{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7QLGLLWGFUUKZPCCJ44T36P4XO","short_pith_number":"pith:7QLGLLWG","schema_version":"1.0","canonical_sha256":"fc1665aec62d28acbc424f393df9fcbba1f42bc305d224e2be38e2ae48be351e","source":{"kind":"arxiv","id":"2603.03243","version":2},"attestation_state":"computed","paper":{"title":"HoMMI: Learning Whole-Body Mobile Manipulation from Human Demonstrations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Aditya Bhat, Dian Wang, Eric Cousineau, Han Zhang, Jeannette Bohg, Jisang Park, Jose Barreiros, Shuran Song, Xiaomeng Xu","submitted_at":"2026-03-03T18:36:49Z","abstract_excerpt":"We present Whole-Body Mobile Manipulation Interface (HoMMI), a data collection and policy learning framework that learns whole-body mobile manipulation directly from robot-free human demonstrations. We augment UMI interfaces with egocentric sensing to capture the global context required for mobile manipulation, enabling portable, robot-free, and scalable data collection. However, naively incorporating egocentric sensing introduces a larger human-to-robot embodiment gap in both observation and action spaces, making policy transfer difficult. We explicitly bridge this gap with a cross-embodiment"},"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":"2603.03243","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-03-03T18:36:49Z","cross_cats_sorted":[],"title_canon_sha256":"8d8d9d7a27dc624e717918d13f34cd625f97341ef786be6933f1e309014ce7af","abstract_canon_sha256":"f0a4773414d56d0606dafb07a5980eb3efef5003b18f08aa14733c0935b555ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:35.597075Z","signature_b64":"9Leb37kppR9najWivEryxRATy6Dek4GQrrzxwkvTXfKFh+Ll1yk0YYxF6xrnf2ZBSbmhye+5wdDs4isqvhZ1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc1665aec62d28acbc424f393df9fcbba1f42bc305d224e2be38e2ae48be351e","last_reissued_at":"2026-05-20T00:00:35.596460Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:35.596460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HoMMI: Learning Whole-Body Mobile Manipulation from Human Demonstrations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Aditya Bhat, Dian Wang, Eric Cousineau, Han Zhang, Jeannette Bohg, Jisang Park, Jose Barreiros, Shuran Song, Xiaomeng Xu","submitted_at":"2026-03-03T18:36:49Z","abstract_excerpt":"We present Whole-Body Mobile Manipulation Interface (HoMMI), a data collection and policy learning framework that learns whole-body mobile manipulation directly from robot-free human demonstrations. We augment UMI interfaces with egocentric sensing to capture the global context required for mobile manipulation, enabling portable, robot-free, and scalable data collection. However, naively incorporating egocentric sensing introduces a larger human-to-robot embodiment gap in both observation and action spaces, making policy transfer difficult. We explicitly bridge this gap with a cross-embodiment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.03243","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/2603.03243/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":"2603.03243","created_at":"2026-05-20T00:00:35.596567+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.03243v2","created_at":"2026-05-20T00:00:35.596567+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.03243","created_at":"2026-05-20T00:00:35.596567+00:00"},{"alias_kind":"pith_short_12","alias_value":"7QLGLLWGFUUK","created_at":"2026-05-20T00:00:35.596567+00:00"},{"alias_kind":"pith_short_16","alias_value":"7QLGLLWGFUUKZPCC","created_at":"2026-05-20T00:00:35.596567+00:00"},{"alias_kind":"pith_short_8","alias_value":"7QLGLLWG","created_at":"2026-05-20T00:00:35.596567+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.16797","citing_title":"EgoKit: Towards Unified Low-Cost Egocentric Data Collection with Heterogeneous Devices","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":161,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03452","citing_title":"BifrostUMI: Bridging Robot-Free Demonstrations and Humanoid Whole-Body Manipulation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22615","citing_title":"GazeVLA: Learning Human Intention for Robotic Manipulation","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14089","citing_title":"UMI-3D: Extending Universal Manipulation Interface from Vision-Limited to 3D Spatial Perception","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08534","citing_title":"ActiveGlasses: Learning Manipulation with Active Vision from Ego-centric Human Demonstration","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7QLGLLWGFUUKZPCCJ44T36P4XO","json":"https://pith.science/pith/7QLGLLWGFUUKZPCCJ44T36P4XO.json","graph_json":"https://pith.science/api/pith-number/7QLGLLWGFUUKZPCCJ44T36P4XO/graph.json","events_json":"https://pith.science/api/pith-number/7QLGLLWGFUUKZPCCJ44T36P4XO/events.json","paper":"https://pith.science/paper/7QLGLLWG"},"agent_actions":{"view_html":"https://pith.science/pith/7QLGLLWGFUUKZPCCJ44T36P4XO","download_json":"https://pith.science/pith/7QLGLLWGFUUKZPCCJ44T36P4XO.json","view_paper":"https://pith.science/paper/7QLGLLWG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.03243&json=true","fetch_graph":"https://pith.science/api/pith-number/7QLGLLWGFUUKZPCCJ44T36P4XO/graph.json","fetch_events":"https://pith.science/api/pith-number/7QLGLLWGFUUKZPCCJ44T36P4XO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7QLGLLWGFUUKZPCCJ44T36P4XO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7QLGLLWGFUUKZPCCJ44T36P4XO/action/storage_attestation","attest_author":"https://pith.science/pith/7QLGLLWGFUUKZPCCJ44T36P4XO/action/author_attestation","sign_citation":"https://pith.science/pith/7QLGLLWGFUUKZPCCJ44T36P4XO/action/citation_signature","submit_replication":"https://pith.science/pith/7QLGLLWGFUUKZPCCJ44T36P4XO/action/replication_record"}},"created_at":"2026-05-20T00:00:35.596567+00:00","updated_at":"2026-05-20T00:00:35.596567+00:00"}