{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4ECJ7NSIJ3CNALBNHGA7R7DWHB","short_pith_number":"pith:4ECJ7NSI","schema_version":"1.0","canonical_sha256":"e1049fb6484ec4d02c2d3981f8fc76386f12db46ed31bd15402971b968425532","source":{"kind":"arxiv","id":"2606.05468","version":1},"attestation_state":"computed","paper":{"title":"FlowPRO: Reward-Free Reinforced Fine-Tuning of Flow-Matching VLAs via Proximalized Preference Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"He Zhang, Junbo Tan, Xueqian Wang, Yihao Wu, Zhengyou Zhang","submitted_at":"2026-06-03T21:47:43Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.05468","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-03T21:47:43Z","cross_cats_sorted":[],"title_canon_sha256":"5c8cbfb9b194c39cc0fba0cd55c3150391b0bcd3310a60beb559b487b0f169f6","abstract_canon_sha256":"efd205a20d1bf34c551e01d7a7a41c70bc9cc844bd2581c8d070f86f9f6304a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:14:52.087787Z","signature_b64":"N3WTHgiPb+yribs0itnRJg3Ihxy4+PVbKEElqGu8WiZE0YrAh+dTIQu94c7TIGTH0Mdm0UuTlVQ2s7Zi2j5xCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1049fb6484ec4d02c2d3981f8fc76386f12db46ed31bd15402971b968425532","last_reissued_at":"2026-06-05T01:14:52.087196Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:14:52.087196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FlowPRO: Reward-Free Reinforced Fine-Tuning of Flow-Matching VLAs via Proximalized Preference Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"He Zhang, Junbo Tan, Xueqian Wang, Yihao Wu, Zhengyou Zhang","submitted_at":"2026-06-03T21:47:43Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05468","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.05468/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.05468","created_at":"2026-06-05T01:14:52.087262+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05468v1","created_at":"2026-06-05T01:14:52.087262+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05468","created_at":"2026-06-05T01:14:52.087262+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ECJ7NSIJ3CN","created_at":"2026-06-05T01:14:52.087262+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ECJ7NSIJ3CNALBN","created_at":"2026-06-05T01:14:52.087262+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ECJ7NSI","created_at":"2026-06-05T01:14:52.087262+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4ECJ7NSIJ3CNALBNHGA7R7DWHB","json":"https://pith.science/pith/4ECJ7NSIJ3CNALBNHGA7R7DWHB.json","graph_json":"https://pith.science/api/pith-number/4ECJ7NSIJ3CNALBNHGA7R7DWHB/graph.json","events_json":"https://pith.science/api/pith-number/4ECJ7NSIJ3CNALBNHGA7R7DWHB/events.json","paper":"https://pith.science/paper/4ECJ7NSI"},"agent_actions":{"view_html":"https://pith.science/pith/4ECJ7NSIJ3CNALBNHGA7R7DWHB","download_json":"https://pith.science/pith/4ECJ7NSIJ3CNALBNHGA7R7DWHB.json","view_paper":"https://pith.science/paper/4ECJ7NSI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05468&json=true","fetch_graph":"https://pith.science/api/pith-number/4ECJ7NSIJ3CNALBNHGA7R7DWHB/graph.json","fetch_events":"https://pith.science/api/pith-number/4ECJ7NSIJ3CNALBNHGA7R7DWHB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ECJ7NSIJ3CNALBNHGA7R7DWHB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ECJ7NSIJ3CNALBNHGA7R7DWHB/action/storage_attestation","attest_author":"https://pith.science/pith/4ECJ7NSIJ3CNALBNHGA7R7DWHB/action/author_attestation","sign_citation":"https://pith.science/pith/4ECJ7NSIJ3CNALBNHGA7R7DWHB/action/citation_signature","submit_replication":"https://pith.science/pith/4ECJ7NSIJ3CNALBNHGA7R7DWHB/action/replication_record"}},"created_at":"2026-06-05T01:14:52.087262+00:00","updated_at":"2026-06-05T01:14:52.087262+00:00"}