{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IQSLBJORI73XLDVBQI7HEJNWI7","short_pith_number":"pith:IQSLBJOR","schema_version":"1.0","canonical_sha256":"4424b0a5d147f7758ea1823e7225b647d7427d3fdc0c68272782809b2ae655d5","source":{"kind":"arxiv","id":"2505.19017","version":1},"attestation_state":"computed","paper":{"title":"WorldEval: World Model as Real-World Robot Policies Evaluator","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Chaomin Shen, Junjie Wen, Yaxuan Li, Yichen Zhu, Yi Xu","submitted_at":"2025-05-25T07:41:39Z","abstract_excerpt":"The field of robotics has made significant strides toward developing generalist robot manipulation policies. However, evaluating these policies in real-world scenarios remains time-consuming and challenging, particularly as the number of tasks scales and environmental conditions change. In this work, we demonstrate that world models can serve as a scalable, reproducible, and reliable proxy for real-world robot policy evaluation. A key challenge is generating accurate policy videos from world models that faithfully reflect the robot actions. We observe that directly inputting robot actions or u"},"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":"2505.19017","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-25T07:41:39Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"88a0d026f6ce7a94ea1a8703ee1ca815bb7c30ed627a34cebf4b2b10fcdb34ef","abstract_canon_sha256":"6558e09569e342456df1fc25a0960a1a66c872f69211a2c740cebd7fec036f63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:23.569774Z","signature_b64":"uI94+tRhO57pMIoafuIOk+DCdDAN52jOWMyG8Ao5nFeXZJzmcxsGFDIkGM7qyoxoTtR/IdAgHjKgSAnEr1/4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4424b0a5d147f7758ea1823e7225b647d7427d3fdc0c68272782809b2ae655d5","last_reissued_at":"2026-07-05T11:09:23.569239Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:23.569239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WorldEval: World Model as Real-World Robot Policies Evaluator","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Chaomin Shen, Junjie Wen, Yaxuan Li, Yichen Zhu, Yi Xu","submitted_at":"2025-05-25T07:41:39Z","abstract_excerpt":"The field of robotics has made significant strides toward developing generalist robot manipulation policies. However, evaluating these policies in real-world scenarios remains time-consuming and challenging, particularly as the number of tasks scales and environmental conditions change. In this work, we demonstrate that world models can serve as a scalable, reproducible, and reliable proxy for real-world robot policy evaluation. A key challenge is generating accurate policy videos from world models that faithfully reflect the robot actions. We observe that directly inputting robot actions or u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19017","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/2505.19017/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":"2505.19017","created_at":"2026-07-05T11:09:23.569304+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19017v1","created_at":"2026-07-05T11:09:23.569304+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19017","created_at":"2026-07-05T11:09:23.569304+00:00"},{"alias_kind":"pith_short_12","alias_value":"IQSLBJORI73X","created_at":"2026-07-05T11:09:23.569304+00:00"},{"alias_kind":"pith_short_16","alias_value":"IQSLBJORI73XLDVB","created_at":"2026-07-05T11:09:23.569304+00:00"},{"alias_kind":"pith_short_8","alias_value":"IQSLBJOR","created_at":"2026-07-05T11:09:23.569304+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06018","citing_title":"RoboTALES: Learning Reasoning-Guided Robot Policies via Task-Aligned Simulated Futures","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2606.19531","citing_title":"ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13053","citing_title":"EA-WM: Event-Aware World Models with Task-Specification Grounding for Long-Horizon Manipulation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12403","citing_title":"World Pilot: Steering Vision-Language-Action Models with World-Action Priors","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12217","citing_title":"Making Foresight Actionable: Repurposing Representation Alignment in World Action Models","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05773","citing_title":"PiL-World: A Chunk-Wise World Model for VLA Policy-in-the-Loop Evaluation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01060","citing_title":"RoboWorld: Fast and Reliable Neural Simulators for Generalist Robot Policy Evaluation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04463","citing_title":"OSCAR: Omni-Embodiment Action-Conditioned World Model for Robotics","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00267","citing_title":"StressDream: Steering Video World Models for Robust Policy Evaluation and Improvement","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29898","citing_title":"Critical Interval MSE: Toward Reliable Offline Validation for Robot Manipulation Policies","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27947","citing_title":"SANTS: A State-Adaptive Scheduler for World Action Models","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17912","citing_title":"WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platform","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2602.06949","citing_title":"DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2510.10125","citing_title":"Ctrl-World: A Controllable Generative World Model for Robot Manipulation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2603.09030","citing_title":"PlayWorld: Learning Robot World Models from Autonomous Play","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2603.28489","citing_title":"Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms","ref_index":211,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22152","citing_title":"dWorldEval: Scalable Robotic Policy Evaluation via Discrete Diffusion World Model","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06388","citing_title":"Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06192","citing_title":"EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fields","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21741","citing_title":"Hi-WM: Human-in-the-World-Model for Scalable Robot Post-Training","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IQSLBJORI73XLDVBQI7HEJNWI7","json":"https://pith.science/pith/IQSLBJORI73XLDVBQI7HEJNWI7.json","graph_json":"https://pith.science/api/pith-number/IQSLBJORI73XLDVBQI7HEJNWI7/graph.json","events_json":"https://pith.science/api/pith-number/IQSLBJORI73XLDVBQI7HEJNWI7/events.json","paper":"https://pith.science/paper/IQSLBJOR"},"agent_actions":{"view_html":"https://pith.science/pith/IQSLBJORI73XLDVBQI7HEJNWI7","download_json":"https://pith.science/pith/IQSLBJORI73XLDVBQI7HEJNWI7.json","view_paper":"https://pith.science/paper/IQSLBJOR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19017&json=true","fetch_graph":"https://pith.science/api/pith-number/IQSLBJORI73XLDVBQI7HEJNWI7/graph.json","fetch_events":"https://pith.science/api/pith-number/IQSLBJORI73XLDVBQI7HEJNWI7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IQSLBJORI73XLDVBQI7HEJNWI7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IQSLBJORI73XLDVBQI7HEJNWI7/action/storage_attestation","attest_author":"https://pith.science/pith/IQSLBJORI73XLDVBQI7HEJNWI7/action/author_attestation","sign_citation":"https://pith.science/pith/IQSLBJORI73XLDVBQI7HEJNWI7/action/citation_signature","submit_replication":"https://pith.science/pith/IQSLBJORI73XLDVBQI7HEJNWI7/action/replication_record"}},"created_at":"2026-07-05T11:09:23.569304+00:00","updated_at":"2026-07-05T11:09:23.569304+00:00"}