{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XMD5YC5PVLLJ2SQNWOVCZ4TJFU","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":"7ba8f3cfc2c8f70596a1c781f0239d67472462b78cfbc0027c0bf8ca733e2104","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-04T15:36:42Z","title_canon_sha256":"cb2c90a5aeb9c3df9aa52ad73b058f979ef8fb140fbd0f9281cc6c91ebe82503"},"schema_version":"1.0","source":{"id":"2602.04663","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.04663","created_at":"2026-05-20T01:05:08Z"},{"alias_kind":"arxiv_version","alias_value":"2602.04663v2","created_at":"2026-05-20T01:05:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.04663","created_at":"2026-05-20T01:05:08Z"},{"alias_kind":"pith_short_12","alias_value":"XMD5YC5PVLLJ","created_at":"2026-05-20T01:05:08Z"},{"alias_kind":"pith_short_16","alias_value":"XMD5YC5PVLLJ2SQN","created_at":"2026-05-20T01:05:08Z"},{"alias_kind":"pith_short_8","alias_value":"XMD5YC5P","created_at":"2026-05-20T01:05:08Z"}],"graph_snapshots":[{"event_id":"sha256:4c50308e83096df99f7dcf6c796370c991a3de9444362682a681bca766d96934","target":"graph","created_at":"2026-05-20T01:05:08Z","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/2602.04663/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning has been widely applied to diffusion and flow models for visual tasks such as text-to-image generation. However, these tasks remain challenging because diffusion models have intractable likelihoods, which creates a barrier for directly applying popular policy-gradient type methods. Existing approaches primarily focus on crafting new objectives built on already heavily engineered LLM objectives, using ad hoc estimators for likelihood, without a thorough investigation into how such estimation affects overall algorithmic performance. In this work, we provide a systematic an","authors_text":"Bo Yuan, Jaemoo Choi, Jinbin Bai, Molei Tao, Petr Molodyk, Wei Guo, Yi Xin, Yongxin Chen, Yuchen Zhu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-04T15:36:42Z","title":"Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.04663","kind":"arxiv","version":2},"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:ea3d485ac8df62586be5e4f10332311934eaa0bb254874e33b7c54d43c0e1241","target":"record","created_at":"2026-05-20T01:05:08Z","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":"7ba8f3cfc2c8f70596a1c781f0239d67472462b78cfbc0027c0bf8ca733e2104","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-04T15:36:42Z","title_canon_sha256":"cb2c90a5aeb9c3df9aa52ad73b058f979ef8fb140fbd0f9281cc6c91ebe82503"},"schema_version":"1.0","source":{"id":"2602.04663","kind":"arxiv","version":2}},"canonical_sha256":"bb07dc0bafaad69d4a0db3aa2cf2692d1c92cc5f32433d278f7b75d9dd4549ef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb07dc0bafaad69d4a0db3aa2cf2692d1c92cc5f32433d278f7b75d9dd4549ef","first_computed_at":"2026-05-20T01:05:08.134258Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:05:08.134258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/2OZb/OAMwaDpgYsAXLsWHs4AlxJMfoRw8wS6OXM09Iea2e1NLq9QKuQ9Lbub8uOD1aFrQezPxJ6ZmNOuMn8Aw==","signature_status":"signed_v1","signed_at":"2026-05-20T01:05:08.135084Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.04663","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea3d485ac8df62586be5e4f10332311934eaa0bb254874e33b7c54d43c0e1241","sha256:4c50308e83096df99f7dcf6c796370c991a3de9444362682a681bca766d96934"],"state_sha256":"f0beac9a98839f1883674adbe391842ab6b7f5931338444956d6233c651f4d8e"}