{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DGJ3RVPOQGT5DFHB3YBILGST77","short_pith_number":"pith:DGJ3RVPO","schema_version":"1.0","canonical_sha256":"1993b8d5ee81a7d194e1de02859a53ffda9be3fcca431b393fb1309929ce70bc","source":{"kind":"arxiv","id":"2505.09601","version":1},"attestation_state":"computed","paper":{"title":"Real2Render2Real: Scaling Robot Data Without Dynamics Simulation or Robot Hardware","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Huang Huang, Justin Yu, Karim El-Refai, Ken Goldberg, Letian Fu, Muhammad Zubair Irshad, Rares Andrei Ambrus, Richard Cheng","submitted_at":"2025-05-14T17:50:35Z","abstract_excerpt":"Scaling robot learning requires vast and diverse datasets. Yet the prevailing data collection paradigm-human teleoperation-remains costly and constrained by manual effort and physical robot access. We introduce Real2Render2Real (R2R2R), a novel approach for generating robot training data without relying on object dynamics simulation or teleoperation of robot hardware. The input is a smartphone-captured scan of one or more objects and a single video of a human demonstration. R2R2R renders thousands of high visual fidelity robot-agnostic demonstrations by reconstructing detailed 3D object geomet"},"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":"2505.09601","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-14T17:50:35Z","cross_cats_sorted":[],"title_canon_sha256":"b059e818b2ed738f0c359d773df54e7aed9060dfe3a6c7e08521df1002aa8311","abstract_canon_sha256":"bc78b76bd69014ff44d91d0d6c9063c21d131b5d64d260988de3f2c13f5aa08e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:11.140375Z","signature_b64":"mVvrdtfrq1D27W+iDrhs3nl4e/RhCoGFSj4q+9FmBGmFPvauf9ML+ZP4wqr3wYRsBfY5jIaTF+Lkm2mNRbJ7Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1993b8d5ee81a7d194e1de02859a53ffda9be3fcca431b393fb1309929ce70bc","last_reissued_at":"2026-07-05T11:03:11.139916Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:11.139916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Real2Render2Real: Scaling Robot Data Without Dynamics Simulation or Robot Hardware","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Huang Huang, Justin Yu, Karim El-Refai, Ken Goldberg, Letian Fu, Muhammad Zubair Irshad, Rares Andrei Ambrus, Richard Cheng","submitted_at":"2025-05-14T17:50:35Z","abstract_excerpt":"Scaling robot learning requires vast and diverse datasets. Yet the prevailing data collection paradigm-human teleoperation-remains costly and constrained by manual effort and physical robot access. We introduce Real2Render2Real (R2R2R), a novel approach for generating robot training data without relying on object dynamics simulation or teleoperation of robot hardware. The input is a smartphone-captured scan of one or more objects and a single video of a human demonstration. R2R2R renders thousands of high visual fidelity robot-agnostic demonstrations by reconstructing detailed 3D object geomet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.09601","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/2505.09601/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":"2505.09601","created_at":"2026-07-05T11:03:11.139971+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.09601v1","created_at":"2026-07-05T11:03:11.139971+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.09601","created_at":"2026-07-05T11:03:11.139971+00:00"},{"alias_kind":"pith_short_12","alias_value":"DGJ3RVPOQGT5","created_at":"2026-07-05T11:03:11.139971+00:00"},{"alias_kind":"pith_short_16","alias_value":"DGJ3RVPOQGT5DFHB","created_at":"2026-07-05T11:03:11.139971+00:00"},{"alias_kind":"pith_short_8","alias_value":"DGJ3RVPO","created_at":"2026-07-05T11:03:11.139971+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25939","citing_title":"DeformGen: Dynamics-Based Topology Augmentation for Deformable Manipulation Policy Learning","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24078","citing_title":"MinInter: Minimizing Trajectory Interpolation During Data Augmentation for Imitation Learning","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23689","citing_title":"AutoDex: An Automated Real-World System for Dexterous Grasping Data Collection","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23371","citing_title":"TSD: A Physics-Inspired Trajectory Saliency Detector for Efficient Imitation Learning","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17520","citing_title":"GASE: Gaussian Splatting-Based Automated System for Reconstructing Embodied-Simulation Environments","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2606.15148","citing_title":"MimicIK: Real-Time Generative Inverse Kinematics from Teleoperation with FK Consistency","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08828","citing_title":"Video2Sim2Real: Full-Stack Autonomous Dexterous Skill Acquisition from a Single Human Video","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28276","citing_title":"SimFoundry: Modular and Automated Scene Generation for Policy Learning and Evaluation","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29379","citing_title":"DR-GS: Physically-Based Deformable and Relightable 2D Gaussians","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25939","citing_title":"DeformGen: Dynamics-Based Topology Augmentation for Deformable Manipulation Policy Learning","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23204","citing_title":"AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery","ref_index":144,"is_internal_anchor":false},{"citing_arxiv_id":"2602.09023","citing_title":"TwinRL: Digital Twin-Driven Reinforcement Learning for Real-World Robotic Manipulation","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2510.08547","citing_title":"R2RGEN: Real-to-Real 3D Data Generation for Spatially Generalized Manipulation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2508.13073","citing_title":"Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey","ref_index":237,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26509","citing_title":"3D Generation for Embodied AI and Robotic Simulation: A Survey","ref_index":183,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25459","citing_title":"GS-Playground: A High-Throughput Photorealistic Simulator for Vision-Informed Robot Learning","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26509","citing_title":"3D Generation for Embodied AI and Robotic Simulation: A Survey","ref_index":183,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10809","citing_title":"WARPED: Wrist-Aligned Rendering for Robot Policy Learning from Egocentric Human Demonstrations","ref_index":119,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26509","citing_title":"3D Generation for Embodied AI and Robotic Simulation: A Survey","ref_index":183,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13645","citing_title":"A Mechanistic Analysis of Sim-and-Real Co-Training in Generative Robot Policies","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DGJ3RVPOQGT5DFHB3YBILGST77","json":"https://pith.science/pith/DGJ3RVPOQGT5DFHB3YBILGST77.json","graph_json":"https://pith.science/api/pith-number/DGJ3RVPOQGT5DFHB3YBILGST77/graph.json","events_json":"https://pith.science/api/pith-number/DGJ3RVPOQGT5DFHB3YBILGST77/events.json","paper":"https://pith.science/paper/DGJ3RVPO"},"agent_actions":{"view_html":"https://pith.science/pith/DGJ3RVPOQGT5DFHB3YBILGST77","download_json":"https://pith.science/pith/DGJ3RVPOQGT5DFHB3YBILGST77.json","view_paper":"https://pith.science/paper/DGJ3RVPO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.09601&json=true","fetch_graph":"https://pith.science/api/pith-number/DGJ3RVPOQGT5DFHB3YBILGST77/graph.json","fetch_events":"https://pith.science/api/pith-number/DGJ3RVPOQGT5DFHB3YBILGST77/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DGJ3RVPOQGT5DFHB3YBILGST77/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DGJ3RVPOQGT5DFHB3YBILGST77/action/storage_attestation","attest_author":"https://pith.science/pith/DGJ3RVPOQGT5DFHB3YBILGST77/action/author_attestation","sign_citation":"https://pith.science/pith/DGJ3RVPOQGT5DFHB3YBILGST77/action/citation_signature","submit_replication":"https://pith.science/pith/DGJ3RVPOQGT5DFHB3YBILGST77/action/replication_record"}},"created_at":"2026-07-05T11:03:11.139971+00:00","updated_at":"2026-07-05T11:03:11.139971+00:00"}