{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DCPO2QGR35ACEBPYLLBHYKEI2E","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":"3fe65d80f961c6443c1a8d2b72c8671c3688fcd1545f68cdb2fe6dccddcf2f46","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-02-09T18:59:52Z","title_canon_sha256":"c982b7a82402dc1669fa4a21737824650a2d487cc634260587a5ec6760ba97f0"},"schema_version":"1.0","source":{"id":"2602.09023","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.09023","created_at":"2026-05-20T01:05:08Z"},{"alias_kind":"arxiv_version","alias_value":"2602.09023v4","created_at":"2026-05-20T01:05:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.09023","created_at":"2026-05-20T01:05:08Z"},{"alias_kind":"pith_short_12","alias_value":"DCPO2QGR35AC","created_at":"2026-05-20T01:05:08Z"},{"alias_kind":"pith_short_16","alias_value":"DCPO2QGR35ACEBPY","created_at":"2026-05-20T01:05:08Z"},{"alias_kind":"pith_short_8","alias_value":"DCPO2QGR","created_at":"2026-05-20T01:05:08Z"}],"graph_snapshots":[{"event_id":"sha256:11545c284f750e957904e12df40347e4e56bff83dc97096e75c676bcb165292b","target":"graph","created_at":"2026-05-20T01:05:08Z","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/2602.09023/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite strong generalization capabilities, Vision-Language-Action (VLA) models remain constrained by the high cost of expert demonstrations and limited real-world interaction. While online reinforcement learning (RL) has shown promise, its application to real-world VLA manipulation is hindered by low exploration efficiency and restricted exploration coverage. Through systematic real-world experiments, we observe that the effective exploration space of online RL is largely constrained by the trajectory distribution induced during supervised fine-tuning (SFT). Motivated by this observation, we ","authors_text":"Chenyang Gu, Gao Huang, Jiaming Liu, Nuowei Han, Peng Jia, Qinwen Xu, Rui Zhou, Shanghang Zhang, Shaojun Shi, Shuo Gu, Sirui Han, Wenzhao Zheng, Yang Yue, Zhuoyang Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-02-09T18:59:52Z","title":"TwinRL: Digital Twin-Driven Reinforcement Learning for Real-World Robotic Manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.09023","kind":"arxiv","version":4},"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":"sha256:8378de72f28b36b8a983613219d657776cdfbfa7062e95d4badc36753a46ab17","target":"record","created_at":"2026-05-20T01:05:08Z","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":"3fe65d80f961c6443c1a8d2b72c8671c3688fcd1545f68cdb2fe6dccddcf2f46","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-02-09T18:59:52Z","title_canon_sha256":"c982b7a82402dc1669fa4a21737824650a2d487cc634260587a5ec6760ba97f0"},"schema_version":"1.0","source":{"id":"2602.09023","kind":"arxiv","version":4}},"canonical_sha256":"189eed40d1df402205f85ac27c2888d10ea5f580fa251f4144a2766abf94a1ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"189eed40d1df402205f85ac27c2888d10ea5f580fa251f4144a2766abf94a1ed","first_computed_at":"2026-05-20T01:05:08.645966Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:05:08.645966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4v+liu/d35WI11d+zRN3pz/KJBPeZg1xdc50X/V0qZvCSOXWgYruttbupAPYsy5W+hvRQR9f+g0qi2HrIz4oAg==","signature_status":"signed_v1","signed_at":"2026-05-20T01:05:08.646918Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.09023","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8378de72f28b36b8a983613219d657776cdfbfa7062e95d4badc36753a46ab17","sha256:11545c284f750e957904e12df40347e4e56bff83dc97096e75c676bcb165292b"],"state_sha256":"42e3aab2182ccde2166b292a865612d61e1a3dff6649abbdbd7816ca8211cd1e"}