{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TG5F55VQNPHIWBTF4U2GHAAMS7","short_pith_number":"pith:TG5F55VQ","schema_version":"1.0","canonical_sha256":"99ba5ef6b06bce8b0665e53463800c97f87e3cda00d47618109720c36d4fc388","source":{"kind":"arxiv","id":"2602.13977","version":2},"attestation_state":"computed","paper":{"title":"WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","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","submitted_at":"2026-02-15T03:48:20Z","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"},"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":"2602.13977","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-02-15T03:48:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ecaf34743e9cb3fb26a1d48a4e45474635b23cf91eb860b1fd82cd6275c2f7d0","abstract_canon_sha256":"feb3bfe71bf2fdd6a81de06242fed291abe5ca4c8b1c0724227bcef33ff2b876"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:34.075452Z","signature_b64":"MvkDAIMizwyw7sheTUevXTgE2xPWpTbYMUz4JkS1ziiMDggJMdkNN5EeuvL66askFAUpXT7cJ78Q02Tle5uwCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99ba5ef6b06bce8b0665e53463800c97f87e3cda00d47618109720c36d4fc388","last_reissued_at":"2026-06-30T01:17:34.074633Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:34.074633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","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","submitted_at":"2026-02-15T03:48:20Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.13977","kind":"arxiv","version":2},"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/2602.13977/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":"2602.13977","created_at":"2026-06-30T01:17:34.074736+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.13977v2","created_at":"2026-06-30T01:17:34.074736+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.13977","created_at":"2026-06-30T01:17:34.074736+00:00"},{"alias_kind":"pith_short_12","alias_value":"TG5F55VQNPHI","created_at":"2026-06-30T01:17:34.074736+00:00"},{"alias_kind":"pith_short_16","alias_value":"TG5F55VQNPHIWBTF","created_at":"2026-06-30T01:17:34.074736+00:00"},{"alias_kind":"pith_short_8","alias_value":"TG5F55VQ","created_at":"2026-06-30T01:17:34.074736+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":20,"sample":[{"citing_arxiv_id":"2606.00090","citing_title":"Silent Failures in Physical AI: A Literature Review of Runtime Action Authorization for Autonomous Systems","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2606.15032","citing_title":"How Should World Models Be Evaluated for Embodied Decision-Making? A Decision-Making-Centric Position","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2606.00113","citing_title":"World Models for Robotic Manipulation: A Survey","ref_index":104,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22446","citing_title":"Pre-VLA: Preemptive Runtime Verification for Reliable Vision-Language-Action and World-Model Rollouts","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12334","citing_title":"Reinforcing VLAs in Task-Agnostic World Models","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08567","citing_title":"ACWM-Phys: Investigating Generalized Physical Interaction in Action-Conditioned Video World Models","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17912","citing_title":"WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platform","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11459","citing_title":"Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09423","citing_title":"SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11832","citing_title":"Learning Action Manifold with Multi-view Latent Priors for Robotic Manipulation","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12334","citing_title":"Reinforcing VLAs in Task-Agnostic World Models","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11459","citing_title":"Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27711","citing_title":"ExoActor: Exocentric Video Generation as Generalizable Interactive Humanoid Control","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08567","citing_title":"ACWM-Phys: Investigating Generalized Physical Interaction in Action-Conditioned Video World Models","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09423","citing_title":"SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00416","citing_title":"Learning While Deploying: Fleet-Scale Reinforcement Learning for Generalist Robot Policies","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21741","citing_title":"Hi-WM: Human-in-the-World-Model for Scalable Robot Post-Training","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01352","citing_title":"VUDA: Breaking CUDA-Vulkan Isolation for Spatial Sharing of Compute and Graphics on the Same GPU","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07288","citing_title":"Sword: Style-Robust World Models as Simulators via Dynamic Latent Bootstrapping for VLA Policy Post-Training","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TG5F55VQNPHIWBTF4U2GHAAMS7","json":"https://pith.science/pith/TG5F55VQNPHIWBTF4U2GHAAMS7.json","graph_json":"https://pith.science/api/pith-number/TG5F55VQNPHIWBTF4U2GHAAMS7/graph.json","events_json":"https://pith.science/api/pith-number/TG5F55VQNPHIWBTF4U2GHAAMS7/events.json","paper":"https://pith.science/paper/TG5F55VQ"},"agent_actions":{"view_html":"https://pith.science/pith/TG5F55VQNPHIWBTF4U2GHAAMS7","download_json":"https://pith.science/pith/TG5F55VQNPHIWBTF4U2GHAAMS7.json","view_paper":"https://pith.science/paper/TG5F55VQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.13977&json=true","fetch_graph":"https://pith.science/api/pith-number/TG5F55VQNPHIWBTF4U2GHAAMS7/graph.json","fetch_events":"https://pith.science/api/pith-number/TG5F55VQNPHIWBTF4U2GHAAMS7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TG5F55VQNPHIWBTF4U2GHAAMS7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TG5F55VQNPHIWBTF4U2GHAAMS7/action/storage_attestation","attest_author":"https://pith.science/pith/TG5F55VQNPHIWBTF4U2GHAAMS7/action/author_attestation","sign_citation":"https://pith.science/pith/TG5F55VQNPHIWBTF4U2GHAAMS7/action/citation_signature","submit_replication":"https://pith.science/pith/TG5F55VQNPHIWBTF4U2GHAAMS7/action/replication_record"}},"created_at":"2026-06-30T01:17:34.074736+00:00","updated_at":"2026-06-30T01:17:34.074736+00:00"}