{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QE6DM3NNDZOF3RDMWU42AMEAPD","short_pith_number":"pith:QE6DM3NN","schema_version":"1.0","canonical_sha256":"813c366dad1e5c5dc46cb539a0308078c114fd7473586e1b3fe6c6d083a60977","source":{"kind":"arxiv","id":"2410.11792","version":1},"attestation_state":"computed","paper":{"title":"OKAMI: Teaching Humanoid Robots Manipulation Skills through Single Video Imitation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Georgios Pavlakos, Jinhan Li, Mingyo Seo, Yifeng Zhu, Yuke Zhu, Yuqi Xie, Zhenyu Jiang","submitted_at":"2024-10-15T17:17:54Z","abstract_excerpt":"We study the problem of teaching humanoid robots manipulation skills by imitating from single video demonstrations. We introduce OKAMI, a method that generates a manipulation plan from a single RGB-D video and derives a policy for execution. At the heart of our approach is object-aware retargeting, which enables the humanoid robot to mimic the human motions in an RGB-D video while adjusting to different object locations during deployment. OKAMI uses open-world vision models to identify task-relevant objects and retarget the body motions and hand poses separately. Our experiments show that OKAM"},"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":"2410.11792","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-15T17:17:54Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"74f009ab18df065ef0d02427dc2bc7eb573ec2b8f1e0b9f03fff237aabde0fe9","abstract_canon_sha256":"d6d1817470a666ab06c12109edbc0ba5b3a6241028c7adffe03dd6697ab50fdb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:59.111123Z","signature_b64":"8s/JgsOuShojmvdVO2NXhxhacBQ6Z+LlU3Y/BPSEfY3sAydlz3cnH8Nb4fiI7EChnv41VuyPSR33RYjikRWLCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"813c366dad1e5c5dc46cb539a0308078c114fd7473586e1b3fe6c6d083a60977","last_reissued_at":"2026-07-05T09:20:59.110589Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:59.110589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OKAMI: Teaching Humanoid Robots Manipulation Skills through Single Video Imitation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Georgios Pavlakos, Jinhan Li, Mingyo Seo, Yifeng Zhu, Yuke Zhu, Yuqi Xie, Zhenyu Jiang","submitted_at":"2024-10-15T17:17:54Z","abstract_excerpt":"We study the problem of teaching humanoid robots manipulation skills by imitating from single video demonstrations. We introduce OKAMI, a method that generates a manipulation plan from a single RGB-D video and derives a policy for execution. At the heart of our approach is object-aware retargeting, which enables the humanoid robot to mimic the human motions in an RGB-D video while adjusting to different object locations during deployment. OKAMI uses open-world vision models to identify task-relevant objects and retarget the body motions and hand poses separately. Our experiments show that OKAM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11792","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/2410.11792/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":"2410.11792","created_at":"2026-07-05T09:20:59.110649+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.11792v1","created_at":"2026-07-05T09:20:59.110649+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11792","created_at":"2026-07-05T09:20:59.110649+00:00"},{"alias_kind":"pith_short_12","alias_value":"QE6DM3NNDZOF","created_at":"2026-07-05T09:20:59.110649+00:00"},{"alias_kind":"pith_short_16","alias_value":"QE6DM3NNDZOF3RDM","created_at":"2026-07-05T09:20:59.110649+00:00"},{"alias_kind":"pith_short_8","alias_value":"QE6DM3NN","created_at":"2026-07-05T09:20:59.110649+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06438","citing_title":"WristMimic: Full-Body Humanoid Control with Wrist-Guided Manipulation","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26443","citing_title":"WatchAct: A Benchmark for Behavior-Grounded Robot Manipulation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19333","citing_title":"Do as I Do: Dexterous Manipulation Data from Everyday Human Videos","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15477","citing_title":"EgoExo-WM: Unlocking Exo Video for Ego World Models","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15477","citing_title":"EgoExo-WM: Unlocking Exo Video for Ego World Models","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2511.04671","citing_title":"X-Diffusion: Training Diffusion Policies on Cross-Embodiment Human Demonstrations","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13015","citing_title":"Learning Versatile Humanoid Manipulation with Touch Dreaming","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QE6DM3NNDZOF3RDMWU42AMEAPD","json":"https://pith.science/pith/QE6DM3NNDZOF3RDMWU42AMEAPD.json","graph_json":"https://pith.science/api/pith-number/QE6DM3NNDZOF3RDMWU42AMEAPD/graph.json","events_json":"https://pith.science/api/pith-number/QE6DM3NNDZOF3RDMWU42AMEAPD/events.json","paper":"https://pith.science/paper/QE6DM3NN"},"agent_actions":{"view_html":"https://pith.science/pith/QE6DM3NNDZOF3RDMWU42AMEAPD","download_json":"https://pith.science/pith/QE6DM3NNDZOF3RDMWU42AMEAPD.json","view_paper":"https://pith.science/paper/QE6DM3NN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.11792&json=true","fetch_graph":"https://pith.science/api/pith-number/QE6DM3NNDZOF3RDMWU42AMEAPD/graph.json","fetch_events":"https://pith.science/api/pith-number/QE6DM3NNDZOF3RDMWU42AMEAPD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QE6DM3NNDZOF3RDMWU42AMEAPD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QE6DM3NNDZOF3RDMWU42AMEAPD/action/storage_attestation","attest_author":"https://pith.science/pith/QE6DM3NNDZOF3RDMWU42AMEAPD/action/author_attestation","sign_citation":"https://pith.science/pith/QE6DM3NNDZOF3RDMWU42AMEAPD/action/citation_signature","submit_replication":"https://pith.science/pith/QE6DM3NNDZOF3RDMWU42AMEAPD/action/replication_record"}},"created_at":"2026-07-05T09:20:59.110649+00:00","updated_at":"2026-07-05T09:20:59.110649+00:00"}