{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:C2VXO4EE6JR32ODIIG4YIO5P7J","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":"4047d15108e4d78d2dee5a2b0198f90faa8fbae61d4e25206beda64f9f47f2b4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T15:59:57Z","title_canon_sha256":"c35321476b2f6ae9dbd23462ba0a4ab321d238d164a50cf6eef0d13d9a9e3ae2"},"schema_version":"1.0","source":{"id":"2606.11025","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.11025","created_at":"2026-06-10T01:11:04Z"},{"alias_kind":"arxiv_version","alias_value":"2606.11025v1","created_at":"2026-06-10T01:11:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11025","created_at":"2026-06-10T01:11:04Z"},{"alias_kind":"pith_short_12","alias_value":"C2VXO4EE6JR3","created_at":"2026-06-10T01:11:04Z"},{"alias_kind":"pith_short_16","alias_value":"C2VXO4EE6JR32ODI","created_at":"2026-06-10T01:11:04Z"},{"alias_kind":"pith_short_8","alias_value":"C2VXO4EE","created_at":"2026-06-10T01:11:04Z"}],"graph_snapshots":[{"event_id":"sha256:54713611b9f600d7ad40e45b93648c65db70e8f1d52e3df86ad34326e398de4d","target":"graph","created_at":"2026-06-10T01:11:04Z","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/2606.11025/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work has demonstrated that online reinforcement learning (RL) can substantially improve the quality and alignment of flow matching models for image and video generation. Methods such as Flow-GRPO and CPS cast the denoising process as a Markov Decision Process and apply PPO-style ratio clipping to enforce a trust region. However, we argue that ratio clipping is structurally ill-suited for flow models: the probability ratio between new and old policies is a noisy, single-sample estimate of the true policy divergence, leading to over-constraining in some regions of the trajectory and under","authors_text":"Bowen Ping, Liefeng Bo, Minnan Luo, Penghui Qi, Tianyu Pang, Xiangxin Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T15:59:57Z","title":"Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11025","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":"sha256:8344ac5ed54e96d52bff7d48ea3731a35789a6c4557db05d857ae4392a0d21d4","target":"record","created_at":"2026-06-10T01:11:04Z","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":"4047d15108e4d78d2dee5a2b0198f90faa8fbae61d4e25206beda64f9f47f2b4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T15:59:57Z","title_canon_sha256":"c35321476b2f6ae9dbd23462ba0a4ab321d238d164a50cf6eef0d13d9a9e3ae2"},"schema_version":"1.0","source":{"id":"2606.11025","kind":"arxiv","version":1}},"canonical_sha256":"16ab777084f263bd386841b9843baffa473ce613f320d5791b688526e12d0fe9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"16ab777084f263bd386841b9843baffa473ce613f320d5791b688526e12d0fe9","first_computed_at":"2026-06-10T01:11:04.376074Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:11:04.376074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I37G9v/0MEpnd3/opQYg9cb13P2PZIL0xgQHIom5eDANacnRVEoON2ik/6YVk5Je3S8U2EypuihttaaC9EDqBA==","signature_status":"signed_v1","signed_at":"2026-06-10T01:11:04.376925Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.11025","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8344ac5ed54e96d52bff7d48ea3731a35789a6c4557db05d857ae4392a0d21d4","sha256:54713611b9f600d7ad40e45b93648c65db70e8f1d52e3df86ad34326e398de4d"],"state_sha256":"5d7babf08df2117552d7b87196025bcf2ad766d9351ad6252c3c9ed9083a6960"}