{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MITFM7XAS7IBP3TEE73UTTMDYZ","short_pith_number":"pith:MITFM7XA","schema_version":"1.0","canonical_sha256":"6226567ee097d017ee6427f749cd83c67749fbc20ec72c4e91c124d368685177","source":{"kind":"arxiv","id":"2504.12609","version":3},"attestation_state":"computed","paper":{"title":"Crossing the Human-Robot Embodiment Gap with Sim-to-Real RL using One Human Demonstration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"C. Karen Liu, Jeannette Bohg, Olivia Y. Lee, Tyler Ga Wei Lum","submitted_at":"2025-04-17T03:15:20Z","abstract_excerpt":"Teaching robots dexterous manipulation skills often requires collecting hundreds of demonstrations using wearables or teleoperation, a process that is challenging to scale. Videos of human-object interactions are easier to collect and scale, but leveraging them directly for robot learning is difficult due to the lack of explicit action labels and human-robot embodiment differences. We propose Human2Sim2Robot, a novel real-to-sim-to-real framework for training dexterous manipulation policies using only one RGB-D video of a human demonstrating a task. Our method utilizes reinforcement learning ("},"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":"2504.12609","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-04-17T03:15:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8643d723aa607e957f0f937f99dd93bbed3e2af63a7f0d4c723b4ce1e1efd26c","abstract_canon_sha256":"c13bf7e54e7e6861a847b7f0906308daa94072ffab02219d646e88e388ed31e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:46.236775Z","signature_b64":"ddDnqUKoMMrU37C7S6EwhRTyE6r+0Zg/E5npGhsTcrHu5PpJgN4bNZ74Hz80yo/wSTgeTj2tekmNfql8RNkRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6226567ee097d017ee6427f749cd83c67749fbc20ec72c4e91c124d368685177","last_reissued_at":"2026-07-05T11:54:46.236292Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:46.236292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Crossing the Human-Robot Embodiment Gap with Sim-to-Real RL using One Human Demonstration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"C. Karen Liu, Jeannette Bohg, Olivia Y. Lee, Tyler Ga Wei Lum","submitted_at":"2025-04-17T03:15:20Z","abstract_excerpt":"Teaching robots dexterous manipulation skills often requires collecting hundreds of demonstrations using wearables or teleoperation, a process that is challenging to scale. Videos of human-object interactions are easier to collect and scale, but leveraging them directly for robot learning is difficult due to the lack of explicit action labels and human-robot embodiment differences. We propose Human2Sim2Robot, a novel real-to-sim-to-real framework for training dexterous manipulation policies using only one RGB-D video of a human demonstrating a task. Our method utilizes reinforcement learning ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12609","kind":"arxiv","version":3},"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/2504.12609/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":"2504.12609","created_at":"2026-07-05T11:54:46.236358+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.12609v3","created_at":"2026-07-05T11:54:46.236358+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12609","created_at":"2026-07-05T11:54:46.236358+00:00"},{"alias_kind":"pith_short_12","alias_value":"MITFM7XAS7IB","created_at":"2026-07-05T11:54:46.236358+00:00"},{"alias_kind":"pith_short_16","alias_value":"MITFM7XAS7IBP3TE","created_at":"2026-07-05T11:54:46.236358+00:00"},{"alias_kind":"pith_short_8","alias_value":"MITFM7XA","created_at":"2026-07-05T11:54:46.236358+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26428","citing_title":"Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly?","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22471","citing_title":"Scalable Multi-Task Data Generation via Reinforcement Learning for Language-Conditioned Bimanual Dexterous Manipulation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19333","citing_title":"Do as I Do: Dexterous Manipulation Data from Everyday Human Videos","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12604","citing_title":"EgoEngine: From Egocentric Human Videos to High-Fidelity Dexterous Robot Demonstrations","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11628","citing_title":"LUCID: Learning Embodiment-Agnostic Intent Models from Unstructured Human Videos for Scalable Dexterous Robot Skill Acquisition","ref_index":23,"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":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05925","citing_title":"DexSynRefine: Synthesizing and Refining Human-Object Interaction Motion for Physically Feasible Dexterous Robot Actions","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22471","citing_title":"Scalable Multi-Task Data Generation via Reinforcement Learning for Language-Conditioned Bimanual Dexterous Manipulation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29517","citing_title":"CORE: Common Outcome Regularities from Action-Free Visual Demonstrations for Robot Manipulation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16743","citing_title":"LACE: Latent Visual Representation for Cross-Embodiment Learning","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05925","citing_title":"DexSynRefine: Synthesizing and Refining Human-Object Interaction Motion for Physically Feasible Dexterous Robot Actions","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MITFM7XAS7IBP3TEE73UTTMDYZ","json":"https://pith.science/pith/MITFM7XAS7IBP3TEE73UTTMDYZ.json","graph_json":"https://pith.science/api/pith-number/MITFM7XAS7IBP3TEE73UTTMDYZ/graph.json","events_json":"https://pith.science/api/pith-number/MITFM7XAS7IBP3TEE73UTTMDYZ/events.json","paper":"https://pith.science/paper/MITFM7XA"},"agent_actions":{"view_html":"https://pith.science/pith/MITFM7XAS7IBP3TEE73UTTMDYZ","download_json":"https://pith.science/pith/MITFM7XAS7IBP3TEE73UTTMDYZ.json","view_paper":"https://pith.science/paper/MITFM7XA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.12609&json=true","fetch_graph":"https://pith.science/api/pith-number/MITFM7XAS7IBP3TEE73UTTMDYZ/graph.json","fetch_events":"https://pith.science/api/pith-number/MITFM7XAS7IBP3TEE73UTTMDYZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MITFM7XAS7IBP3TEE73UTTMDYZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MITFM7XAS7IBP3TEE73UTTMDYZ/action/storage_attestation","attest_author":"https://pith.science/pith/MITFM7XAS7IBP3TEE73UTTMDYZ/action/author_attestation","sign_citation":"https://pith.science/pith/MITFM7XAS7IBP3TEE73UTTMDYZ/action/citation_signature","submit_replication":"https://pith.science/pith/MITFM7XAS7IBP3TEE73UTTMDYZ/action/replication_record"}},"created_at":"2026-07-05T11:54:46.236358+00:00","updated_at":"2026-07-05T11:54:46.236358+00:00"}