{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7T3FOS2RQBBK6QUVHWCRVMNFMP","short_pith_number":"pith:7T3FOS2R","schema_version":"1.0","canonical_sha256":"fcf6574b518042af42953d851ab1a563c626870a90cde4bf3aee4770022a874b","source":{"kind":"arxiv","id":"2510.10125","version":3},"attestation_state":"computed","paper":{"title":"Ctrl-World: A Controllable Generative World Model for Robot Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A controllable world model ranks robot policies and improves them by 44.7 percent through imagined trajectories alone.","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chelsea Finn, Jianyu Chen, Lucy Xiaoyang Shi, Yanjiang Guo","submitted_at":"2025-10-11T09:13:10Z","abstract_excerpt":"Generalist robot policies can now perform a wide range of manipulation skills, but evaluating and improving their ability with unfamiliar objects and instructions remains a significant challenge. Rigorous evaluation requires a large number of real-world rollouts, while systematic improvement demands additional corrective data with expert labels. Both of these processes are slow, costly, and difficult to scale. World models offer a promising, scalable alternative by enabling policies to rollout within imagination space. However, a key challenge is building a controllable world model that can ha"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2510.10125","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-10-11T09:13:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3019f14dbb11216663c9ef08481998aa772d3e8d4855973c51901e64ae6d4311","abstract_canon_sha256":"16dd01db064d2c62aee7b939ec6d294e3ef075f723ec58306d3e5f200272cc2c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:49.506293Z","signature_b64":"hg5q73HrISZKDMhoCJSOLIAV9TRwlaO9wGWFPD7qCJGeRYONyjmr2DK6apHQJHzmxI4NHL6ihrUDd9j0uliEDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcf6574b518042af42953d851ab1a563c626870a90cde4bf3aee4770022a874b","last_reissued_at":"2026-05-17T23:38:49.505782Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:49.505782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ctrl-World: A Controllable Generative World Model for Robot Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A controllable world model ranks robot policies and improves them by 44.7 percent through imagined trajectories alone.","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chelsea Finn, Jianyu Chen, Lucy Xiaoyang Shi, Yanjiang Guo","submitted_at":"2025-10-11T09:13:10Z","abstract_excerpt":"Generalist robot policies can now perform a wide range of manipulation skills, but evaluating and improving their ability with unfamiliar objects and instructions remains a significant challenge. Rigorous evaluation requires a large number of real-world rollouts, while systematic improvement demands additional corrective data with expert labels. Both of these processes are slow, costly, and difficult to scale. World models offer a promising, scalable alternative by enabling policies to rollout within imagination space. However, a key challenge is building a controllable world model that can ha"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"By synthesizing successful trajectories in imagination and using them for supervised fine-tuning, our approach can improve policy success by 44.7%.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The generated trajectories are sufficiently accurate proxies for real-world dynamics on novel objects, instructions, and camera placements to enable reliable policy ranking and effective fine-tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A controllable world model trained on the DROID dataset generates consistent multi-view robot trajectories for over 20 seconds and improves generalist policy success rates by 44.7% via imagined trajectory fine-tuning.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A controllable world model ranks robot policies and improves them by 44.7 percent through imagined trajectories alone.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"151df77c49b7b3312d0c27b87f6f77990c2fcd09b51e91c45bd4a7dd8afada08"},"source":{"id":"2510.10125","kind":"arxiv","version":3},"verdict":{"id":"f26e11c6-4ee4-47a8-b897-324ba90446e0","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T01:08:54.062305Z","strongest_claim":"By synthesizing successful trajectories in imagination and using them for supervised fine-tuning, our approach can improve policy success by 44.7%.","one_line_summary":"A controllable world model trained on the DROID dataset generates consistent multi-view robot trajectories for over 20 seconds and improves generalist policy success rates by 44.7% via imagined trajectory fine-tuning.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The generated trajectories are sufficiently accurate proxies for real-world dynamics on novel objects, instructions, and camera placements to enable reliable policy ranking and effective fine-tuning.","pith_extraction_headline":"A controllable world model ranks robot policies and improves them by 44.7 percent through imagined trajectories alone."