{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JDW2Z2LSF4TZF2CS5ZL4LJQZXX","short_pith_number":"pith:JDW2Z2LS","schema_version":"1.0","canonical_sha256":"48edace9722f2792e852ee57c5a619bdc85544a3e10fd085586f5671945b0707","source":{"kind":"arxiv","id":"2509.18046","version":2},"attestation_state":"computed","paper":{"title":"HuMam: Humanoid Motion Control via End-to-End Deep Reinforcement Learning with Mamba","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.ET","cs.SY","eess.SP","eess.SY"],"primary_cat":"cs.RO","authors_text":"Jinzhao Zhou, Pengxiang Meng, Xiaowen Tao, Yinuo Wang, Yuanyang Qi","submitted_at":"2025-09-22T17:19:55Z","abstract_excerpt":"End-to-end reinforcement learning (RL) for humanoid locomotion is appealing for its compact perception-action mapping, yet practical policies often suffer from training instability, inefficient feature fusion, and high actuation cost. We present HuMam, a state-centric end-to-end RL framework that employs a single-layer Mamba encoder to fuse robot-centric states with oriented footstep targets and a continuous phase clock. The policy outputs joint position targets tracked by a low-level PD loop and is optimized with PPO. A concise six-term reward balances contact quality, swing smoothness, foot "},"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":"2509.18046","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.RO","submitted_at":"2025-09-22T17:19:55Z","cross_cats_sorted":["cs.AI","cs.ET","cs.SY","eess.SP","eess.SY"],"title_canon_sha256":"e1162a988ec121f32627e2de2494e7132bdf0ab19b0ba1213d703334b6c3a64e","abstract_canon_sha256":"d093c4c91629b0446b40bcf327dd45bf4019e263021b7bd62a2eb91725969fd8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:08.881996Z","signature_b64":"2FmdVxIKA6xduTZITqtrRUoR67opmikw+K1SeIffZCjdPxAzN49g+DxTSYvRx6sO3GWXWxlb84H9FrICuUhiDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48edace9722f2792e852ee57c5a619bdc85544a3e10fd085586f5671945b0707","last_reissued_at":"2026-06-02T02:04:08.881382Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:08.881382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HuMam: Humanoid Motion Control via End-to-End Deep Reinforcement Learning with Mamba","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.ET","cs.SY","eess.SP","eess.SY"],"primary_cat":"cs.RO","authors_text":"Jinzhao Zhou, Pengxiang Meng, Xiaowen Tao, Yinuo Wang, Yuanyang Qi","submitted_at":"2025-09-22T17:19:55Z","abstract_excerpt":"End-to-end reinforcement learning (RL) for humanoid locomotion is appealing for its compact perception-action mapping, yet practical policies often suffer from training instability, inefficient feature fusion, and high actuation cost. We present HuMam, a state-centric end-to-end RL framework that employs a single-layer Mamba encoder to fuse robot-centric states with oriented footstep targets and a continuous phase clock. The policy outputs joint position targets tracked by a low-level PD loop and is optimized with PPO. A concise six-term reward balances contact quality, swing smoothness, foot "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.18046","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/2509.18046/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":"2509.18046","created_at":"2026-06-02T02:04:08.881463+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.18046v2","created_at":"2026-06-02T02:04:08.881463+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.18046","created_at":"2026-06-02T02:04:08.881463+00:00"},{"alias_kind":"pith_short_12","alias_value":"JDW2Z2LSF4TZ","created_at":"2026-06-02T02:04:08.881463+00:00"},{"alias_kind":"pith_short_16","alias_value":"JDW2Z2LSF4TZF2CS","created_at":"2026-06-02T02:04:08.881463+00:00"},{"alias_kind":"pith_short_8","alias_value":"JDW2Z2LS","created_at":"2026-06-02T02:04:08.881463+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/JDW2Z2LSF4TZF2CS5ZL4LJQZXX","json":"https://pith.science/pith/JDW2Z2LSF4TZF2CS5ZL4LJQZXX.json","graph_json":"https://pith.science/api/pith-number/JDW2Z2LSF4TZF2CS5ZL4LJQZXX/graph.json","events_json":"https://pith.science/api/pith-number/JDW2Z2LSF4TZF2CS5ZL4LJQZXX/events.json","paper":"https://pith.science/paper/JDW2Z2LS"},"agent_actions":{"view_html":"https://pith.science/pith/JDW2Z2LSF4TZF2CS5ZL4LJQZXX","download_json":"https://pith.science/pith/JDW2Z2LSF4TZF2CS5ZL4LJQZXX.json","view_paper":"https://pith.science/paper/JDW2Z2LS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.18046&json=true","fetch_graph":"https://pith.science/api/pith-number/JDW2Z2LSF4TZF2CS5ZL4LJQZXX/graph.json","fetch_events":"https://pith.science/api/pith-number/JDW2Z2LSF4TZF2CS5ZL4LJQZXX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JDW2Z2LSF4TZF2CS5ZL4LJQZXX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JDW2Z2LSF4TZF2CS5ZL4LJQZXX/action/storage_attestation","attest_author":"https://pith.science/pith/JDW2Z2LSF4TZF2CS5ZL4LJQZXX/action/author_attestation","sign_citation":"https://pith.science/pith/JDW2Z2LSF4TZF2CS5ZL4LJQZXX/action/citation_signature","submit_replication":"https://pith.science/pith/JDW2Z2LSF4TZF2CS5ZL4LJQZXX/action/replication_record"}},"created_at":"2026-06-02T02:04:08.881463+00:00","updated_at":"2026-06-02T02:04:08.881463+00:00"}