{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CLYJS7LIFRW5FKSHKLN7GEM77H","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":"1711bedac81c30b5a6342483826b98a66ca4f08e01987b8728cc5f5529714c79","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-30T15:46:57Z","title_canon_sha256":"43a90eed443f6a4ec3dc71d64b9d1e5e307161b7f2f2ce7055fbe536aa9b3d06"},"schema_version":"1.0","source":{"id":"2606.31846","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.31846","created_at":"2026-07-01T01:18:17Z"},{"alias_kind":"arxiv_version","alias_value":"2606.31846v1","created_at":"2026-07-01T01:18:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31846","created_at":"2026-07-01T01:18:17Z"},{"alias_kind":"pith_short_12","alias_value":"CLYJS7LIFRW5","created_at":"2026-07-01T01:18:17Z"},{"alias_kind":"pith_short_16","alias_value":"CLYJS7LIFRW5FKSH","created_at":"2026-07-01T01:18:17Z"},{"alias_kind":"pith_short_8","alias_value":"CLYJS7LI","created_at":"2026-07-01T01:18:17Z"}],"graph_snapshots":[{"event_id":"sha256:11be39fc2263c3af79b55c90b6c8bab4cd3e38864ab85769c01f96c0a84282bf","target":"graph","created_at":"2026-07-01T01:18:17Z","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/2606.31846/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language-Action (VLA) models offer a promising framework for robotic manipulation by connecting language instructions, visual observations, and continuous control. However, most existing policies remain limited by behavior cloning or supervised fine-tuning (SFT) from fixed demonstrations, which provides limited opportunity to improve from the policy's own failures. In this paper, we present Z-1, a reinforcement learning (RL) post-training framework for flow-based VLA models. Built on top of $\\pi_{0.5}$, Z-1 uses only publicly released RoboCasa demonstrations for SFT and then applies a t","authors_text":"Lang Cao, Luyi Li, Mofan Peng, Peng Wang, Renhong Chen, Yitong Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-30T15:46:57Z","title":"Z-1: Efficient Reinforcement Learning for Vision-Language-Action Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31846","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:ba11760b315aaa28e65a4361019d63deb0f52c74e427dd5a76010d1676e7c186","target":"record","created_at":"2026-07-01T01:18:17Z","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":"1711bedac81c30b5a6342483826b98a66ca4f08e01987b8728cc5f5529714c79","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-30T15:46:57Z","title_canon_sha256":"43a90eed443f6a4ec3dc71d64b9d1e5e307161b7f2f2ce7055fbe536aa9b3d06"},"schema_version":"1.0","source":{"id":"2606.31846","kind":"arxiv","version":1}},"canonical_sha256":"12f0997d682c6dd2aa4752dbf3119ff9cb656f1bbc4b5c049f6a744a514c602a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12f0997d682c6dd2aa4752dbf3119ff9cb656f1bbc4b5c049f6a744a514c602a","first_computed_at":"2026-07-01T01:18:17.467754Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T01:18:17.467754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f9OAyPBenys5OTjktCA9xTOYuA1L2+1OLraC/Pz3JNXkvzKUM87VatJLHn4Kwu49gVhZkua/cZEbOpp1pkhZCA==","signature_status":"signed_v1","signed_at":"2026-07-01T01:18:17.468194Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.31846","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba11760b315aaa28e65a4361019d63deb0f52c74e427dd5a76010d1676e7c186","sha256:11be39fc2263c3af79b55c90b6c8bab4cd3e38864ab85769c01f96c0a84282bf"],"state_sha256":"faacd52dfaef24bc37ae755f5cbee4f321d0715b9a837a48489a1728aa4c2849"}