{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UZA5YTVKLNWUESL6EN5OTMXFEH","short_pith_number":"pith:UZA5YTVK","schema_version":"1.0","canonical_sha256":"a641dc4eaa5b6d42497e237ae9b2e521c1b4194088934af005e0289b3f787d3e","source":{"kind":"arxiv","id":"2410.11825","version":3},"attestation_state":"computed","paper":{"title":"Learning Smooth Humanoid Locomotion through Lipschitz-Constrained Policies","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Jiajun Wu, Koushil Sreenath, Qiayuan Liao, Saurabh Gupta, S. Shankar Sastry, Xialin He, Xue Bin Peng, Yanjie Ze, Yen-Jen Wang, Zhongyu Li, Zixuan Chen","submitted_at":"2024-10-15T17:52:20Z","abstract_excerpt":"Reinforcement learning combined with sim-to-real transfer offers a general framework for developing locomotion controllers for legged robots. To facilitate successful deployment in the real world, smoothing techniques, such as low-pass filters and smoothness rewards, are often employed to develop policies with smooth behaviors. However, because these techniques are non-differentiable and usually require tedious tuning of a large set of hyperparameters, they tend to require extensive manual tuning for each robotic platform. To address this challenge and establish a general technique for enforci"},"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":"2410.11825","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-15T17:52:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7cfd4d3aaa6892462cd251f40dbe41872d0f3f628aebdd0279dd27581d02ad7f","abstract_canon_sha256":"a09005d1aaff2c1d7fa12d312fa812d00db2337b7826e17657b31f10ca2a512e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:06.260425Z","signature_b64":"eug16TQRbpdiVVynFOSXEEogCR5GlkqEADpiQ6j1/uN7BFzG5eyxIZb56PWd7l8pQofMk20/SyYzWZ+yXY9DAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a641dc4eaa5b6d42497e237ae9b2e521c1b4194088934af005e0289b3f787d3e","last_reissued_at":"2026-07-05T09:27:06.259024Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:06.259024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Smooth Humanoid Locomotion through Lipschitz-Constrained Policies","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Jiajun Wu, Koushil Sreenath, Qiayuan Liao, Saurabh Gupta, S. Shankar Sastry, Xialin He, Xue Bin Peng, Yanjie Ze, Yen-Jen Wang, Zhongyu Li, Zixuan Chen","submitted_at":"2024-10-15T17:52:20Z","abstract_excerpt":"Reinforcement learning combined with sim-to-real transfer offers a general framework for developing locomotion controllers for legged robots. To facilitate successful deployment in the real world, smoothing techniques, such as low-pass filters and smoothness rewards, are often employed to develop policies with smooth behaviors. However, because these techniques are non-differentiable and usually require tedious tuning of a large set of hyperparameters, they tend to require extensive manual tuning for each robotic platform. To address this challenge and establish a general technique for enforci"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11825","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/2410.11825/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":"2410.11825","created_at":"2026-07-05T09:27:06.259924+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.11825v3","created_at":"2026-07-05T09:27:06.259924+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11825","created_at":"2026-07-05T09:27:06.259924+00:00"},{"alias_kind":"pith_short_12","alias_value":"UZA5YTVKLNWU","created_at":"2026-07-05T09:27:06.259924+00:00"},{"alias_kind":"pith_short_16","alias_value":"UZA5YTVKLNWUESL6","created_at":"2026-07-05T09:27:06.259924+00:00"},{"alias_kind":"pith_short_8","alias_value":"UZA5YTVK","created_at":"2026-07-05T09:27:06.259924+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09758","citing_title":"Difference-Aware Retrieval Policies for Imitation Learning","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2509.13095","citing_title":"Empowering Multi-Robot Cooperation via Sequential World Models","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UZA5YTVKLNWUESL6EN5OTMXFEH","json":"https://pith.science/pith/UZA5YTVKLNWUESL6EN5OTMXFEH.json","graph_json":"https://pith.science/api/pith-number/UZA5YTVKLNWUESL6EN5OTMXFEH/graph.json","events_json":"https://pith.science/api/pith-number/UZA5YTVKLNWUESL6EN5OTMXFEH/events.json","paper":"https://pith.science/paper/UZA5YTVK"},"agent_actions":{"view_html":"https://pith.science/pith/UZA5YTVKLNWUESL6EN5OTMXFEH","download_json":"https://pith.science/pith/UZA5YTVKLNWUESL6EN5OTMXFEH.json","view_paper":"https://pith.science/paper/UZA5YTVK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.11825&json=true","fetch_graph":"https://pith.science/api/pith-number/UZA5YTVKLNWUESL6EN5OTMXFEH/graph.json","fetch_events":"https://pith.science/api/pith-number/UZA5YTVKLNWUESL6EN5OTMXFEH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UZA5YTVKLNWUESL6EN5OTMXFEH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UZA5YTVKLNWUESL6EN5OTMXFEH/action/storage_attestation","attest_author":"https://pith.science/pith/UZA5YTVKLNWUESL6EN5OTMXFEH/action/author_attestation","sign_citation":"https://pith.science/pith/UZA5YTVKLNWUESL6EN5OTMXFEH/action/citation_signature","submit_replication":"https://pith.science/pith/UZA5YTVKLNWUESL6EN5OTMXFEH/action/replication_record"}},"created_at":"2026-07-05T09:27:06.259924+00:00","updated_at":"2026-07-05T09:27:06.259924+00:00"}