{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WXTYIVFTL7CGSLDKB4XLHA27RH","short_pith_number":"pith:WXTYIVFT","schema_version":"1.0","canonical_sha256":"b5e78454b35fc4692c6a0f2eb3835f89dba0edcd9de6a5e42fb543e973606a61","source":{"kind":"arxiv","id":"2502.04692","version":3},"attestation_state":"computed","paper":{"title":"STRIDE: Automating Reward Design, Deep Reinforcement Learning Training and Feedback Optimization in Humanoid Robotics Locomotion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Jinxiong Lu, Luhui Hu, Yueting Zhuang, Yunxin Liu, Yuxiao Chen, Zhenwei Wu","submitted_at":"2025-02-07T06:37:05Z","abstract_excerpt":"Humanoid robotics presents significant challenges in artificial intelligence, requiring precise coordination and control of high-degree-of-freedom systems. Designing effective reward functions for deep reinforcement learning (DRL) in this domain remains a critical bottleneck, demanding extensive manual effort, domain expertise, and iterative refinement. To overcome these challenges, we introduce STRIDE, a novel framework built on agentic engineering to automate reward design, DRL training, and feedback optimization for humanoid robot locomotion tasks. By combining the structured principles of "},"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":"2502.04692","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-02-07T06:37:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b12315d3f0881237d66e101fbc3c274dff299ce8b6a95a2b097374c7c57c232e","abstract_canon_sha256":"ee3fef4fc0ba915f979d81f39ecd5065b280f9cb226b7b04ea9878a67fcb762c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:08.446572Z","signature_b64":"PM+p5JpQ3kXIb8bo/qNckXw+XrsvXLU9n2EF6UoKQZleKsBql8M5iN6X2E7l5DvrSwWFllo3hNssVxkJE8ZmCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5e78454b35fc4692c6a0f2eb3835f89dba0edcd9de6a5e42fb543e973606a61","last_reissued_at":"2026-07-05T10:13:08.446016Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:08.446016Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STRIDE: Automating Reward Design, Deep Reinforcement Learning Training and Feedback Optimization in Humanoid Robotics Locomotion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Jinxiong Lu, Luhui Hu, Yueting Zhuang, Yunxin Liu, Yuxiao Chen, Zhenwei Wu","submitted_at":"2025-02-07T06:37:05Z","abstract_excerpt":"Humanoid robotics presents significant challenges in artificial intelligence, requiring precise coordination and control of high-degree-of-freedom systems. Designing effective reward functions for deep reinforcement learning (DRL) in this domain remains a critical bottleneck, demanding extensive manual effort, domain expertise, and iterative refinement. To overcome these challenges, we introduce STRIDE, a novel framework built on agentic engineering to automate reward design, DRL training, and feedback optimization for humanoid robot locomotion tasks. By combining the structured principles of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04692","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/2502.04692/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":"2502.04692","created_at":"2026-07-05T10:13:08.446071+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.04692v3","created_at":"2026-07-05T10:13:08.446071+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04692","created_at":"2026-07-05T10:13:08.446071+00:00"},{"alias_kind":"pith_short_12","alias_value":"WXTYIVFTL7CG","created_at":"2026-07-05T10:13:08.446071+00:00"},{"alias_kind":"pith_short_16","alias_value":"WXTYIVFTL7CGSLDK","created_at":"2026-07-05T10:13:08.446071+00:00"},{"alias_kind":"pith_short_8","alias_value":"WXTYIVFT","created_at":"2026-07-05T10:13:08.446071+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/WXTYIVFTL7CGSLDKB4XLHA27RH","json":"https://pith.science/pith/WXTYIVFTL7CGSLDKB4XLHA27RH.json","graph_json":"https://pith.science/api/pith-number/WXTYIVFTL7CGSLDKB4XLHA27RH/graph.json","events_json":"https://pith.science/api/pith-number/WXTYIVFTL7CGSLDKB4XLHA27RH/events.json","paper":"https://pith.science/paper/WXTYIVFT"},"agent_actions":{"view_html":"https://pith.science/pith/WXTYIVFTL7CGSLDKB4XLHA27RH","download_json":"https://pith.science/pith/WXTYIVFTL7CGSLDKB4XLHA27RH.json","view_paper":"https://pith.science/paper/WXTYIVFT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.04692&json=true","fetch_graph":"https://pith.science/api/pith-number/WXTYIVFTL7CGSLDKB4XLHA27RH/graph.json","fetch_events":"https://pith.science/api/pith-number/WXTYIVFTL7CGSLDKB4XLHA27RH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WXTYIVFTL7CGSLDKB4XLHA27RH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WXTYIVFTL7CGSLDKB4XLHA27RH/action/storage_attestation","attest_author":"https://pith.science/pith/WXTYIVFTL7CGSLDKB4XLHA27RH/action/author_attestation","sign_citation":"https://pith.science/pith/WXTYIVFTL7CGSLDKB4XLHA27RH/action/citation_signature","submit_replication":"https://pith.science/pith/WXTYIVFTL7CGSLDKB4XLHA27RH/action/replication_record"}},"created_at":"2026-07-05T10:13:08.446071+00:00","updated_at":"2026-07-05T10:13:08.446071+00:00"}