{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5IYMMIQDC5XVSIFXTMLYVDJOO6","short_pith_number":"pith:5IYMMIQD","schema_version":"1.0","canonical_sha256":"ea30c62203176f5920b79b178a8d2e778524db80bcc4f80c935afcb718e35977","source":{"kind":"arxiv","id":"2505.20290","version":2},"attestation_state":"computed","paper":{"title":"EgoZero: Robot Learning from Smart Glasses","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Ademi Adeniji, Haotian Zhan, Lerrel Pinto, Pieter Abbeel, Raunaq Bhirangi, Siddhant Haldar, Vincent Liu","submitted_at":"2025-05-26T17:59:17Z","abstract_excerpt":"Despite recent progress in general purpose robotics, robot policies still lag far behind basic human capabilities in the real world. Humans interact constantly with the physical world, yet this rich data resource remains largely untapped in robot learning. We propose EgoZero, a minimal system that learns robust manipulation policies from human demonstrations captured with Project Aria smart glasses, $\\textbf{and zero robot data}$. EgoZero enables: (1) extraction of complete, robot-executable actions from in-the-wild, egocentric, human demonstrations, (2) compression of human visual observation"},"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":"2505.20290","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-26T17:59:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1d231d72d4a89115055523d4126ac0375e863c99abc5f22fb3224652a9d77343","abstract_canon_sha256":"68f307ec8e5a6f3fb19b9a3a48d8be2bfe1fe6aee444e29f9161b6d80feae90a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:21.363632Z","signature_b64":"zwh27N+Y1DreaQRBoNQacVnJpfp4vvgBg3yIvi3Ll255GaGGClST+9VhgFEnnpdeGLwSnPmPsIiwFwylvRrvDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea30c62203176f5920b79b178a8d2e778524db80bcc4f80c935afcb718e35977","last_reissued_at":"2026-07-05T11:15:21.363144Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:21.363144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EgoZero: Robot Learning from Smart Glasses","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Ademi Adeniji, Haotian Zhan, Lerrel Pinto, Pieter Abbeel, Raunaq Bhirangi, Siddhant Haldar, Vincent Liu","submitted_at":"2025-05-26T17:59:17Z","abstract_excerpt":"Despite recent progress in general purpose robotics, robot policies still lag far behind basic human capabilities in the real world. Humans interact constantly with the physical world, yet this rich data resource remains largely untapped in robot learning. We propose EgoZero, a minimal system that learns robust manipulation policies from human demonstrations captured with Project Aria smart glasses, $\\textbf{and zero robot data}$. EgoZero enables: (1) extraction of complete, robot-executable actions from in-the-wild, egocentric, human demonstrations, (2) compression of human visual observation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20290","kind":"arxiv","version":2},"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/2505.20290/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":"2505.20290","created_at":"2026-07-05T11:15:21.363201+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20290v2","created_at":"2026-07-05T11:15:21.363201+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20290","created_at":"2026-07-05T11:15:21.363201+00:00"},{"alias_kind":"pith_short_12","alias_value":"5IYMMIQDC5XV","created_at":"2026-07-05T11:15:21.363201+00:00"},{"alias_kind":"pith_short_16","alias_value":"5IYMMIQDC5XVSIFX","created_at":"2026-07-05T11:15:21.363201+00:00"},{"alias_kind":"pith_short_8","alias_value":"5IYMMIQD","created_at":"2026-07-05T11:15:21.363201+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26588","citing_title":"Inference-Time Robot Behavior Steering through Physically-Aware Reconfiguration of Task-Structure","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19333","citing_title":"Do as I Do: Dexterous Manipulation Data from Everyday Human Videos","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17054","citing_title":"Human Universal Grasping","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12604","citing_title":"EgoEngine: From Egocentric Human Videos to High-Fidelity Dexterous Robot Demonstrations","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10743","citing_title":"Hand-centric Human-to-Robot Trajectory Transfer from Video Demonstrations via Open-World Contact Localization","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24934","citing_title":"HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28813","citing_title":"Human2Any: Human-to-Robot Transfer via Constraint-Aware Compositional Planning","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29940","citing_title":"WARP: Whole-Body Retargeting for Learning from Offline Human Demonstrations","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17200","citing_title":"ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretraining","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2511.04671","citing_title":"X-Diffusion: Training Diffusion Policies on Cross-Embodiment Human Demonstrations","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2602.06949","citing_title":"DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos","ref_index":65,"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":68,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07607","citing_title":"EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the World","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08534","citing_title":"ActiveGlasses: Learning Manipulation with Active Vision from Ego-centric Human Demonstration","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5IYMMIQDC5XVSIFXTMLYVDJOO6","json":"https://pith.science/pith/5IYMMIQDC5XVSIFXTMLYVDJOO6.json","graph_json":"https://pith.science/api/pith-number/5IYMMIQDC5XVSIFXTMLYVDJOO6/graph.json","events_json":"https://pith.science/api/pith-number/5IYMMIQDC5XVSIFXTMLYVDJOO6/events.json","paper":"https://pith.science/paper/5IYMMIQD"},"agent_actions":{"view_html":"https://pith.science/pith/5IYMMIQDC5XVSIFXTMLYVDJOO6","download_json":"https://pith.science/pith/5IYMMIQDC5XVSIFXTMLYVDJOO6.json","view_paper":"https://pith.science/paper/5IYMMIQD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20290&json=true","fetch_graph":"https://pith.science/api/pith-number/5IYMMIQDC5XVSIFXTMLYVDJOO6/graph.json","fetch_events":"https://pith.science/api/pith-number/5IYMMIQDC5XVSIFXTMLYVDJOO6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5IYMMIQDC5XVSIFXTMLYVDJOO6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5IYMMIQDC5XVSIFXTMLYVDJOO6/action/storage_attestation","attest_author":"https://pith.science/pith/5IYMMIQDC5XVSIFXTMLYVDJOO6/action/author_attestation","sign_citation":"https://pith.science/pith/5IYMMIQDC5XVSIFXTMLYVDJOO6/action/citation_signature","submit_replication":"https://pith.science/pith/5IYMMIQDC5XVSIFXTMLYVDJOO6/action/replication_record"}},"created_at":"2026-07-05T11:15:21.363201+00:00","updated_at":"2026-07-05T11:15:21.363201+00:00"}