{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TUNFEOYD5WP7USROPGTMHUT2AW","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":"0c65467f4baa5ec60f1a3d29baa798c692bec3b317cc86f206aa884e82510acd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-19T04:23:10Z","title_canon_sha256":"3a62fcb02a459336c7f917afce6ed3051a4af31757fc52e471f8890526a89b01"},"schema_version":"1.0","source":{"id":"2606.21086","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21086","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21086v1","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21086","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"pith_short_12","alias_value":"TUNFEOYD5WP7","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"pith_short_16","alias_value":"TUNFEOYD5WP7USRO","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"pith_short_8","alias_value":"TUNFEOYD","created_at":"2026-06-23T01:12:29Z"}],"graph_snapshots":[{"event_id":"sha256:0beed8830cda04a691db345ddd86ec570bad7c2f17715850fd8b419b556f2b31","target":"graph","created_at":"2026-06-23T01:12:29Z","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/2606.21086/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Reflow-regularized Flow Matching Policy Gradients (ReFPO), a simple online RL method that adds explicit Reflow regularization to FPO for efficient flow-based control. We uncover a key structural property: the gradient updates in Flow Matching Policy Gradients (FPO) can be interpreted as an implicit advantage-weighted Reflow process, providing a new geometric perspective on flow-based policy gradients. Building on this insight, ReFPO introduces an explicit geometric regularizer that can be implemented with a single line of code change without incurring additional computational overhe","authors_text":"Chengsi Yao, Fan Feng, Ge Wang, Honghao Cai, Jiahao Yang, Jinke Ren, Shenhao Yan, Shuguang Cui, Xi Li, Yatong Han, Yibo Peng, Yiming Zhao, Zhen Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-19T04:23:10Z","title":"ReFPO: Reflow Regularization for Flow Matching Policy Gradients"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21086","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:bd16c14678d74a7b50db6de51bffb98e86fde6de87dff846fbbd17a8ee5fa042","target":"record","created_at":"2026-06-23T01:12:29Z","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":"0c65467f4baa5ec60f1a3d29baa798c692bec3b317cc86f206aa884e82510acd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-19T04:23:10Z","title_canon_sha256":"3a62fcb02a459336c7f917afce6ed3051a4af31757fc52e471f8890526a89b01"},"schema_version":"1.0","source":{"id":"2606.21086","kind":"arxiv","version":1}},"canonical_sha256":"9d1a523b03ed9ffa4a2e79a6c3d27a059d46ac7875bb4dca775908bbc3302788","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d1a523b03ed9ffa4a2e79a6c3d27a059d46ac7875bb4dca775908bbc3302788","first_computed_at":"2026-06-23T01:12:29.378871Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:12:29.378871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7C1IzDWnrpsHd4TE0tR7eGySEj+yYAS47cf9UN0hKMFssgvNNAlvxsJvHLvRXTol7pZzVkrUukLjp9kOnF6yCA==","signature_status":"signed_v1","signed_at":"2026-06-23T01:12:29.379389Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.21086","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd16c14678d74a7b50db6de51bffb98e86fde6de87dff846fbbd17a8ee5fa042","sha256:0beed8830cda04a691db345ddd86ec570bad7c2f17715850fd8b419b556f2b31"],"state_sha256":"af6ffddf13a87b71b6961291995a2578ffc73c05654cba1f75a939019f5cb071"}