},"references":{"count":56,"sample":[{"doi":"","year":null,"title":"Cosmos World Foundation Model Platform for Physical AI","work_id":"a2dba24c-318d-476a-8b21-4289c265810c","ref_index":1,"cited_arxiv_id":"2501.03575","is_internal_anchor":true},{"doi":"","year":null,"title":"RoboArena: Distributed real-world evaluation of generalist robot policies","work_id":"a02af411-4d93-4ac8-a15c-930c8f021765","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation","work_id":"a3bde288-aace-40db-8067-3ae6656f9509","ref_index":3,"cited_arxiv_id":"2409.16283","is_internal_anchor":true},{"doi":"","year":null,"title":"Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models","work_id":"954b4359-f4ed-4c73-ae5b-f75d486b6fc8","ref_index":4,"cited_arxiv_id":"2310.10639","is_internal_anchor":true},{"doi":"","year":null,"title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","work_id":"f790abdc-a796-482f-a40d-f8ee035ecfc2","ref_index":5,"cited_arxiv_id":"2410.24164","is_internal_anchor":true}],"resolved_work":56,"snapshot_sha256":"243ff9ac1de778d6328c913e9251ca801609863084055bc3a4127ff3483d2c95","internal_anchors":32},"formal_canon":{"evidence_count":2,"snapshot_sha256":"5f4eaeb564048631af71e0063430757edbdb147dd3d0e57b12560c030c4487d8"},"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":"2510.10125","created_at":"2026-05-17T23:38:49.505875+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.10125v3","created_at":"2026-05-17T23:38:49.505875+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.10125","created_at":"2026-05-17T23:38:49.505875+00:00"},{"alias_kind":"pith_short_12","alias_value":"7T3FOS2RQBBK","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"7T3FOS2RQBBK6QUV","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"7T3FOS2R","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":27,"internal_anchor_count":27,"sample":[{"citing_arxiv_id":"2605.22882","citing_title":"GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation","ref_index":20,"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":27,"is_internal_anchor":true},{"citing_arxiv_id":"2603.14392","citing_title":"WestWorld: A Knowledge-Encoded Scalable Trajectory World Model for Diverse Robotic Systems","ref_index":14,"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":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17580","citing_title":"ECG-WM: A Physiology-Informed ECG World Model for Clinical Intervention Simulation","ref_index":5,"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":21,"is_internal_anchor":true},{"citing_arxiv_id":"2601.02078","citing_title":"Genie Sim 3.0 : A High-Fidelity Comprehensive Simulation Platform for Humanoid Robot","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2602.06949","citing_title":"DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2602.11075","citing_title":"RISE: Self-Improving Robot Policy with Compositional World Model","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2603.09030","citing_title":"PlayWorld: Learning Robot World Models from Autonomous Play","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2512.15692","citing_title":"mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12167","citing_title":"From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27792","citing_title":"MotuBrain: An Advanced World Action Model for Robot Control","ref_index":16,"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":3,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23121","citing_title":"Breaking Lock-In: Preserving Steerability under Low-Data VLA Post-Training","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22152","citing_title":"dWorldEval: Scalable Robotic Policy Evaluation via Discrete Diffusion World Model","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06388","citing_title":"Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00080","citing_title":"World Model for Robot Learning: A Comprehensive Survey","ref_index":21,"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":16,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19734","citing_title":"UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09330","citing_title":"VAG: Dual-Stream Video-Action Generation for Embodied Data Synthesis","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07687","citing_title":"PhySPRING: Structure-Preserving Reduction of Physics-Informed Twins via GNN","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06168","citing_title":"Action Images: End-to-End Policy Learning via Multiview Video Generation","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2604.05014","citing_title":"StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7T3FOS2RQBBK6QUVHWCRVMNFMP","json":"https://pith.science/pith/7T3FOS2RQBBK6QUVHWCRVMNFMP.json","graph_json":"https://pith.science/api/pith-number/7T3FOS2RQBBK6QUVHWCRVMNFMP/graph.json","events_json":"https://pith.science/api/pith-number/7T3FOS2RQBBK6QUVHWCRVMNFMP/events.json","paper":"https://pith.science/paper/7T3FOS2R"},"agent_actions":{"view_html":"https://pith.science/pith/7T3FOS2RQBBK6QUVHWCRVMNFMP","download_json":"https://pith.science/pith/7T3FOS2RQBBK6QUVHWCRVMNFMP.json","view_paper":"https://pith.science/paper/7T3FOS2R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.10125&json=true","fetch_graph":"https://pith.science/api/pith-number/7T3FOS2RQBBK6QUVHWCRVMNFMP/graph.json","fetch_events":"https://pith.science/api/pith-number/7T3FOS2RQBBK6QUVHWCRVMNFMP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7T3FOS2RQBBK6QUVHWCRVMNFMP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7T3FOS2RQBBK6QUVHWCRVMNFMP/action/storage_attestation","attest_author":"https://pith.science/pith/7T3FOS2RQBBK6QUVHWCRVMNFMP/action/author_attestation","sign_citation":"https://pith.science/pith/7T3FOS2RQBBK6QUVHWCRVMNFMP/action/citation_signature","submit_replication":"https://pith.science/pith/7T3FOS2RQBBK6QUVHWCRVMNFMP/action/replication_record"}},"created_at":"2026-05-17T23:38:49.505875+00:00","updated_at":"2026-05-17T23:38:49.505875+00:00"}