{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WP7WP5Z7KCK4MMHBFYLYWVBCJA","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":"52baf3748d42679bdcf2f641598e8da4a6454083a76113b56bed138da0b15612","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-09-04T09:48:43Z","title_canon_sha256":"01d7aaab5b57ab65b76f8442c353ef170510a8c999163b30827225c1c40d7f12"},"schema_version":"1.0","source":{"id":"2509.04063","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.04063","created_at":"2026-07-05T12:04:52Z"},{"alias_kind":"arxiv_version","alias_value":"2509.04063v1","created_at":"2026-07-05T12:04:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04063","created_at":"2026-07-05T12:04:52Z"},{"alias_kind":"pith_short_12","alias_value":"WP7WP5Z7KCK4","created_at":"2026-07-05T12:04:52Z"},{"alias_kind":"pith_short_16","alias_value":"WP7WP5Z7KCK4MMHB","created_at":"2026-07-05T12:04:52Z"},{"alias_kind":"pith_short_8","alias_value":"WP7WP5Z7","created_at":"2026-07-05T12:04:52Z"}],"graph_snapshots":[{"event_id":"sha256:9c1e72d985ad491b637950925009f38dcf9dbaacb09914847d2f2d7332e95648","target":"graph","created_at":"2026-07-05T12:04:52Z","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/2509.04063/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language-Action (VLA) models based on flow matching have shown excellent performance in general-purpose robotic manipulation tasks. However, the action accuracy of these models on complex downstream tasks is unsatisfactory. One important reason is that these models rely solely on the post-training paradigm of imitation learning, which makes it difficult to have a deeper understanding of the distribution properties of data quality, which is exactly what Reinforcement Learning (RL) excels at. In this paper, we theoretically propose an offline RL post-training objective for VLA flow models","authors_text":"Donglin Wang, Hongchao Lu, Hongyin Zhang, Junxi Jin, Qixin Zeng, Shiyuan Zhang, Yifan Qiao","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-09-04T09:48:43Z","title":"Balancing Signal and Variance: Adaptive Offline RL Post-Training for VLA Flow Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04063","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":"sha256:0e25167e4ab802be50ba99c2160b4a101c5da9fdf29c048dc2c2a1d06ccf8d4c","target":"record","created_at":"2026-07-05T12:04:52Z","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":"52baf3748d42679bdcf2f641598e8da4a6454083a76113b56bed138da0b15612","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-09-04T09:48:43Z","title_canon_sha256":"01d7aaab5b57ab65b76f8442c353ef170510a8c999163b30827225c1c40d7f12"},"schema_version":"1.0","source":{"id":"2509.04063","kind":"arxiv","version":1}},"canonical_sha256":"b3ff67f73f5095c630e12e178b54224824a50889d454194efd2465f375bc2345","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b3ff67f73f5095c630e12e178b54224824a50889d454194efd2465f375bc2345","first_computed_at":"2026-07-05T12:04:52.745177Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:04:52.745177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vnDuuq+bEgNbfsbb50w8kZSavvF4ZXK8v6UUmUtfj9+Rq6PnEYGKkp1bYJhQ9y13qIxBrtQAf3naHJay1YFjCA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:04:52.745635Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.04063","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e25167e4ab802be50ba99c2160b4a101c5da9fdf29c048dc2c2a1d06ccf8d4c","sha256:9c1e72d985ad491b637950925009f38dcf9dbaacb09914847d2f2d7332e95648"],"state_sha256":"f0a49a6ce85a9a9554aeadbd499b481c6042204dc354ca03c465d292c829f453"}