{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XNIRCRJKT3LQKJRGXFBOB6KBAJ","short_pith_number":"pith:XNIRCRJK","schema_version":"1.0","canonical_sha256":"bb5111452a9ed7052626b942e0f9410262fc7a92a530d7b42a18b28e56bae72c","source":{"kind":"arxiv","id":"2605.25477","version":1},"attestation_state":"computed","paper":{"title":"EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chelsea Finn, Dorsa Sadigh, Kuo-Han Hung, Perry Dong, Tian Gao","submitted_at":"2026-05-25T06:31:03Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.25477","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-25T06:31:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"68fe68b6de0ebd810347d3848fd5af6ad006b6bc6dc2acb67e8e7cc6e4b1b766","abstract_canon_sha256":"3b080c536720589875571b10db87d49a112c33fece63f49a07c3a2ed15bfb99a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:38.359472Z","signature_b64":"L3/zM82JXnHfhT+2rflf5zi4G1Zb/Gu6NMrnHXG7GO3TwiijdTMP909OPRnsDHgGYjaELDh7YYzR7OcCVyCPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb5111452a9ed7052626b942e0f9410262fc7a92a530d7b42a18b28e56bae72c","last_reissued_at":"2026-05-26T02:04:38.358532Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:38.358532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chelsea Finn, Dorsa Sadigh, Kuo-Han Hung, Perry Dong, Tian Gao","submitted_at":"2026-05-25T06:31:03Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25477","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.25477/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.25477","created_at":"2026-05-26T02:04:38.358706+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.25477v1","created_at":"2026-05-26T02:04:38.358706+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25477","created_at":"2026-05-26T02:04:38.358706+00:00"},{"alias_kind":"pith_short_12","alias_value":"XNIRCRJKT3LQ","created_at":"2026-05-26T02:04:38.358706+00:00"},{"alias_kind":"pith_short_16","alias_value":"XNIRCRJKT3LQKJRG","created_at":"2026-05-26T02:04:38.358706+00:00"},{"alias_kind":"pith_short_8","alias_value":"XNIRCRJK","created_at":"2026-05-26T02:04:38.358706+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XNIRCRJKT3LQKJRGXFBOB6KBAJ","json":"https://pith.science/pith/XNIRCRJKT3LQKJRGXFBOB6KBAJ.json","graph_json":"https://pith.science/api/pith-number/XNIRCRJKT3LQKJRGXFBOB6KBAJ/graph.json","events_json":"https://pith.science/api/pith-number/XNIRCRJKT3LQKJRGXFBOB6KBAJ/events.json","paper":"https://pith.science/paper/XNIRCRJK"},"agent_actions":{"view_html":"https://pith.science/pith/XNIRCRJKT3LQKJRGXFBOB6KBAJ","download_json":"https://pith.science/pith/XNIRCRJKT3LQKJRGXFBOB6KBAJ.json","view_paper":"https://pith.science/paper/XNIRCRJK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.25477&json=true","fetch_graph":"https://pith.science/api/pith-number/XNIRCRJKT3LQKJRGXFBOB6KBAJ/graph.json","fetch_events":"https://pith.science/api/pith-number/XNIRCRJKT3LQKJRGXFBOB6KBAJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XNIRCRJKT3LQKJRGXFBOB6KBAJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XNIRCRJKT3LQKJRGXFBOB6KBAJ/action/storage_attestation","attest_author":"https://pith.science/pith/XNIRCRJKT3LQKJRGXFBOB6KBAJ/action/author_attestation","sign_citation":"https://pith.science/pith/XNIRCRJKT3LQKJRGXFBOB6KBAJ/action/citation_signature","submit_replication":"https://pith.science/pith/XNIRCRJKT3LQKJRGXFBOB6KBAJ/action/replication_record"}},"created_at":"2026-05-26T02:04:38.358706+00:00","updated_at":"2026-05-26T02:04:38.358706+00:00"}