{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QE6DM3NNDZOF3RDMWU42AMEAPD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d6d1817470a666ab06c12109edbc0ba5b3a6241028c7adffe03dd6697ab50fdb","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-15T17:17:54Z","title_canon_sha256":"74f009ab18df065ef0d02427dc2bc7eb573ec2b8f1e0b9f03fff237aabde0fe9"},"schema_version":"1.0","source":{"id":"2410.11792","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.11792","created_at":"2026-07-05T09:20:59Z"},{"alias_kind":"arxiv_version","alias_value":"2410.11792v1","created_at":"2026-07-05T09:20:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11792","created_at":"2026-07-05T09:20:59Z"},{"alias_kind":"pith_short_12","alias_value":"QE6DM3NNDZOF","created_at":"2026-07-05T09:20:59Z"},{"alias_kind":"pith_short_16","alias_value":"QE6DM3NNDZOF3RDM","created_at":"2026-07-05T09:20:59Z"},{"alias_kind":"pith_short_8","alias_value":"QE6DM3NN","created_at":"2026-07-05T09:20:59Z"}],"graph_snapshots":[{"event_id":"sha256:8cc7a9e7bdaef1aafcc1f8036f32eb96d4a6e280dab9eeb9d9a2d0339df40ed8","target":"graph","created_at":"2026-07-05T09:20:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.11792/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Georgios Pavlakos, Jinhan Li, Mingyo Seo, Yifeng Zhu, Yuke Zhu, Yuqi Xie, Zhenyu Jiang","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-15T17:17:54Z","title":"OKAMI: Teaching Humanoid Robots Manipulation Skills through Single Video Imitation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11792","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e6442f63eaa7d2d10d7d00c7b8780b1093203ff4e5ef17751e7c8ac90c69dc42","target":"record","created_at":"2026-07-05T09:20:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d6d1817470a666ab06c12109edbc0ba5b3a6241028c7adffe03dd6697ab50fdb","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-15T17:17:54Z","title_canon_sha256":"74f009ab18df065ef0d02427dc2bc7eb573ec2b8f1e0b9f03fff237aabde0fe9"},"schema_version":"1.0","source":{"id":"2410.11792","kind":"arxiv","version":1}},"canonical_sha256":"813c366dad1e5c5dc46cb539a0308078c114fd7473586e1b3fe6c6d083a60977","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"813c366dad1e5c5dc46cb539a0308078c114fd7473586e1b3fe6c6d083a60977","first_computed_at":"2026-07-05T09:20:59.110589Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:20:59.110589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8s/JgsOuShojmvdVO2NXhxhacBQ6Z+LlU3Y/BPSEfY3sAydlz3cnH8Nb4fiI7EChnv41VuyPSR33RYjikRWLCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:20:59.111123Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.11792","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e6442f63eaa7d2d10d7d00c7b8780b1093203ff4e5ef17751e7c8ac90c69dc42","sha256:8cc7a9e7bdaef1aafcc1f8036f32eb96d4a6e280dab9eeb9d9a2d0339df40ed8"],"state_sha256":"857973c3e04d3a36b76e3717895b9cf7e4ad5b58ca86ed5969cf11c2a290b4c3"}