{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VZ4ED6DWTNBRTRTTEHZ2K5YPIU","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":"8d3ab5172cdbbb96a655f97e549e294ab3f3b5c6c093a4f1b3a787d04e0b9467","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-02-08T05:01:17Z","title_canon_sha256":"f531d9d4e7d64a63ade669527588cbdc6da82964bcc5cac33e395c17a1b85881"},"schema_version":"1.0","source":{"id":"2502.05450","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.05450","created_at":"2026-07-05T10:48:25Z"},{"alias_kind":"arxiv_version","alias_value":"2502.05450v2","created_at":"2026-07-05T10:48:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05450","created_at":"2026-07-05T10:48:25Z"},{"alias_kind":"pith_short_12","alias_value":"VZ4ED6DWTNBR","created_at":"2026-07-05T10:48:25Z"},{"alias_kind":"pith_short_16","alias_value":"VZ4ED6DWTNBRTRTT","created_at":"2026-07-05T10:48:25Z"},{"alias_kind":"pith_short_8","alias_value":"VZ4ED6DW","created_at":"2026-07-05T10:48:25Z"}],"graph_snapshots":[{"event_id":"sha256:f522647f7633316b01c707b3f8e2bf7d36324cf945e31746f76e4979b99a6b24","target":"graph","created_at":"2026-07-05T10:48:25Z","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/2502.05450/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language-Action (VLA) models have shown substantial potential in real-world robotic manipulation. However, fine-tuning these models through supervised learning struggles to achieve robust performance due to limited, inconsistent demonstrations, especially in contact-rich environments. In this paper, we propose a reinforced fine-tuning approach for VLA models, named ConRFT, which consists of offline and online fine-tuning with a unified consistency-based training objective, to address these challenges. In the offline stage, our method integrates behavior cloning and Q-learning to effecti","authors_text":"Dongbin Zhao, Haoran Li, Shuai Tian, Shugao Liu, Yingting Zhou, Yuhui Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-02-08T05:01:17Z","title":"ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05450","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:c7faf9acd5359ab930ff0173f9386bb0f499eead4708182e97e0c611591c4dcf","target":"record","created_at":"2026-07-05T10:48:25Z","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":"8d3ab5172cdbbb96a655f97e549e294ab3f3b5c6c093a4f1b3a787d04e0b9467","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-02-08T05:01:17Z","title_canon_sha256":"f531d9d4e7d64a63ade669527588cbdc6da82964bcc5cac33e395c17a1b85881"},"schema_version":"1.0","source":{"id":"2502.05450","kind":"arxiv","version":2}},"canonical_sha256":"ae7841f8769b4319c67321f3a5770f4536e15c56af10a6c6f1ad9dd8300599d4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae7841f8769b4319c67321f3a5770f4536e15c56af10a6c6f1ad9dd8300599d4","first_computed_at":"2026-07-05T10:48:25.275400Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:48:25.275400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rgce1uQrEgOklJsjQEHUpbRs+C9vpLSllxcu8605n7rgAgK1FS6wgv6ovKzu6X0ovm7gj2UoZHxH1U+Bq3CgCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:48:25.275930Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.05450","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7faf9acd5359ab930ff0173f9386bb0f499eead4708182e97e0c611591c4dcf","sha256:f522647f7633316b01c707b3f8e2bf7d36324cf945e31746f76e4979b99a6b24"],"state_sha256":"f8d56762b2ac14d7c80aa2684fbe9b2a2336724ee949e34d3636d4eebf0d4f31"}