{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2ROOKFUQ52KJIU5KI2LOLHT54Q","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":"736132b540ca4f6e7f88fa80e59039d30c20ecbfff006d672ac71a3637265e83","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-11T03:11:18Z","title_canon_sha256":"2a35847e86d618ace73bdcad3f1cc7e78eeb3f51bf0d2d0a68eee3bf5de8b35a"},"schema_version":"1.0","source":{"id":"2510.09976","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.09976","created_at":"2026-06-26T01:15:46Z"},{"alias_kind":"arxiv_version","alias_value":"2510.09976v2","created_at":"2026-06-26T01:15:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.09976","created_at":"2026-06-26T01:15:46Z"},{"alias_kind":"pith_short_12","alias_value":"2ROOKFUQ52KJ","created_at":"2026-06-26T01:15:46Z"},{"alias_kind":"pith_short_16","alias_value":"2ROOKFUQ52KJIU5K","created_at":"2026-06-26T01:15:46Z"},{"alias_kind":"pith_short_8","alias_value":"2ROOKFUQ","created_at":"2026-06-26T01:15:46Z"}],"graph_snapshots":[{"event_id":"sha256:ce35d5196f5a551a95141419f98234d40853e3c8af2eaf02afcfab322dea11ec","target":"graph","created_at":"2026-06-26T01:15:46Z","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/2510.09976/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language-Action (VLA) models such as OpenVLA, Octo, and $\\pi_0$ have shown strong generalization by leveraging large-scale demonstrations, yet their performance is still fundamentally constrained by the quality and coverage of supervised data. Reinforcement learning (RL) provides a promising path for improving and fine-tuning VLAs through online interaction. However, conventional policy gradient methods are computationally infeasible in the context of flow-matching based models due to the intractability of the importance sampling process, which requires explicit computation of policy ra","authors_text":"Erliang Lin, Feifei Zhao, Huangrui Li, Mingyang Lyu, Ruolin Chen, Yinqian Sun, Yi Zeng","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-11T03:11:18Z","title":"Reinforcement Fine-Tuning of Flow-Matching Policies for Vision-Language-Action Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.09976","kind":"arxiv","version":2},"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:fcbe72d634dc670cb44390b30ce6602d627f2449443368657bc6765b78076914","target":"record","created_at":"2026-06-26T01:15:46Z","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":"736132b540ca4f6e7f88fa80e59039d30c20ecbfff006d672ac71a3637265e83","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-11T03:11:18Z","title_canon_sha256":"2a35847e86d618ace73bdcad3f1cc7e78eeb3f51bf0d2d0a68eee3bf5de8b35a"},"schema_version":"1.0","source":{"id":"2510.09976","kind":"arxiv","version":2}},"canonical_sha256":"d45ce51690ee949453aa4696e59e7de408866501fae28aea8789b60bd5c98137","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d45ce51690ee949453aa4696e59e7de408866501fae28aea8789b60bd5c98137","first_computed_at":"2026-06-26T01:15:46.448171Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-26T01:15:46.448171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l9vQzUaRziZ78S9gVDnLRh38htDlL8V5o9uW1CLRslB3MhEautBRnfQi3qfcObrAmo5O7nD0CDounmha7mR3Dw==","signature_status":"signed_v1","signed_at":"2026-06-26T01:15:46.448699Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.09976","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fcbe72d634dc670cb44390b30ce6602d627f2449443368657bc6765b78076914","sha256:ce35d5196f5a551a95141419f98234d40853e3c8af2eaf02afcfab322dea11ec"],"state_sha256":"80a77f179b4e6c47f3eff6b5433c20da4b93ab3813ff52e4705ced064c996bb3"}