{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LVNGJWCJAOYAEWWHN33NDCWVC4","short_pith_number":"pith:LVNGJWCJ","schema_version":"1.0","canonical_sha256":"5d5a64d84903b0025ac76ef6d18ad51700ff8f8d04a62e17472e1e3c24c0b90e","source":{"kind":"arxiv","id":"2606.03985","version":1},"attestation_state":"computed","paper":{"title":"Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Chenghuai Lin, Dairu Liu, He Wang, Jilong Wang, Li Yi, Sikai Liang, Wenyao Zhang, Xinqiang Yu, Xuchuan Chen, Yu Guan, Yunrui Lian, Zekun Qi, Zhikai Zhang","submitted_at":"2026-06-02T17:59:05Z","abstract_excerpt":"We introduce Humanoid-GPT, a GPT-style Transformer with causal attention trained on a billion-scale motion corpus for whole-body control. Unlike prior shallow MLP trackers constrained by scarce data and an agility-generalization trade-off, Humanoid-GPT is pre-trained on a 2B-frame retargeted corpus that unifies all major mocap datasets with large-scale in-house recordings. Scaling both data and model capacity yields a single generative Transformer that tracks highly dynamic behaviors while achieving unprecedented zero-shot generalization to unseen motions and control tasks. Extensive experimen"},"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":"2606.03985","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-02T17:59:05Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"a187c06df8c9edefdf9ba7d50341ee9d59f379bc3dcbe37b939d45611cb49ce4","abstract_canon_sha256":"786f587250580558d5b34e510fb9580c28f0142d10080c565e79dc77bbaafc13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T02:06:08.754957Z","signature_b64":"bx6aKJYU2V9Kttm8FYtwxk0VyiX00HKgi/PiJY8UrX97eWdKASMEL1ir3I5+WvdMs+JWPknS4xhiAtRsh/LPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d5a64d84903b0025ac76ef6d18ad51700ff8f8d04a62e17472e1e3c24c0b90e","last_reissued_at":"2026-06-03T02:06:08.754521Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T02:06:08.754521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Chenghuai Lin, Dairu Liu, He Wang, Jilong Wang, Li Yi, Sikai Liang, Wenyao Zhang, Xinqiang Yu, Xuchuan Chen, Yu Guan, Yunrui Lian, Zekun Qi, Zhikai Zhang","submitted_at":"2026-06-02T17:59:05Z","abstract_excerpt":"We introduce Humanoid-GPT, a GPT-style Transformer with causal attention trained on a billion-scale motion corpus for whole-body control. Unlike prior shallow MLP trackers constrained by scarce data and an agility-generalization trade-off, Humanoid-GPT is pre-trained on a 2B-frame retargeted corpus that unifies all major mocap datasets with large-scale in-house recordings. Scaling both data and model capacity yields a single generative Transformer that tracks highly dynamic behaviors while achieving unprecedented zero-shot generalization to unseen motions and control tasks. Extensive experimen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03985","kind":"arxiv","version":1},"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/2606.03985/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":"2606.03985","created_at":"2026-06-03T02:06:08.754579+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03985v1","created_at":"2026-06-03T02:06:08.754579+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03985","created_at":"2026-06-03T02:06:08.754579+00:00"},{"alias_kind":"pith_short_12","alias_value":"LVNGJWCJAOYA","created_at":"2026-06-03T02:06:08.754579+00:00"},{"alias_kind":"pith_short_16","alias_value":"LVNGJWCJAOYAEWWH","created_at":"2026-06-03T02:06:08.754579+00:00"},{"alias_kind":"pith_short_8","alias_value":"LVNGJWCJ","created_at":"2026-06-03T02:06:08.754579+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LVNGJWCJAOYAEWWHN33NDCWVC4","json":"https://pith.science/pith/LVNGJWCJAOYAEWWHN33NDCWVC4.json","graph_json":"https://pith.science/api/pith-number/LVNGJWCJAOYAEWWHN33NDCWVC4/graph.json","events_json":"https://pith.science/api/pith-number/LVNGJWCJAOYAEWWHN33NDCWVC4/events.json","paper":"https://pith.science/paper/LVNGJWCJ"},"agent_actions":{"view_html":"https://pith.science/pith/LVNGJWCJAOYAEWWHN33NDCWVC4","download_json":"https://pith.science/pith/LVNGJWCJAOYAEWWHN33NDCWVC4.json","view_paper":"https://pith.science/paper/LVNGJWCJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03985&json=true","fetch_graph":"https://pith.science/api/pith-number/LVNGJWCJAOYAEWWHN33NDCWVC4/graph.json","fetch_events":"https://pith.science/api/pith-number/LVNGJWCJAOYAEWWHN33NDCWVC4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LVNGJWCJAOYAEWWHN33NDCWVC4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LVNGJWCJAOYAEWWHN33NDCWVC4/action/storage_attestation","attest_author":"https://pith.science/pith/LVNGJWCJAOYAEWWHN33NDCWVC4/action/author_attestation","sign_citation":"https://pith.science/pith/LVNGJWCJAOYAEWWHN33NDCWVC4/action/citation_signature","submit_replication":"https://pith.science/pith/LVNGJWCJAOYAEWWHN33NDCWVC4/action/replication_record"}},"created_at":"2026-06-03T02:06:08.754579+00:00","updated_at":"2026-06-03T02:06:08.754579+00:00"}