{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:DPMOW76WR2U7IZBJSNHMGKAA66","short_pith_number":"pith:DPMOW76W","canonical_record":{"source":{"id":"1910.10194","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-10-22T18:37:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5ed2b3de1601132e5b81bdbed4752981183b070af74973325fa034698ccf91dc","abstract_canon_sha256":"c1b840e8ad849c0af29b0eb97e0c5e62d56516627c6e71bc0bedb6b68f63cb50"},"schema_version":"1.0"},"canonical_sha256":"1bd8eb7fd68ea9f46429934ec32800f79b2bbf70f3e200ff4d1b114ae0f17581","source":{"kind":"arxiv","id":"1910.10194","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.10194","created_at":"2026-07-05T00:14:22Z"},{"alias_kind":"arxiv_version","alias_value":"1910.10194v1","created_at":"2026-07-05T00:14:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.10194","created_at":"2026-07-05T00:14:22Z"},{"alias_kind":"pith_short_12","alias_value":"DPMOW76WR2U7","created_at":"2026-07-05T00:14:22Z"},{"alias_kind":"pith_short_16","alias_value":"DPMOW76WR2U7IZBJ","created_at":"2026-07-05T00:14:22Z"},{"alias_kind":"pith_short_8","alias_value":"DPMOW76W","created_at":"2026-07-05T00:14:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:DPMOW76WR2U7IZBJSNHMGKAA66","target":"record","payload":{"canonical_record":{"source":{"id":"1910.10194","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-10-22T18:37:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5ed2b3de1601132e5b81bdbed4752981183b070af74973325fa034698ccf91dc","abstract_canon_sha256":"c1b840e8ad849c0af29b0eb97e0c5e62d56516627c6e71bc0bedb6b68f63cb50"},"schema_version":"1.0"},"canonical_sha256":"1bd8eb7fd68ea9f46429934ec32800f79b2bbf70f3e200ff4d1b114ae0f17581","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:14:22.726361Z","signature_b64":"Gz5j04ayf0yPL3NbALJlrPTgjori6cf99TfmoQ3Nt4ktQcdTljS+xD4IPyIi9eL4XK38ATejxzYTVfcricuJBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bd8eb7fd68ea9f46429934ec32800f79b2bbf70f3e200ff4d1b114ae0f17581","last_reissued_at":"2026-07-05T00:14:22.725733Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:14:22.725733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.10194","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:14:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9miLuV/tyy4uicIUvaNXdAycHahkzn8pZ7TIQ8T4lcOvGM62bJgnin3O/UgtfnmtAvXWJGAuwbU5V/UAuhLZAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T12:29:32.168160Z"},"content_sha256":"53272433b30e1972f403b3d7821736f256132ab2813d7248a4aa43a129debab4","schema_version":"1.0","event_id":"sha256:53272433b30e1972f403b3d7821736f256132ab2813d7248a4aa43a129debab4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:DPMOW76WR2U7IZBJSNHMGKAA66","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Teach Biped Robots to Walk via Gait Principles and Reinforcement Learning with Adversarial Critics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Chenglong Fu, Clarence W. de Silva, Haoyong Yu, Kuangen Zhang, Zhimin Hou","submitted_at":"2019-10-22T18:37:30Z","abstract_excerpt":"Controlling a biped robot to walk stably is a challenging task considering its nonlinearity and hybrid dynamics. Reinforcement learning can address these issues by directly mapping the observed states to optimal actions that maximize the cumulative reward. However, the local minima caused by unsuitable rewards and the overestimation of the cumulative reward impede the maximization of the cumulative reward. To increase the cumulative reward, this paper designs a gait reward based on walking principles, which compensates the local minima for unnatural motions. Besides, an Adversarial Twin Delaye"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.10194","kind":"arxiv","version":1},"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/1910.10194/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":"2026-07-05T00:14:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vsPymsqAoXs2V+V9f0WXuALZghfhEDm9CekCO2QLts7yKTpsaCRsAMBa1TRu45eehvNa7a7RRdEpF5Bb+wyPCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T12:29:32.169724Z"},"content_sha256":"7a80c9b7bdeff3381bc6b97ce2711532408880adba6e32625ff7d1012f6847b5","schema_version":"1.0","event_id":"sha256:7a80c9b7bdeff3381bc6b97ce2711532408880adba6e32625ff7d1012f6847b5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DPMOW76WR2U7IZBJSNHMGKAA66/bundle.json","state_url":"https://pith.science/pith