{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XNIRCRJKT3LQKJRGXFBOB6KBAJ","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":"3b080c536720589875571b10db87d49a112c33fece63f49a07c3a2ed15bfb99a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-25T06:31:03Z","title_canon_sha256":"68fe68b6de0ebd810347d3848fd5af6ad006b6bc6dc2acb67e8e7cc6e4b1b766"},"schema_version":"1.0","source":{"id":"2605.25477","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25477","created_at":"2026-05-26T02:04:38Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25477v1","created_at":"2026-05-26T02:04:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25477","created_at":"2026-05-26T02:04:38Z"},{"alias_kind":"pith_short_12","alias_value":"XNIRCRJKT3LQ","created_at":"2026-05-26T02:04:38Z"},{"alias_kind":"pith_short_16","alias_value":"XNIRCRJKT3LQKJRG","created_at":"2026-05-26T02:04:38Z"},{"alias_kind":"pith_short_8","alias_value":"XNIRCRJK","created_at":"2026-05-26T02:04:38Z"}],"graph_snapshots":[{"event_id":"sha256:0e182607a5d92dfda56c709324ded2163852369ee8c99946fdb0569a98bdc7f8","target":"graph","created_at":"2026-05-26T02:04:38Z","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/2605.25477/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The ability to efficiently and reliably learn new tasks has been a foundational challenge in robotics. Vision-Language-Action (VLA) models have demonstrated strong generalization across diverse manipulation tasks, yet pretrained policies consistently fall short of the reliability required for real-world deployment. Reinforcement learning (RL) fine-tuning offers a promising path to bridge this gap, but existing approaches either train from scratch without fully leveraging pretrained priors, or fine-tune VLAs without achieving the sample efficiency and success rates that practical deployment dem","authors_text":"Chelsea Finn, Dorsa Sadigh, Kuo-Han Hung, Perry Dong, Tian Gao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-25T06:31:03Z","title":"EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25477","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:ee5fd4f4832a6076d644bfd44d6750b237efbfc2c38662e6e762ddf747dc6901","target":"record","created_at":"2026-05-26T02:04:38Z","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":"3b080c536720589875571b10db87d49a112c33fece63f49a07c3a2ed15bfb99a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-25T06:31:03Z","title_canon_sha256":"68fe68b6de0ebd810347d3848fd5af6ad006b6bc6dc2acb67e8e7cc6e4b1b766"},"schema_version":"1.0","source":{"id":"2605.25477","kind":"arxiv","version":1}},"canonical_sha256":"bb5111452a9ed7052626b942e0f9410262fc7a92a530d7b42a18b28e56bae72c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb5111452a9ed7052626b942e0f9410262fc7a92a530d7b42a18b28e56bae72c","first_computed_at":"2026-05-26T02:04:38.358532Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:04:38.358532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L3/zM82JXnHfhT+2rflf5zi4G1Zb/Gu6NMrnHXG7GO3TwiijdTMP909OPRnsDHgGYjaELDh7YYzR7OcCVyCPDg==","signature_status":"signed_v1","signed_at":"2026-05-26T02:04:38.359472Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.25477","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee5fd4f4832a6076d644bfd44d6750b237efbfc2c38662e6e762ddf747dc6901","sha256:0e182607a5d92dfda56c709324ded2163852369ee8c99946fdb0569a98bdc7f8"],"state_sha256":"6813f7f1a0932f3cdcdc05585e392cbc2c04bdcfc03874ccf2666d875419db63"}