{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QPYO4P72NM6PX26JDNIBWGZIDK","short_pith_number":"pith:QPYO4P72","schema_version":"1.0","canonical_sha256":"83f0ee3ffa6b3cfbebc91b501b1b281a8c177fa0e5fe690e8744470b0da21f5e","source":{"kind":"arxiv","id":"2503.03081","version":3},"attestation_state":"computed","paper":{"title":"AirExo-2: Scaling up Generalizable Robotic Imitation Learning with Low-Cost Exoskeletons","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Cewu Lu, Chenxi Wang, Hao-Shu Fang, Hongjie Fang, Jingjing Chen, Jun Lv, Lixin Yang, Shangning Xia, Weiming Wang, Xinyu Zhan, Xiyan Yi, Yiming Wang, Yunhan Guo, Zihao He","submitted_at":"2025-03-05T00:44:12Z","abstract_excerpt":"Scaling up robotic imitation learning for real-world applications requires efficient and scalable demonstration collection methods. While teleoperation is effective, it depends on costly and inflexible robot platforms. In-the-wild demonstrations offer a promising alternative, but existing collection devices have key limitations: handheld setups offer limited observational coverage, and whole-body systems often require fine-tuning with robot data due to domain gaps. To address these challenges, we present AirExo-2, a low-cost exoskeleton system for large-scale in-the-wild data collection, along"},"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":"2503.03081","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-03-05T00:44:12Z","cross_cats_sorted":[],"title_canon_sha256":"3210c5a903dc5a570db2a2c72bee76e074e3dc305456fadc67df8683194970d8","abstract_canon_sha256":"f74a56cda96bea00a662ffbd262f94f0131f3702d2ad8b3246afc108c273b4fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:25.670729Z","signature_b64":"v2tLDBk1waiYm38hJ0iJhg3xiqz7u0hVUm8raHRG+nDTdUDe27sPE8TJy9Z+ggepEKXvbLChIeTFzF/TX5DhDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83f0ee3ffa6b3cfbebc91b501b1b281a8c177fa0e5fe690e8744470b0da21f5e","last_reissued_at":"2026-07-05T11:58:25.670223Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:25.670223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AirExo-2: Scaling up Generalizable Robotic Imitation Learning with Low-Cost Exoskeletons","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Cewu Lu, Chenxi Wang, Hao-Shu Fang, Hongjie Fang, Jingjing Chen, Jun Lv, Lixin Yang, Shangning Xia, Weiming Wang, Xinyu Zhan, Xiyan Yi, Yiming Wang, Yunhan Guo, Zihao He","submitted_at":"2025-03-05T00:44:12Z","abstract_excerpt":"Scaling up robotic imitation learning for real-world applications requires efficient and scalable demonstration collection methods. While teleoperation is effective, it depends on costly and inflexible robot platforms. In-the-wild demonstrations offer a promising alternative, but existing collection devices have key limitations: handheld setups offer limited observational coverage, and whole-body systems often require fine-tuning with robot data due to domain gaps. To address these challenges, we present AirExo-2, a low-cost exoskeleton system for large-scale in-the-wild data collection, along"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.03081","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/2503.03081/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":"2503.03081","created_at":"2026-07-05T11:58:25.670281+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.03081v3","created_at":"2026-07-05T11:58:25.670281+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.03081","created_at":"2026-07-05T11:58:25.670281+00:00"},{"alias_kind":"pith_short_12","alias_value":"QPYO4P72NM6P","created_at":"2026-07-05T11:58:25.670281+00:00"},{"alias_kind":"pith_short_16","alias_value":"QPYO4P72NM6PX26J","created_at":"2026-07-05T11:58:25.670281+00:00"},{"alias_kind":"pith_short_8","alias_value":"QPYO4P72","created_at":"2026-07-05T11:58:25.670281+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.17001","citing_title":"Unify Robot Actions in Camera Frame","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15281","citing_title":"R3D: Revisiting 3D Policy Learning","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QPYO4P72NM6PX26JDNIBWGZIDK","json":"https://pith.science/pith/QPYO4P72NM6PX26JDNIBWGZIDK.json","graph_json":"https://pith.science/api/pith-number/QPYO4P72NM6PX26JDNIBWGZIDK/graph.json","events_json":"https://pith.science/api/pith-number/QPYO4P72NM6PX26JDNIBWGZIDK/events.json","paper":"https://pith.science/paper/QPYO4P72"},"agent_actions":{"view_html":"https://pith.science/pith/QPYO4P72NM6PX26JDNIBWGZIDK","download_json":"https://pith.science/pith/QPYO4P72NM6PX26JDNIBWGZIDK.json","view_paper":"https://pith.science/paper/QPYO4P72","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.03081&json=true","fetch_graph":"https://pith.science/api/pith-number/QPYO4P72NM6PX26JDNIBWGZIDK/graph.json","fetch_events":"https://pith.science/api/pith-number/QPYO4P72NM6PX26JDNIBWGZIDK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QPYO4P72NM6PX26JDNIBWGZIDK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QPYO4P72NM6PX26JDNIBWGZIDK/action/storage_attestation","attest_author":"https://pith.science/pith/QPYO4P72NM6PX26JDNIBWGZIDK/action/author_attestation","sign_citation":"https://pith.science/pith/QPYO4P72NM6PX26JDNIBWGZIDK/action/citation_signature","submit_replication":"https://pith.science/pith/QPYO4P72NM6PX26JDNIBWGZIDK/action/replication_record"}},"created_at":"2026-07-05T11:58:25.670281+00:00","updated_at":"2026-07-05T11:58:25.670281+00:00"}