{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JDW2Z2LSF4TZF2CS5ZL4LJQZXX","short_pith_number":"pith:JDW2Z2LS","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"},"canonical_sha256":"48edace9722f2792e852ee57c5a619bdc85544a3e10fd085586f5671945b0707","source":{"kind":"arxiv","id":"2509.18046","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.18046","created_at":"2026-06-02T02:04:08Z"},{"alias_kind":"arxiv_version","alias_value":"2509.18046v2","created_at":"2026-06-02T02:04:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.18046","created_at":"2026-06-02T02:04:08Z"},{"alias_kind":"pith_short_12","alias_value":"JDW2Z2LSF4TZ","created_at":"2026-06-02T02:04:08Z"},{"alias_kind":"pith_short_16","alias_value":"JDW2Z2LSF4TZF2CS","created_at":"2026-06-02T02:04:08Z"},{"alias_kind":"pith_short_8","alias_value":"JDW2Z2LS","created_at":"2026-06-02T02:04:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JDW2Z2LSF4TZF2CS5ZL4LJQZXX","target":"record","payload":{"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"},"canonical_sha256":"48edace9722f2792e852ee57c5a619bdc85544a3e10fd085586f5671945b0707","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"},"source_kind":"arxiv","source_id":"2509.18046","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T02:04:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2XAZpJllwEWjQqpyV3tAmLDwgXj2YYTaVvRWcH1SfktkuOrpk+7bSwQCklpMce6MCrdbJvLxcLNdfE0hd30ECQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:46:13.087723Z"},"content_sha256":"2720f14105ab59d4c2da03e7984a6edba451257c5aa13312a74579d635446096","schema_version":"1.0","event_id":"sha256:2720f14105ab59d4c2da03e7984a6edba451257c5aa13312a74579d635446096"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JDW2Z2LSF4TZF2CS5ZL4LJQZXX","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T02:04:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nFT6uI9PgEUFm5Qw17LSxEOxhvVAUnMnrUqajZl7Nm1J+lL/drOgfXfLpIvWAMofQRPrUgsW3Vx7lmbqq6v5CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:46:13.093641Z"},"content_sha256":"8e0c90837072cb2cd47c1cbc6223cb8c5275cd4d7d44ac1dd7194d175fcb0c6d","schema_version":"1.0","event_id":"sha256:8e0c90837072cb2cd47c1cbc6223cb8c5275cd4d7d44ac1dd7194d175fcb0c6d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JDW2Z2LSF4TZF2CS5ZL4LJQZXX/bundle.json","state_url":"https://pith.science/pith/JDW2Z2LSF4TZF2CS5ZL4LJQZXX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JDW2Z2LSF4TZF2CS5ZL4LJQZXX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T20:46:13Z","links":{"resolver":"https://pith.science/pith/JDW2Z2LSF4TZF2CS5ZL4LJQZXX","bundle":"https://pith.science/pith/JDW2Z2LSF4TZF2CS5ZL4LJQZXX/bundle.json","state":"https://pith.science/pith/JDW2Z2LSF4TZF2CS5ZL4LJQZXX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JDW2Z2LSF4TZF2CS5ZL4LJQZXX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JDW2Z2LSF4TZF2CS5ZL4LJQZXX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d093c4c91629b0446b40bcf327dd45bf4019e263021b7bd62a2eb91725969fd8","cross_cats_sorted":["cs.AI","cs.ET","cs.SY","eess.SP","eess.SY"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.RO","submitted_at":"2025-09-22T17:19:55Z","title_canon_sha256":"e1162a988ec121f32627e2de2494e7132bdf0ab19b0ba1213d703334b6c3a64e"},"schema_version":"1.0","source":{"id":"2509.18046","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.18046","created_at":"2026-06-02T02:04:08Z"},{"alias_kind":"arxiv_version","alias_value":"2509.18046v2","created_at":"2026-06-02T02:04:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.18046","created_at":"2026-06-02T02:04:08Z"},{"alias_kind":"pith_short_12","alias_value":"JDW2Z2LSF4TZ","created_at":"2026-06-02T02:04:08Z"},{"alias_kind":"pith_short_16","alias_value":"JDW2Z2LSF4TZF2CS","created_at":"2026-06-02T02:04:08Z"},{"alias_kind":"pith_short_8","alias_value":"JDW2Z2LS","created_at":"2026-06-02T02:04:08Z"}],"graph_snapshots":[{"event_id":"sha256:8e0c90837072cb2cd47c1cbc6223cb8c5275cd4d7d44ac1dd7194d175fcb0c6d","target":"graph","created_at":"2026-06-02T02:04:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2509.18046/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Jinzhao Zhou, Pengxiang Meng, Xiaowen Tao, Yinuo Wang, Yuanyang Qi","cross_cats":["cs.AI","cs.ET","cs.SY","eess.SP","eess.SY"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.RO","submitted_at":"2025-09-22T17:19:55Z","title":"HuMam: Humanoid Motion Control via End-to-End Deep Reinforcement Learning with Mamba"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.18046","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2720f14105ab59d4c2da03e7984a6edba451257c5aa13312a74579d635446096","target":"record","created_at":"2026-06-02T02:04:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d093c4c91629b0446b40bcf327dd45bf4019e263021b7bd62a2eb91725969fd8","cross_cats_sorted":["cs.AI","cs.ET","cs.SY","eess.SP","eess.SY"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.RO","submitted_at":"2025-09-22T17:19:55Z","title_canon_sha256":"e1162a988ec121f32627e2de2494e7132bdf0ab19b0ba1213d703334b6c3a64e"},"schema_version":"1.0","source":{"id":"2509.18046","kind":"arxiv","version":2}},"canonical_sha256":"48edace9722f2792e852ee57c5a619bdc85544a3e10fd085586f5671945b0707","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48edace9722f2792e852ee57c5a619bdc85544a3e10fd085586f5671945b0707","first_computed_at":"2026-06-02T02:04:08.881382Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:08.881382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2FmdVxIKA6xduTZITqtrRUoR67opmikw+K1SeIffZCjdPxAzN49g+DxTSYvRx6sO3GWXWxlb84H9FrICuUhiDg==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:08.881996Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.18046","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2720f14105ab59d4c2da03e7984a6edba451257c5aa13312a74579d635446096","sha256:8e0c90837072cb2cd47c1cbc6223cb8c5275cd4d7d44ac1dd7194d175fcb0c6d"],"state_sha256":"0ec017fb7b6d359cc4417af801b54df3e7eaeabccaf1707e9eca421ce8c340eb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XmnkFHpI9YFZ7UE45J0tIMuu95kGDTYNTYWW/oQpD8QvarYp+WJrQLRcYD6Fq599xU5qBPK2w39SkUmxacg4AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T20:46:13.099576Z","bundle_sha256":"146f4c7ba1ea948324586a0985cb7fe8068a52557fb82008b26cf847d2a7f18d"}}