/DPMOW76WR2U7IZBJSNHMGKAA66/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DPMOW76WR2U7IZBJSNHMGKAA66/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":"2026-08-17T12:29:32Z","links":{"resolver":"https://pith.science/pith/DPMOW76WR2U7IZBJSNHMGKAA66","bundle":"https://pith.science/pith/DPMOW76WR2U7IZBJSNHMGKAA66/bundle.json","state":"https://pith.science/pith/DPMOW76WR2U7IZBJSNHMGKAA66/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DPMOW76WR2U7IZBJSNHMGKAA66/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:DPMOW76WR2U7IZBJSNHMGKAA66","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":"c1b840e8ad849c0af29b0eb97e0c5e62d56516627c6e71bc0bedb6b68f63cb50","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-10-22T18:37:30Z","title_canon_sha256":"5ed2b3de1601132e5b81bdbed4752981183b070af74973325fa034698ccf91dc"},"schema_version":"1.0","source":{"id":"1910.10194","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.10194","created_at":"2026-07-05T00:14:22Z"},{"alias_kind":"arxiv_version","alias_value":"1910.10194v1","created_at":"2026-07-05T00:14:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.10194","created_at":"2026-07-05T00:14:22Z"},{"alias_kind":"pith_short_12","alias_value":"DPMOW76WR2U7","created_at":"2026-07-05T00:14:22Z"},{"alias_kind":"pith_short_16","alias_value":"DPMOW76WR2U7IZBJ","created_at":"2026-07-05T00:14:22Z"},{"alias_kind":"pith_short_8","alias_value":"DPMOW76W","created_at":"2026-07-05T00:14:22Z"}],"graph_snapshots":[{"event_id":"sha256:7a80c9b7bdeff3381bc6b97ce2711532408880adba6e32625ff7d1012f6847b5","target":"graph","created_at":"2026-07-05T00:14:22Z","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/1910.10194/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Controlling a biped robot to walk stably is a challenging task considering its nonlinearity and hybrid dynamics. Reinforcement learning can address these issues by directly mapping the observed states to optimal actions that maximize the cumulative reward. However, the local minima caused by unsuitable rewards and the overestimation of the cumulative reward impede the maximization of the cumulative reward. To increase the cumulative reward, this paper designs a gait reward based on walking principles, which compensates the local minima for unnatural motions. Besides, an Adversarial Twin Delaye","authors_text":"Chenglong Fu, Clarence W. de Silva, Haoyong Yu, Kuangen Zhang, Zhimin Hou","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-10-22T18:37:30Z","title":"Teach Biped Robots to Walk via Gait Principles and Reinforcement Learning with Adversarial Critics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.10194","kind":"arxiv","version":1},"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":"sha256:53272433b30e1972f403b3d7821736f256132ab2813d7248a4aa43a129debab4","target":"record","created_at":"2026-07-05T00:14:22Z","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":"c1b840e8ad849c0af29b0eb97e0c5e62d56516627c6e71bc0bedb6b68f63cb50","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-10-22T18:37:30Z","title_canon_sha256":"5ed2b3de1601132e5b81bdbed4752981183b070af74973325fa034698ccf91dc"},"schema_version":"1.0","source":{"id":"1910.10194","kind":"arxiv","version":1}},"canonical_sha256":"1bd8eb7fd68ea9f46429934ec32800f79b2bbf70f3e200ff4d1b114ae0f17581","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1bd8eb7fd68ea9f46429934ec32800f79b2bbf70f3e200ff4d1b114ae0f17581","first_computed_at":"2026-07-05T00:14:22.725733Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:14:22.725733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gz5j04ayf0yPL3NbALJlrPTgjori6cf99TfmoQ3Nt4ktQcdTljS+xD4IPyIi9eL4XK38ATejxzYTVfcricuJBw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:14:22.726361Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.10194","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53272433b30e1972f403b3d7821736f256132ab2813d7248a4aa43a129debab4","sha256:7a80c9b7bdeff3381bc6b97ce2711532408880adba6e32625ff7d1012f6847b5"],"state_sha256":"939963292a9b08b7c13fe88ed407f70cb4e48fcc4a8ddd150e170c687518d1c6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nHtkzWtBXjolWJA3EwtHZXCef5U1S0k5F6UhI9nfrONgYZH+dVlypQnrfd4U5lddxBiB4NvNbmcF1V9/pqGtAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T12:29:32.180839Z","bundle_sha256":"8485875ae41735969ca0e6d4b09687b5a02015604b1f86bb625735af6def72ba"}}