{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YQVWSCYCL2GBBSCUO5WWQAIIGC","short_pith_number":"pith:YQVWSCYC","schema_version":"1.0","canonical_sha256":"c42b690b025e8c10c854776d68010830b04f457f965bcd55c664dc3bbe3e7550","source":{"kind":"arxiv","id":"2508.03068","version":2},"attestation_state":"computed","paper":{"title":"Hand-Eye Autonomous Delivery: Learning Humanoid Navigation, Locomotion and Reaching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"C. Karen Liu, Jennifer Lew, Pei Xu, Sirui Chen, Yufei Ye, Zi-Ang Cao","submitted_at":"2025-08-05T04:30:02Z","abstract_excerpt":"We propose Hand-Eye Autonomous Delivery (HEAD), a framework that learns navigation, locomotion, and reaching skills for humanoids, directly from human motion and vision perception data. We take a modular approach where the high-level planner commands the target position and orientation of the hands and eyes of the humanoid, delivered by the low-level policy that controls the whole-body movements. Specifically, the low-level whole-body controller learns to track the three points (eyes, left hand, and right hand) from existing large-scale human motion capture data while high-level policy learns "},"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":"2508.03068","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-08-05T04:30:02Z","cross_cats_sorted":[],"title_canon_sha256":"99d34cce901595e82618401ab2ede8b0d8e9fdca93045550f868849a8ee5eb80","abstract_canon_sha256":"9e60066f4e646ff4e673368ac2f65755d955bf01702ecabc172f6637b4cba97d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:39.708946Z","signature_b64":"s8f6Sz+SqTiCD1Rl2HmdZTqLhY0WMowkRNgHOGkhuaTS3SguI3r9c1Y9hcbvicFgsFMAWsMOzzfWhqcTV/eHBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c42b690b025e8c10c854776d68010830b04f457f965bcd55c664dc3bbe3e7550","last_reissued_at":"2026-07-05T11:50:39.708451Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:39.708451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hand-Eye Autonomous Delivery: Learning Humanoid Navigation, Locomotion and Reaching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"C. Karen Liu, Jennifer Lew, Pei Xu, Sirui Chen, Yufei Ye, Zi-Ang Cao","submitted_at":"2025-08-05T04:30:02Z","abstract_excerpt":"We propose Hand-Eye Autonomous Delivery (HEAD), a framework that learns navigation, locomotion, and reaching skills for humanoids, directly from human motion and vision perception data. We take a modular approach where the high-level planner commands the target position and orientation of the hands and eyes of the humanoid, delivered by the low-level policy that controls the whole-body movements. Specifically, the low-level whole-body controller learns to track the three points (eyes, left hand, and right hand) from existing large-scale human motion capture data while high-level policy learns "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.03068","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/2508.03068/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":"2508.03068","created_at":"2026-07-05T11:50:39.708510+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.03068v2","created_at":"2026-07-05T11:50:39.708510+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.03068","created_at":"2026-07-05T11:50:39.708510+00:00"},{"alias_kind":"pith_short_12","alias_value":"YQVWSCYCL2GB","created_at":"2026-07-05T11:50:39.708510+00:00"},{"alias_kind":"pith_short_16","alias_value":"YQVWSCYCL2GBBSCU","created_at":"2026-07-05T11:50:39.708510+00:00"},{"alias_kind":"pith_short_8","alias_value":"YQVWSCYC","created_at":"2026-07-05T11:50:39.708510+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30645","citing_title":"VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Scenes","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22272","citing_title":"Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priors","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22272","citing_title":"Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priors","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YQVWSCYCL2GBBSCUO5WWQAIIGC","json":"https://pith.science/pith/YQVWSCYCL2GBBSCUO5WWQAIIGC.json","graph_json":"https://pith.science/api/pith-number/YQVWSCYCL2GBBSCUO5WWQAIIGC/graph.json","events_json":"https://pith.science/api/pith-number/YQVWSCYCL2GBBSCUO5WWQAIIGC/events.json","paper":"https://pith.science/paper/YQVWSCYC"},"agent_actions":{"view_html":"https://pith.science/pith/YQVWSCYCL2GBBSCUO5WWQAIIGC","download_json":"https://pith.science/pith/YQVWSCYCL2GBBSCUO5WWQAIIGC.json","view_paper":"https://pith.science/paper/YQVWSCYC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.03068&json=true","fetch_graph":"https://pith.science/api/pith-number/YQVWSCYCL2GBBSCUO5WWQAIIGC/graph.json","fetch_events":"https://pith.science/api/pith-number/YQVWSCYCL2GBBSCUO5WWQAIIGC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YQVWSCYCL2GBBSCUO5WWQAIIGC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YQVWSCYCL2GBBSCUO5WWQAIIGC/action/storage_attestation","attest_author":"https://pith.science/pith/YQVWSCYCL2GBBSCUO5WWQAIIGC/action/author_attestation","sign_citation":"https://pith.science/pith/YQVWSCYCL2GBBSCUO5WWQAIIGC/action/citation_signature","submit_replication":"https://pith.science/pith/YQVWSCYCL2GBBSCUO5WWQAIIGC/action/replication_record"}},"created_at":"2026-07-05T11:50:39.708510+00:00","updated_at":"2026-07-05T11:50:39.708510+00:00"}