{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TXJR54DUZMEVE4AZH2Q5WVU6IU","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":"435fc8d99593b354349fae080aed462e4d1c4e3df96863e2e1e0bd819b9e0bde","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-02-06T08:57:55Z","title_canon_sha256":"15b9f478587eada233616d273554b93b613d0cb6d6dc6a71d55a9566c65bf097"},"schema_version":"1.0","source":{"id":"2602.06508","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.06508","created_at":"2026-05-26T02:04:05Z"},{"alias_kind":"arxiv_version","alias_value":"2602.06508v2","created_at":"2026-05-26T02:04:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.06508","created_at":"2026-05-26T02:04:05Z"},{"alias_kind":"pith_short_12","alias_value":"TXJR54DUZMEV","created_at":"2026-05-26T02:04:05Z"},{"alias_kind":"pith_short_16","alias_value":"TXJR54DUZMEVE4AZ","created_at":"2026-05-26T02:04:05Z"},{"alias_kind":"pith_short_8","alias_value":"TXJR54DU","created_at":"2026-05-26T02:04:05Z"}],"graph_snapshots":[{"event_id":"sha256:724585e87067ac944b2f69266ce82ab95cc1670268c9fa3fe3109d6607ae98e7","target":"graph","created_at":"2026-05-26T02:04:05Z","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/2602.06508/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) can refine Vision-Language-Action (VLA) policies beyond behavior cloning, but real-world RL remains expensive due to extensive rollouts, resets, supervision, and safety risks. Action-conditioned video world models offer an option to train in virtual environments, yet they exhibit imprecise action following, particularly on subtle near-success failures. Besides, they lack native reward signals for RL. Computing rewards based on inaccurate visual predictions remain unreliable. We introduce World-VLA-Loop, structured around two foundational designs and a higher-level c","authors_text":"Hai Ci, Kevin Yuchen Ma, Mike Zheng Shou, Xiaokang Liu, Zechen Bai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-02-06T08:57:55Z","title":"World-VLA-Loop: Closed-Loop Learning of Video World Model and VLA Policy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.06508","kind":"arxiv","version":2},"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":"sha256:3e3b3b90fbb28c461c5a7312cd2d09376eab7cf5b074fdbd8e587405970fcc29","target":"record","created_at":"2026-05-26T02:04:05Z","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":"435fc8d99593b354349fae080aed462e4d1c4e3df96863e2e1e0bd819b9e0bde","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-02-06T08:57:55Z","title_canon_sha256":"15b9f478587eada233616d273554b93b613d0cb6d6dc6a71d55a9566c65bf097"},"schema_version":"1.0","source":{"id":"2602.06508","kind":"arxiv","version":2}},"canonical_sha256":"9dd31ef074cb095270193ea1db569e450a6bd041d883ec4a76d44b21e9deffe5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9dd31ef074cb095270193ea1db569e450a6bd041d883ec4a76d44b21e9deffe5","first_computed_at":"2026-05-26T02:04:05.196105Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:04:05.196105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GzRve1GWzckqbZHdyID2M9lSyx3bzDGVe+tRLrrgKeRPfr8G9kikAy1VBmf+7v8iaj7/Vr02O7nrBL/DZJVtBg==","signature_status":"signed_v1","signed_at":"2026-05-26T02:04:05.196997Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.06508","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e3b3b90fbb28c461c5a7312cd2d09376eab7cf5b074fdbd8e587405970fcc29","sha256:724585e87067ac944b2f69266ce82ab95cc1670268c9fa3fe3109d6607ae98e7"],"state_sha256":"4e9d0ac3e94e456c477ee48a6cdb5841957bf48a4c6d9fde6d87d9b1564d8daf"}