01fe7f8c5436e963a1569c05f61e011797a60149febffe0803286d98c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T17:59:21Z","title_canon_sha256":"5ae12131a73adbcc70e1f2aa922f7b8dcc78f8d95a90f02b23a8fc51ebc21180"},"schema_version":"1.0","source":{"id":"2605.26108","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26108","created_at":"2026-05-26T03:05:24Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26108v1","created_at":"2026-05-26T03:05:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26108","created_at":"2026-05-26T03:05:24Z"},{"alias_kind":"pith_short_12","alias_value":"EO63BI7RVRSQ","created_at":"2026-05-26T03:05:24Z"},{"alias_kind":"pith_short_16","alias_value":"EO63BI7RVRSQA7CU","created_at":"2026-05-26T03:05:24Z"},{"alias_kind":"pith_short_8","alias_value":"EO63BI7R","created_at":"2026-05-26T03:05:24Z"}],"graph_snapshots":[{"event_id":"sha256:1c0a3030e932556edd5754c80c634729b6853e57e53961b4d56378865c37f5b8","target":"graph","created_at":"2026-05-26T03:05:24Z","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/2605.26108/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in few-step diffusion distillation have enabled efficient image generation, yet aligning these models with human preferences remains challenging. We propose Reward-Tilted Distribution Matching Distillation (RTDMD), a two-stage framework that unifies distribution matching distillation with reward-guided reinforcement learning for few-step flow generators. We show that minimizing the KL divergence to a reward-tilted teacher distribution naturally decomposes into a distribution matching term and a reward maximization term. In the first stage, we introduce Ambient-Consistent Distri","authors_text":"Chi Zhang, Jun Zhang, Ruoyu Wang, Tianyu Pang, Xiangxin Zhou, Yushi Huang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T17:59:21Z","title":"Reinforcing Few-step Generators via Reward-Tilted Distribution Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26108","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":"sha256:7f76e129d8e61c7d266974083d4eea300a49181189ff7b8f15bf416a5d0de3d5","target":"record","created_at":"2026-05-26T03:05:24Z","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":"71ccc7f01fe7f8c5436e963a1569c05f61e011797a60149febffe0803286d98c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T17:59:21Z","title_canon_sha256":"5ae12131a73adbcc70e1f2aa922f7b8dcc78f8d95a90f02b23a8fc51ebc21180"},"schema_version":"1.0","source":{"id":"2605.26108","kind":"arxiv","version":1}},"canonical_sha256":"23bdb0a3f1ac65007c54933fa34c177fe2a6b6407b780c9ba03e84fdc32737e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23bdb0a3f1ac65007c54933fa34c177fe2a6b6407b780c9ba03e84fdc32737e5","first_computed_at":"2026-05-26T03:05:24.493686Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T03:05:24.493686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l9VXVq7LVmypRv4u87MmfEn9ED+CR3BbmzBd5jGDaBRjgIO0ot14hw0/h61T8QmyGplXGuOhtRBwkiFDoI5vCg==","signature_status":"signed_v1","signed_at":"2026-05-26T03:05:24.494707Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.26108","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f76e129d8e61c7d266974083d4eea300a49181189ff7b8f15bf416a5d0de3d5","sha256:1c0a3030e932556edd5754c80c634729b6853e57e53961b4d56378865c37f5b8"],"state_sha256":"e7c81935e10f33330cd38857eb0b13c7efc3ac5a5a2d3524f83fa29a5b50085f"}