{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AFFMKTITHRS22UR742O76OUOHX","short_pith_number":"pith:AFFMKTIT","schema_version":"1.0","canonical_sha256":"014ac54d133c65ad523fe69dff3a8e3dc83151240c7e8092c839cc38e796d97c","source":{"kind":"arxiv","id":"2410.24221","version":1},"attestation_state":"computed","paper":{"title":"EgoMimic: Scaling Imitation Learning via Egocentric Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Chen Wang, Danfei Xu, Dhruv Patel, Judy Hoffman, Pranay Mathur, Ryan Punamiya, Shuo Cheng, Simar Kareer","submitted_at":"2024-10-31T17:59:55Z","abstract_excerpt":"The scale and diversity of demonstration data required for imitation learning is a significant challenge. We present EgoMimic, a full-stack framework which scales manipulation via human embodiment data, specifically egocentric human videos paired with 3D hand tracking. EgoMimic achieves this through: (1) a system to capture human embodiment data using the ergonomic Project Aria glasses, (2) a low-cost bimanual manipulator that minimizes the kinematic gap to human data, (3) cross-domain data alignment techniques, and (4) an imitation learning architecture that co-trains on human and robot data."},"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":"2410.24221","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-31T17:59:55Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"fa98ba748dfc43d4fe50a772c6dee798f6c2db29860e48f39244e786dedb2612","abstract_canon_sha256":"d43b14954d8cead1bb0776000077507fc4f9f2510911ad99d3bddd56c2ac4d1b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:21.441525Z","signature_b64":"m0pNmOUNWt3ZCzRXC0/bORLhpVfsLj9Tgz7xIx3aJ3ghNNyDfd2qAIy8uIgi5e+q5ORtvsd0rLp2mqHW7WcWAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"014ac54d133c65ad523fe69dff3a8e3dc83151240c7e8092c839cc38e796d97c","last_reissued_at":"2026-07-05T09:29:21.441013Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:21.441013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EgoMimic: Scaling Imitation Learning via Egocentric Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Chen Wang, Danfei Xu, Dhruv Patel, Judy Hoffman, Pranay Mathur, Ryan Punamiya, Shuo Cheng, Simar Kareer","submitted_at":"2024-10-31T17:59:55Z","abstract_excerpt":"The scale and diversity of demonstration data required for imitation learning is a significant challenge. We present EgoMimic, a full-stack framework which scales manipulation via human embodiment data, specifically egocentric human videos paired with 3D hand tracking. EgoMimic achieves this through: (1) a system to capture human embodiment data using the ergonomic Project Aria glasses, (2) a low-cost bimanual manipulator that minimizes the kinematic gap to human data, (3) cross-domain data alignment techniques, and (4) an imitation learning architecture that co-trains on human and robot data."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.24221","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/2410.24221/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":"2410.24221","created_at":"2026-07-05T09:29:21.441075+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.24221v1","created_at":"2026-07-05T09:29:21.441075+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.24221","created_at":"2026-07-05T09:29:21.441075+00:00"},{"alias_kind":"pith_short_12","alias_value":"AFFMKTITHRS2","created_at":"2026-07-05T09:29:21.441075+00:00"},{"alias_kind":"pith_short_16","alias_value":"AFFMKTITHRS22UR7","created_at":"2026-07-05T09:29:21.441075+00:00"},{"alias_kind":"pith_short_8","alias_value":"AFFMKTIT","created_at":"2026-07-05T09:29:21.441075+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2607.08436","citing_title":"EgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Data","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2607.08639","citing_title":"Native Video-Action Pretraining for Generalizable Robot Control","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2607.06988","citing_title":"WAM-TTT: Steering World-Action Models by Watching Human Play at Test Time","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20781","citing_title":"World Action Models: A Survey","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20521","citing_title":"HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17055","citing_title":"T-Rex: Tactile-Reactive Dexterous Manipulation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17054","citing_title":"Human Universal Grasping","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12604","citing_title":"EgoEngine: From Egocentric Human Videos to High-Fidelity Dexterous Robot Demonstrations","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05945","citing_title":"MobileEgo Anywhere: Open Infrastructure for long horizon egocentric data on commodity hardware","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29298","citing_title":"MonoDuo: Using One Robot Arm to Learn Bimanual Policies","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30957","citing_title":"RDGen: Demonstration Generation for High-Quality Robot Learning via Reinforcement Learning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2507.05331","citing_title":"A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulation","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2507.12440","citing_title":"EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2507.00990","citing_title":"Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2509.21723","citing_title":"VLBiMan: Vision-Language Anchored One-Shot Demonstration Enables Generalizable Bimanual Robotic Manipulation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2511.12878","citing_title":"Uni-Hand: Universal Hand Motion Forecasting in Egocentric Views","ref_index":2,"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":235,"is_internal_anchor":false},{"citing_arxiv_id":"2507.15493","citing_title":"GR-3 Technical Report","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":197,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03637","citing_title":"Bridging the Embodiment Gap: Disentangled Cross-Embodiment Video Editing","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09613","citing_title":"SABER: A Scalable Action-Based Embodied Dataset for Real-World VLA Adaptation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07331","citing_title":"RoSHI: A Versatile Robot-oriented Suit for Human Data In-the-Wild","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06747","citing_title":"HumanNet: Scaling Human-centric Video Learning to One Million Hours","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AFFMKTITHRS22UR742O76OUOHX","json":"https://pith.science/pith/AFFMKTITHRS22UR742O76OUOHX.json","graph_json":"https://pith.science/api/pith-number/AFFMKTITHRS22UR742O76OUOHX/graph.json","events_json":"https://pith.science/api/pith-number/AFFMKTITHRS22UR742O76OUOHX/events.json","paper":"https://pith.science/paper/AFFMKTIT"},"agent_actions":{"view_html":"https://pith.science/pith/AFFMKTITHRS22UR742O76OUOHX","download_json":"https://pith.science/pith/AFFMKTITHRS22UR742O76OUOHX.json","view_paper":"https://pith.science/paper/AFFMKTIT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.24221&json=true","fetch_graph":"https://pith.science/api/pith-number/AFFMKTITHRS22UR742O76OUOHX/graph.json","fetch_events":"https://pith.science/api/pith-number/AFFMKTITHRS22UR742O76OUOHX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AFFMKTITHRS22UR742O76OUOHX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AFFMKTITHRS22UR742O76OUOHX/action/storage_attestation","attest_author":"https://pith.science/pith/AFFMKTITHRS22UR742O76OUOHX/action/author_attestation","sign_citation":"https://pith.science/pith/AFFMKTITHRS22UR742O76OUOHX/action/citation_signature","submit_replication":"https://pith.science/pith/AFFMKTITHRS22UR742O76OUOHX/action/replication_record"}},"created_at":"2026-07-05T09:29:21.441075+00:00","updated_at":"2026-07-05T09:29:21.441075+00:00"}