{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HX2D5TMJI2VW6HZRKRIGGVPCPD","short_pith_number":"pith:HX2D5TMJ","schema_version":"1.0","canonical_sha256":"3df43ecd8946ab6f1f3154506355e278fe2e5424d73adfa90444305bbe937c3a","source":{"kind":"arxiv","id":"2603.09170","version":2},"attestation_state":"computed","paper":{"title":"ZeroWBC: Learning Natural Whole-Body Humanoid Interaction from Human Egocentric Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Bin Zhao, Dong Wang, Haoming Song, Haoran Yang, Jiacheng Bao, Xuelong Li, Yucheng Xin, Yuyang Tian","submitted_at":"2026-03-10T04:19:43Z","abstract_excerpt":"Achieving versatile and natural whole-body humanoid interaction control remains challenging due to the high cost of whole-body teleoperation data. We present ZeroWBC, a teleoperation-free framework that learns humanoid whole-body interaction from human egocentric videos paired with synchronized whole-body motion and text annotations. ZeroWBC adopts a generation-then-tracking formulation to tackle the static scene whole-body interaction control problem. Given an initial egocentric image and a language instruction, a fine-tuned Vision-Language Model generates future human whole-body motion token"},"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":"2603.09170","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-03-10T04:19:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ba53252c0c7c9cfc00fdad9c0a89dfdc800143703a272e775464e4f4616ec44e","abstract_canon_sha256":"01e749fc32163bd13eaeb760e93c19f9ef6b4ff22a132d916be9ade0c8f1556b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:47.721863Z","signature_b64":"3JNqdJb/KkPGMKr185KHLeVIcVHkhbPQbHTcR3z+bqWehox/6WQ15IrrHo2gptfdB8aTCaKobUIKBCrbi7oZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3df43ecd8946ab6f1f3154506355e278fe2e5424d73adfa90444305bbe937c3a","last_reissued_at":"2026-06-04T01:08:47.721347Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:47.721347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ZeroWBC: Learning Natural Whole-Body Humanoid Interaction from Human Egocentric Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Bin Zhao, Dong Wang, Haoming Song, Haoran Yang, Jiacheng Bao, Xuelong Li, Yucheng Xin, Yuyang Tian","submitted_at":"2026-03-10T04:19:43Z","abstract_excerpt":"Achieving versatile and natural whole-body humanoid interaction control remains challenging due to the high cost of whole-body teleoperation data. We present ZeroWBC, a teleoperation-free framework that learns humanoid whole-body interaction from human egocentric videos paired with synchronized whole-body motion and text annotations. ZeroWBC adopts a generation-then-tracking formulation to tackle the static scene whole-body interaction control problem. Given an initial egocentric image and a language instruction, a fine-tuned Vision-Language Model generates future human whole-body motion token"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.09170","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/2603.09170/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":"2603.09170","created_at":"2026-06-04T01:08:47.721411+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.09170v2","created_at":"2026-06-04T01:08:47.721411+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.09170","created_at":"2026-06-04T01:08:47.721411+00:00"},{"alias_kind":"pith_short_12","alias_value":"HX2D5TMJI2VW","created_at":"2026-06-04T01:08:47.721411+00:00"},{"alias_kind":"pith_short_16","alias_value":"HX2D5TMJI2VW6HZR","created_at":"2026-06-04T01:08:47.721411+00:00"},{"alias_kind":"pith_short_8","alias_value":"HX2D5TMJ","created_at":"2026-06-04T01:08:47.721411+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2605.22272","citing_title":"Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priors","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22272","citing_title":"Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priors","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07993","citing_title":"HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body Manipulation","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23570","citing_title":"EgoLive: A Large-Scale Egocentric Dataset from Real-World Human Tasks","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07993","citing_title":"HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body Manipulation","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HX2D5TMJI2VW6HZRKRIGGVPCPD","json":"https://pith.science/pith/HX2D5TMJI2VW6HZRKRIGGVPCPD.json","graph_json":"https://pith.science/api/pith-number/HX2D5TMJI2VW6HZRKRIGGVPCPD/graph.json","events_json":"https://pith.science/api/pith-number/HX2D5TMJI2VW6HZRKRIGGVPCPD/events.json","paper":"https://pith.science/paper/HX2D5TMJ"},"agent_actions":{"view_html":"https://pith.science/pith/HX2D5TMJI2VW6HZRKRIGGVPCPD","download_json":"https://pith.science/pith/HX2D5TMJI2VW6HZRKRIGGVPCPD.json","view_paper":"https://pith.science/paper/HX2D5TMJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.09170&json=true","fetch_graph":"https://pith.science/api/pith-number/HX2D5TMJI2VW6HZRKRIGGVPCPD/graph.json","fetch_events":"https://pith.science/api/pith-number/HX2D5TMJI2VW6HZRKRIGGVPCPD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HX2D5TMJI2VW6HZRKRIGGVPCPD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HX2D5TMJI2VW6HZRKRIGGVPCPD/action/storage_attestation","attest_author":"https://pith.science/pith/HX2D5TMJI2VW6HZRKRIGGVPCPD/action/author_attestation","sign_citation":"https://pith.science/pith/HX2D5TMJI2VW6HZRKRIGGVPCPD/action/citation_signature","submit_replication":"https://pith.science/pith/HX2D5TMJI2VW6HZRKRIGGVPCPD/action/replication_record"}},"created_at":"2026-06-04T01:08:47.721411+00:00","updated_at":"2026-06-04T01:08:47.721411+00:00"}