{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JTRISRMIVRMQX5FVCFONSCRAKT","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":"331b1da967c7eaa27564e6c695ae797782800c77cff0fcf744b8f91dc567acdf","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-15T10:53:35Z","title_canon_sha256":"c33b704796eef14919c56f2050870a3a0b6229d17e4ef3893554027d5498b968"},"schema_version":"1.0","source":{"id":"2506.12811","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12811","created_at":"2026-07-05T11:22:00Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12811v1","created_at":"2026-07-05T11:22:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12811","created_at":"2026-07-05T11:22:00Z"},{"alias_kind":"pith_short_12","alias_value":"JTRISRMIVRMQ","created_at":"2026-07-05T11:22:00Z"},{"alias_kind":"pith_short_16","alias_value":"JTRISRMIVRMQX5FV","created_at":"2026-07-05T11:22:00Z"},{"alias_kind":"pith_short_8","alias_value":"JTRISRMI","created_at":"2026-07-05T11:22:00Z"}],"graph_snapshots":[{"event_id":"sha256:647247fa2011e2bb3bd57d87bb1e5b029ccb4bf57e2bb0dda4a844b668879993","target":"graph","created_at":"2026-07-05T11:22:00Z","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/2506.12811/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present \\textbf{FlowRL}, a novel framework for online reinforcement learning that integrates flow-based policy representation with Wasserstein-2-regularized optimization. We argue that in addition to training signals, enhancing the expressiveness of the policy class is crucial for the performance gains in RL. Flow-based generative models offer such potential, excelling at capturing complex, multimodal action distributions. However, their direct application in online RL is challenging due to a fundamental objective mismatch: standard flow training optimizes for static data imitation, while R","authors_text":"Fuchun Sun, Jiafeng Xu, Lei Lv, Tao Kong, Xiao Ma, Yu Luo, Yunfei Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-15T10:53:35Z","title":"Flow-Based Policy for Online Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12811","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":"sha256:793e22a58af5ba8c44a578f63b7da4afe0588a84dd0d56a72818db7dd4802f61","target":"record","created_at":"2026-07-05T11:22:00Z","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":"331b1da967c7eaa27564e6c695ae797782800c77cff0fcf744b8f91dc567acdf","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-15T10:53:35Z","title_canon_sha256":"c33b704796eef14919c56f2050870a3a0b6229d17e4ef3893554027d5498b968"},"schema_version":"1.0","source":{"id":"2506.12811","kind":"arxiv","version":1}},"canonical_sha256":"4ce2894588ac590bf4b5115cd90a2054fc09d8c2d83f35223f52dad251433278","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ce2894588ac590bf4b5115cd90a2054fc09d8c2d83f35223f52dad251433278","first_computed_at":"2026-07-05T11:22:00.639785Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:00.639785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9ux7FGgp5KKBW21e6brxlwf3Aasl0tww7xSQBASSRZeP25cJ91ih90Pjv1HP5Ins2LMhVbN1OgmiqdFQCywOAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:00.640255Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.12811","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:793e22a58af5ba8c44a578f63b7da4afe0588a84dd0d56a72818db7dd4802f61","sha256:647247fa2011e2bb3bd57d87bb1e5b029ccb4bf57e2bb0dda4a844b668879993"],"state_sha256":"22baebc5c8715cca95dff19b8f774e205578517aa5e77e708040fe5e6adae538"}