{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CPL3YYIWWBCRUG7KYCTEIOUU7B","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":"1d30d02bc34e3db7ac421cfb1482b2a3541784b5c588010acee555d640e17d0a","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-07T03:41:58Z","title_canon_sha256":"9c8f05a08cfc9831dc319cb1323585d28f0b19a919ed6cd3ceca2e0d96fa70f4"},"schema_version":"1.0","source":{"id":"2608.06768","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.06768","created_at":"2026-08-10T01:11:58Z"},{"alias_kind":"arxiv_version","alias_value":"2608.06768v1","created_at":"2026-08-10T01:11:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06768","created_at":"2026-08-10T01:11:58Z"},{"alias_kind":"pith_short_12","alias_value":"CPL3YYIWWBCR","created_at":"2026-08-10T01:11:58Z"},{"alias_kind":"pith_short_16","alias_value":"CPL3YYIWWBCRUG7K","created_at":"2026-08-10T01:11:58Z"},{"alias_kind":"pith_short_8","alias_value":"CPL3YYIW","created_at":"2026-08-10T01:11:58Z"}],"graph_snapshots":[{"event_id":"sha256:f445350061d72c0d944d20a5a42671e96dd1509996ce062a63e5fbcbfdd285e1","target":"graph","created_at":"2026-08-10T01:11:58Z","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/2608.06768/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models have strong generative capabilities. However, their maximum likelihood training objective only focuses on reconstructing the data distribution, making it difficult to align with specific preferences. Reinforcement learning (RL) for preference alignment in diffusion models is promising but limited by reward sparsity. Since a single reward cannot support optimization, existing RL methods usually backpropagate the final reward to all previous steps. However, denoising is stage-wise, with distinct semantics and controllability. Repeating the final reward across all steps creates a","authors_text":"Jikang Cheng, Ling Liang, Renye Yan, Wei Peng, Yimao Cai, You Wu, Zongwei Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-07T03:41:58Z","title":"Explore or Converge? Stage-Guided Per-Step Optimization for Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06768","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":"sha256:9bb8e58f226e28edbad60b6255ecbeceed406850b1cab3dfefa5d610014ca490","target":"record","created_at":"2026-08-10T01:11:58Z","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":"1d30d02bc34e3db7ac421cfb1482b2a3541784b5c588010acee555d640e17d0a","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-07T03:41:58Z","title_canon_sha256":"9c8f05a08cfc9831dc319cb1323585d28f0b19a919ed6cd3ceca2e0d96fa70f4"},"schema_version":"1.0","source":{"id":"2608.06768","kind":"arxiv","version":1}},"canonical_sha256":"13d7bc6116b0451a1beac0a6443a94f8623a88eb516f082619260a338922ecf3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"13d7bc6116b0451a1beac0a6443a94f8623a88eb516f082619260a338922ecf3","first_computed_at":"2026-08-10T01:11:58.653803Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-10T01:11:58.653803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OpoVKD1LN6PqnhuA+I/5SUm4RibhTwFa/lGgGYEdbS6ubTt6Cm+j8fF/yymeq4DMyPav8HtiEWqv+0JMLL4uAg==","signature_status":"signed_v1","signed_at":"2026-08-10T01:11:58.656752Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.06768","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9bb8e58f226e28edbad60b6255ecbeceed406850b1cab3dfefa5d610014ca490","sha256:f445350061d72c0d944d20a5a42671e96dd1509996ce062a63e5fbcbfdd285e1"],"state_sha256":"5a698f537ca1dca2765aeba5422e394a7ee5a18ca1f8c09986d6930cce2003f2"}