{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NPKCWRO7GKG5NRCBBO3YCFXGSE","short_pith_number":"pith:NPKCWRO7","schema_version":"1.0","canonical_sha256":"6bd42b45df328dd6c4410bb78116e691279f23e002a792bca914914b80750360","source":{"kind":"arxiv","id":"2509.20717","version":2},"attestation_state":"computed","paper":{"title":"RobotDancing: Residual-Action Reinforcement Learning Enables Robust Long-Horizon Humanoid Motion Tracking","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Alois Knoll, Bo-Sheng Huang, Xinlong Wang, Xukun Li, Yibo Peng, Yuan Meng, Zhenguo Sun, Zhenshan Bing","submitted_at":"2025-09-25T03:30:34Z","abstract_excerpt":"Long-horizon, high-dynamic motion tracking on humanoids remains brittle: retargeted reference motions are typically kinematically plausible but dynamically inconsistent with the robot, so small tracking errors accumulate and eventually destabilize control. We present RobotDancing, a practical single-stage reinforcement learning recipe that tracks retargeted motions by predicting reference-conditioned residual joint targets. By parameterizing actions as residual corrections on top of the reference, the policy can focus on compensating reference--robot dynamics mismatch (e.g., actuation limits, "},"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":"2509.20717","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-09-25T03:30:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a61227926af140e6fece660906ed5f96a2212adfc3edf378567846232e23c867","abstract_canon_sha256":"5034757b8eae544bdff26daef653ff8f3ba9538c544435149cd55130e2da524e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T01:57:54.501786Z","signature_b64":"nhykDyZ0AV8MCeAky9lDosp31s1wka8l8EdEg88J/07k6hHEADKskiBF8bjZnoK6XvI8j3vRYar06g9B4Zw/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bd42b45df328dd6c4410bb78116e691279f23e002a792bca914914b80750360","last_reissued_at":"2026-08-04T01:57:54.500059Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T01:57:54.500059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RobotDancing: Residual-Action Reinforcement Learning Enables Robust Long-Horizon Humanoid Motion Tracking","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Alois Knoll, Bo-Sheng Huang, Xinlong Wang, Xukun Li, Yibo Peng, Yuan Meng, Zhenguo Sun, Zhenshan Bing","submitted_at":"2025-09-25T03:30:34Z","abstract_excerpt":"Long-horizon, high-dynamic motion tracking on humanoids remains brittle: retargeted reference motions are typically kinematically plausible but dynamically inconsistent with the robot, so small tracking errors accumulate and eventually destabilize control. We present RobotDancing, a practical single-stage reinforcement learning recipe that tracks retargeted motions by predicting reference-conditioned residual joint targets. By parameterizing actions as residual corrections on top of the reference, the policy can focus on compensating reference--robot dynamics mismatch (e.g., actuation limits, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.20717","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/2509.20717/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":"2509.20717","created_at":"2026-08-04T01:57:54.501410+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.20717v2","created_at":"2026-08-04T01:57:54.501410+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.20717","created_at":"2026-08-04T01:57:54.501410+00:00"},{"alias_kind":"pith_short_12","alias_value":"NPKCWRO7GKG5","created_at":"2026-08-04T01:57:54.501410+00:00"},{"alias_kind":"pith_short_16","alias_value":"NPKCWRO7GKG5NRCB","created_at":"2026-08-04T01:57:54.501410+00:00"},{"alias_kind":"pith_short_8","alias_value":"NPKCWRO7","created_at":"2026-08-04T01:57:54.501410+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.12814","citing_title":"Stubborn: A Streamlined and Unified Reinforcement Learning Framework for Robust Motion Tracking and Fall Recovery for Humanoids","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NPKCWRO7GKG5NRCBBO3YCFXGSE","json":"https://pith.science/pith/NPKCWRO7GKG5NRCBBO3YCFXGSE.json","graph_json":"https://pith.science/api/pith-number/NPKCWRO7GKG5NRCBBO3YCFXGSE/graph.json","events_json":"https://pith.science/api/pith-number/NPKCWRO7GKG5NRCBBO3YCFXGSE/events.json","paper":"https://pith.science/paper/NPKCWRO7"},"agent_actions":{"view_html":"https://pith.science/pith/NPKCWRO7GKG5NRCBBO3YCFXGSE","download_json":"https://pith.science/pith/NPKCWRO7GKG5NRCBBO3YCFXGSE.json","view_paper":"https://pith.science/paper/NPKCWRO7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.20717&json=true","fetch_graph":"https://pith.science/api/pith-number/NPKCWRO7GKG5NRCBBO3YCFXGSE/graph.json","fetch_events":"https://pith.science/api/pith-number/NPKCWRO7GKG5NRCBBO3YCFXGSE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NPKCWRO7GKG5NRCBBO3YCFXGSE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NPKCWRO7GKG5NRCBBO3YCFXGSE/action/storage_attestation","attest_author":"https://pith.science/pith/NPKCWRO7GKG5NRCBBO3YCFXGSE/action/author_attestation","sign_citation":"https://pith.science/pith/NPKCWRO7GKG5NRCBBO3YCFXGSE/action/citation_signature","submit_replication":"https://pith.science/pith/NPKCWRO7GKG5NRCBBO3YCFXGSE/action/replication_record"}},"created_at":"2026-08-04T01:57:54.501410+00:00","updated_at":"2026-08-04T01:57:54.501410+00:00"}