{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6XQQV3ODNGDQFHKNRNJIP4ZCE7","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":"4f4ba94cc16ee86bc3aded616e56e26aee11011719517cd34eb4180417ef9371","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T22:20:51Z","title_canon_sha256":"6a6995e87f850c181a2572167533fdb892d9f67b9aa3cbf306bc10e44eeee489"},"schema_version":"1.0","source":{"id":"2605.27736","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27736","created_at":"2026-05-28T01:04:47Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27736v1","created_at":"2026-05-28T01:04:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27736","created_at":"2026-05-28T01:04:47Z"},{"alias_kind":"pith_short_12","alias_value":"6XQQV3ODNGDQ","created_at":"2026-05-28T01:04:47Z"},{"alias_kind":"pith_short_16","alias_value":"6XQQV3ODNGDQFHKN","created_at":"2026-05-28T01:04:47Z"},{"alias_kind":"pith_short_8","alias_value":"6XQQV3OD","created_at":"2026-05-28T01:04:47Z"}],"graph_snapshots":[{"event_id":"sha256:461db089cef2fb06ebe0a4b9615214e25bd5f056818f6aea912aa2117a60e08e","target":"graph","created_at":"2026-05-28T01:04:47Z","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/2605.27736/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Online reinforcement learning is becoming increasingly important for aligning diffusion models with non-differentiable objectives. However, existing methods still face limitations in assigning fine-grained credit along denoising trajectories and in realizing stable value-based optimization. We propose a state-aligned latent actor-critic framework for diffusion post-training, in which the diffusion model serves as its own timestep-conditioned value function and predicts values directly on noisy latent states. This enables trajectory-level PPO training, supports stable actor-critic optimization ","authors_text":"Ceyuan Yang, Qihang Zhang, Zhengyang Liang","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T22:20:51Z","title":"Explicit Critic Guidance for Aligning Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27736","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":"sha256:1ac88c1334315813d5510c7c99a202c4dff7d13e1cdf9e6c3e77ab637412aaba","target":"record","created_at":"2026-05-28T01:04:47Z","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":"4f4ba94cc16ee86bc3aded616e56e26aee11011719517cd34eb4180417ef9371","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T22:20:51Z","title_canon_sha256":"6a6995e87f850c181a2572167533fdb892d9f67b9aa3cbf306bc10e44eeee489"},"schema_version":"1.0","source":{"id":"2605.27736","kind":"arxiv","version":1}},"canonical_sha256":"f5e10aedc36987029d4d8b5287f32227edadbcc2332e90b4b1734fc0f595b83f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5e10aedc36987029d4d8b5287f32227edadbcc2332e90b4b1734fc0f595b83f","first_computed_at":"2026-05-28T01:04:47.564706Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:47.564706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UojY2qIo5WBYJ/KrwsiV+DhtFCckDCVr0874caIbsdCzYZ6TZiRIH1oNEnDg9w+mmIh48LXp0kAq9Fu0vNJOBA==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:47.565079Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.27736","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ac88c1334315813d5510c7c99a202c4dff7d13e1cdf9e6c3e77ab637412aaba","sha256:461db089cef2fb06ebe0a4b9615214e25bd5f056818f6aea912aa2117a60e08e"],"state_sha256":"bfd0dbb13e2858a13123de06628772b79cebd8cf658d26a53d4be35667dcaef8"}