{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TG5F55VQNPHIWBTF4U2GHAAMS7","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":"feb3bfe71bf2fdd6a81de06242fed291abe5ca4c8b1c0724227bcef33ff2b876","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-02-15T03:48:20Z","title_canon_sha256":"ecaf34743e9cb3fb26a1d48a4e45474635b23cf91eb860b1fd82cd6275c2f7d0"},"schema_version":"1.0","source":{"id":"2602.13977","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.13977","created_at":"2026-06-30T01:17:34Z"},{"alias_kind":"arxiv_version","alias_value":"2602.13977v2","created_at":"2026-06-30T01:17:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.13977","created_at":"2026-06-30T01:17:34Z"},{"alias_kind":"pith_short_12","alias_value":"TG5F55VQNPHI","created_at":"2026-06-30T01:17:34Z"},{"alias_kind":"pith_short_16","alias_value":"TG5F55VQNPHIWBTF","created_at":"2026-06-30T01:17:34Z"},{"alias_kind":"pith_short_8","alias_value":"TG5F55VQ","created_at":"2026-06-30T01:17:34Z"}],"graph_snapshots":[{"event_id":"sha256:972cce695691ad152aae473cbdecf3d1caf2c2c50f5526e93ed05db6b3df966b","target":"graph","created_at":"2026-06-30T01:17:34Z","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/2602.13977/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) promises to unlock capabilities beyond imitation learning for Vision--Language--Action (VLA) models, but its requirement for massive real-world interaction prevents direct deployment on physical robots. Recent work attempts to use learned world models as simulators for policy optimization, yet closed-loop imagined rollouts inevitably suffer from hallucination and long-horizon error accumulation. Such errors not only degrade visual fidelity, but also mislead policy optimization by providing unreliable learning signals. We propose WoVR, a reliable world-model-based RL","authors_text":"Chao Yu, Dongbin Zhao, Hao Lin, Haoran Li, Mingjie Wei, Quanlu Zhang, Shangqing Zhou, Tianxing Zhou, Yuhui Chen, Yutong Jiang, Yu Wang, Zefang Huang, Zhen Guo, Zhennan Jiang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-02-15T03:48:20Z","title":"WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.13977","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":"sha256:79a34c34e73c8074cb13fe42150269e18c544eb4662d1bef353c9dd8da6b8b5a","target":"record","created_at":"2026-06-30T01:17:34Z","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":"feb3bfe71bf2fdd6a81de06242fed291abe5ca4c8b1c0724227bcef33ff2b876","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-02-15T03:48:20Z","title_canon_sha256":"ecaf34743e9cb3fb26a1d48a4e45474635b23cf91eb860b1fd82cd6275c2f7d0"},"schema_version":"1.0","source":{"id":"2602.13977","kind":"arxiv","version":2}},"canonical_sha256":"99ba5ef6b06bce8b0665e53463800c97f87e3cda00d47618109720c36d4fc388","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"99ba5ef6b06bce8b0665e53463800c97f87e3cda00d47618109720c36d4fc388","first_computed_at":"2026-06-30T01:17:34.074633Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:17:34.074633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MvkDAIMizwyw7sheTUevXTgE2xPWpTbYMUz4JkS1ziiMDggJMdkNN5EeuvL66askFAUpXT7cJ78Q02Tle5uwCA==","signature_status":"signed_v1","signed_at":"2026-06-30T01:17:34.075452Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.13977","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79a34c34e73c8074cb13fe42150269e18c544eb4662d1bef353c9dd8da6b8b5a","sha256:972cce695691ad152aae473cbdecf3d1caf2c2c50f5526e93ed05db6b3df966b"],"state_sha256":"207f5119ba1bea80b8fba5479f51672865042e241057983e269fee8e5ceb65d6"}