{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:T3RKL6MLNEJIA3QRQKNUXEPHMZ","short_pith_number":"pith:T3RKL6ML","schema_version":"1.0","canonical_sha256":"9ee2a5f98b6912806e11829b4b91e76647b42fbe1987468f545d3c6fc27b76c1","source":{"kind":"arxiv","id":"2511.07820","version":3},"attestation_state":"computed","paper":{"title":"SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.GR","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Chenran Li, Cyrus Hogg, David Minor, David Sami, Edy Lim, Eugene Jeong, Fernando Casta\\~neda, Haoru Xue, Jan Kautz, Jiefeng Li, Jinhyung Park, Lina Song, Linxi \"Jim\" Fan, Qingwei Ben, Runyu Ding, Simon Yuen, Sirui Chen, Tairan He, Tingwu Wang, Umar Iqbal, Wenli Xiao, Xingye Da, Yan Chang, Ye Yuan, Yuke Zhu, Zhengyi Luo, Zi-Ang Cao, Zi Wang","submitted_at":"2025-11-11T04:37:40Z","abstract_excerpt":"Despite the rise of billion-parameter foundation models trained across thousands of GPUs, similar scaling gains have not been shown for humanoid control. Current neural controllers for humanoids remain modest in size, target a limited set of behaviors, and are trained on a handful of GPUs. We show that scaling model capacity, data, and compute yields a generalist humanoid controller capable of natural, robust whole-body movements. We position motion tracking as a scalable task for humanoid control, leveraging dense supervision from diverse motion-capture data to acquire human motion priors wit"},"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":"2511.07820","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-11-11T04:37:40Z","cross_cats_sorted":["cs.AI","cs.CV","cs.GR","cs.SY","eess.SY"],"title_canon_sha256":"4218a49473742cf71d9db04fd867bec56dd4f901e70a8fceab9bf17fce85df58","abstract_canon_sha256":"bfe657780eeb157d48347b61559130fb2e6bcd2533de76fee902bbf36f83699a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T02:04:38.134933Z","signature_b64":"dk0VFuFdYOh11MpHJrbXeP7n04Hhbzqq9rICX6gcX6faBASGbd/85Fd0vc1xcjRzcjmhFe9C9xCSO9qlw+3JAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ee2a5f98b6912806e11829b4b91e76647b42fbe1987468f545d3c6fc27b76c1","last_reissued_at":"2026-05-22T02:04:38.134085Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T02:04:38.134085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.GR","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Chenran Li, Cyrus Hogg, David Minor, David Sami, Edy Lim, Eugene Jeong, Fernando Casta\\~neda, Haoru Xue, Jan Kautz, Jiefeng Li, Jinhyung Park, Lina Song, Linxi \"Jim\" Fan, Qingwei Ben, Runyu Ding, Simon Yuen, Sirui Chen, Tairan He, Tingwu Wang, Umar Iqbal, Wenli Xiao, Xingye Da, Yan Chang, Ye Yuan, Yuke Zhu, Zhengyi Luo, Zi-Ang Cao, Zi Wang","submitted_at":"2025-11-11T04:37:40Z","abstract_excerpt":"Despite the rise of billion-parameter foundation models trained across thousands of GPUs, similar scaling gains have not been shown for humanoid control. Current neural controllers for humanoids remain modest in size, target a limited set of behaviors, and are trained on a handful of GPUs. We show that scaling model capacity, data, and compute yields a generalist humanoid controller capable of natural, robust whole-body movements. We position motion tracking as a scalable task for humanoid control, leveraging dense supervision from diverse motion-capture data to acquire human motion priors wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.07820","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/2511.07820/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":"2511.07820","created_at":"2026-05-22T02:04:38.134206+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.07820v3","created_at":"2026-05-22T02:04:38.134206+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.07820","created_at":"2026-05-22T02:04:38.134206+00:00"},{"alias_kind":"pith_short_12","alias_value":"T3RKL6MLNEJI","created_at":"2026-05-22T02:04:38.134206+00:00"},{"alias_kind":"pith_short_16","alias_value":"T3RKL6MLNEJIA3QR","created_at":"2026-05-22T02:04:38.134206+00:00"},{"alias_kind":"pith_short_8","alias_value":"T3RKL6ML","created_at":"2026-05-22T02:04:38.134206+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":15,"sample":[{"citing_arxiv_id":"2604.07993","citing_title":"HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body Manipulation","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15336","citing_title":"HoloMotion-1 Technical Report","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19981","citing_title":"CEER: Compliant End-Effector and Root Control as a Unified Interface for Hierarchical Humanoid Loco-Manipulation","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15336","citing_title":"HoloMotion-1 Technical Report","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2602.09628","citing_title":"TeleGate: Whole-Body Humanoid Teleoperation via Gated Expert Selection with Motion Prior","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2602.11758","citing_title":"HAIC: Humanoid Agile Object Interaction Control via Dynamics-Aware World Model","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2602.15827","citing_title":"Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27711","citing_title":"ExoActor: Exocentric Video Generation as Generalizable Interactive Humanoid Control","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01518","citing_title":"VOFA: Visual Object Goal Pushing with Force-Adaptive Control for Humanoids","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13015","citing_title":"Learning Versatile Humanoid Manipulation with Touch Dreaming","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2604.12909","citing_title":"Tree Learning: A Multi-Skill Continual Learning Framework for Humanoid Robots","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11251","citing_title":"CLAW: Composable Language-Annotated Whole-body Motion Generation","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08508","citing_title":"Sumo: Dynamic and Generalizable Whole-Body Loco-Manipulation","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07993","citing_title":"HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body Manipulation","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17335","citing_title":"Learning Whole-Body Humanoid Locomotion via Motion Generation and Motion Tracking","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T3RKL6MLNEJIA3QRQKNUXEPHMZ","json":"https://pith.science/pith/T3RKL6MLNEJIA3QRQKNUXEPHMZ.json","graph_json":"https://pith.science/api/pith-number/T3RKL6MLNEJIA3QRQKNUXEPHMZ/graph.json","events_json":"https://pith.science/api/pith-number/T3RKL6MLNEJIA3QRQKNUXEPHMZ/events.json","paper":"https://pith.science/paper/T3RKL6ML"},"agent_actions":{"view_html":"https://pith.science/pith/T3RKL6MLNEJIA3QRQKNUXEPHMZ","download_json":"https://pith.science/pith/T3RKL6MLNEJIA3QRQKNUXEPHMZ.json","view_paper":"https://pith.science/paper/T3RKL6ML","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.07820&json=true","fetch_graph":"https://pith.science/api/pith-number/T3RKL6MLNEJIA3QRQKNUXEPHMZ/graph.json","fetch_events":"https://pith.science/api/pith-number/T3RKL6MLNEJIA3QRQKNUXEPHMZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T3RKL6MLNEJIA3QRQKNUXEPHMZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T3RKL6MLNEJIA3QRQKNUXEPHMZ/action/storage_attestation","attest_author":"https://pith.science/pith/T3RKL6MLNEJIA3QRQKNUXEPHMZ/action/author_attestation","sign_citation":"https://pith.science/pith/T3RKL6MLNEJIA3QRQKNUXEPHMZ/action/citation_signature","submit_replication":"https://pith.science/pith/T3RKL6MLNEJIA3QRQKNUXEPHMZ/action/replication_record"}},"created_at":"2026-05-22T02:04:38.134206+00:00","updated_at":"2026-05-22T02:04:38.134206+00:00"}