{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4ECJ7NSIJ3CNALBNHGA7R7DWHB","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":"efd205a20d1bf34c551e01d7a7a41c70bc9cc844bd2581c8d070f86f9f6304a2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-03T21:47:43Z","title_canon_sha256":"5c8cbfb9b194c39cc0fba0cd55c3150391b0bcd3310a60beb559b487b0f169f6"},"schema_version":"1.0","source":{"id":"2606.05468","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05468","created_at":"2026-06-05T01:14:52Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05468v1","created_at":"2026-06-05T01:14:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05468","created_at":"2026-06-05T01:14:52Z"},{"alias_kind":"pith_short_12","alias_value":"4ECJ7NSIJ3CN","created_at":"2026-06-05T01:14:52Z"},{"alias_kind":"pith_short_16","alias_value":"4ECJ7NSIJ3CNALBN","created_at":"2026-06-05T01:14:52Z"},{"alias_kind":"pith_short_8","alias_value":"4ECJ7NSI","created_at":"2026-06-05T01:14:52Z"}],"graph_snapshots":[{"event_id":"sha256:ae7977d138d1fca941f9d0ba82a343df7a0f1d0f1c95f92712cf6c21b4cb3248","target":"graph","created_at":"2026-06-05T01:14:52Z","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/2606.05468/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Post-training Vision-Language-Action (VLA) models into policies that can be reliably deployed on real robots remains a major bottleneck. SFT and DAgger exploit failure signals only indirectly, and reward-based RL is bottlenecked by the difficulty of real-world reward design and of training reliable critics. We present FlowPRO, a reward-free offline reinforced fine-tuning framework for flow-matching VLAs. Algorithmically, we propose RPRO (Robotic Flow-matching Proximalized Preference Optimization), a preference-optimization objective tailored to the flow-matching action head of VLA models. RPRO","authors_text":"He Zhang, Junbo Tan, Xueqian Wang, Yihao Wu, Zhengyou Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-03T21:47:43Z","title":"FlowPRO: Reward-Free Reinforced Fine-Tuning of Flow-Matching VLAs via Proximalized Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05468","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:d2a750e512bc7eb0e92bb9bd1010a6725b5f8434e88b2825043f563dde33cd69","target":"record","created_at":"2026-06-05T01:14:52Z","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":"efd205a20d1bf34c551e01d7a7a41c70bc9cc844bd2581c8d070f86f9f6304a2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-03T21:47:43Z","title_canon_sha256":"5c8cbfb9b194c39cc0fba0cd55c3150391b0bcd3310a60beb559b487b0f169f6"},"schema_version":"1.0","source":{"id":"2606.05468","kind":"arxiv","version":1}},"canonical_sha256":"e1049fb6484ec4d02c2d3981f8fc76386f12db46ed31bd15402971b968425532","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1049fb6484ec4d02c2d3981f8fc76386f12db46ed31bd15402971b968425532","first_computed_at":"2026-06-05T01:14:52.087196Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:14:52.087196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N3WTHgiPb+yribs0itnRJg3Ihxy4+PVbKEElqGu8WiZE0YrAh+dTIQu94c7TIGTH0Mdm0UuTlVQ2s7Zi2j5xCA==","signature_status":"signed_v1","signed_at":"2026-06-05T01:14:52.087787Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05468","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2a750e512bc7eb0e92bb9bd1010a6725b5f8434e88b2825043f563dde33cd69","sha256:ae7977d138d1fca941f9d0ba82a343df7a0f1d0f1c95f92712cf6c21b4cb3248"],"state_sha256":"b59471a2b6d488e03854b60c83319880cc971ca8dd6ce710c37000d121fc23a4"}