{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:XB5ZKLH34P57ZB7ZJJ272A6345","short_pith_number":"pith:XB5ZKLH3","canonical_record":{"source":{"id":"2011.04741","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-09T20:35:33Z","cross_cats_sorted":[],"title_canon_sha256":"dba64348cd9512b54807a7d8426f31f27250dd653f86b1a64a4ad3cad862a8d2","abstract_canon_sha256":"39926a613abef2690410bb50bc59b4631a40897c01e3e0cbb4302c7d1cea2e65"},"schema_version":"1.0"},"canonical_sha256":"b87b952cfbe3fbfc87f94a75fd03dbe7582267c22ee03af9643e99277a837b25","source":{"kind":"arxiv","id":"2011.04741","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.04741","created_at":"2026-07-05T02:37:56Z"},{"alias_kind":"arxiv_version","alias_value":"2011.04741v2","created_at":"2026-07-05T02:37:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.04741","created_at":"2026-07-05T02:37:56Z"},{"alias_kind":"pith_short_12","alias_value":"XB5ZKLH34P57","created_at":"2026-07-05T02:37:56Z"},{"alias_kind":"pith_short_16","alias_value":"XB5ZKLH34P57ZB7Z","created_at":"2026-07-05T02:37:56Z"},{"alias_kind":"pith_short_8","alias_value":"XB5ZKLH3","created_at":"2026-07-05T02:37:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:XB5ZKLH34P57ZB7ZJJ272A6345","target":"record","payload":{"canonical_record":{"source":{"id":"2011.04741","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-09T20:35:33Z","cross_cats_sorted":[],"title_canon_sha256":"dba64348cd9512b54807a7d8426f31f27250dd653f86b1a64a4ad3cad862a8d2","abstract_canon_sha256":"39926a613abef2690410bb50bc59b4631a40897c01e3e0cbb4302c7d1cea2e65"},"schema_version":"1.0"},"canonical_sha256":"b87b952cfbe3fbfc87f94a75fd03dbe7582267c22ee03af9643e99277a837b25","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:37:56.807804Z","signature_b64":"xLqUqI7a3A1N+WR8BxVIyipm7dXUXKYF4e4cGC3pytuWAl2gktW6xXQIDLJfeIn+Ye3yHTCekk202ScUz9IWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b87b952cfbe3fbfc87f94a75fd03dbe7582267c22ee03af9643e99277a837b25","last_reissued_at":"2026-07-05T02:37:56.807332Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:37:56.807332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.04741","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":"2026-07-05T02:37:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cyBaoX7FN481qDleVe5iGionjPcB4ftmhKlwlF4BREIuXAGmAZvFgwBY8bBUqMRVUB82gJjhZrqQLtEtl9ZPBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T21:12:02.347065Z"},"content_sha256":"db4b49e935c39b74ecff2b3b272b26d513efbc104cce157c2625afb350fe6992","schema_version":"1.0","event_id":"sha256:db4b49e935c39b74ecff2b3b272b26d513efbc104cce157c2625afb350fe6992"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:XB5ZKLH34P57ZB7ZJJ272A6345","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Task Space Actions for Bipedal Locomotion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alan Fern, Helei Duan, Jeremy Dao, Jonathan Hurst, Kevin Green, Taylor Apgar","submitted_at":"2020-11-09T20:35:33Z","abstract_excerpt":"Recent work has demonstrated the success of reinforcement learning (RL) for training bipedal locomotion policies for real robots. This prior work, however, has focused on learning joint-coordination controllers based on an objective of following joint trajectories produced by already available controllers. As such, it is difficult to train these approaches to achieve higher-level goals of legged locomotion, such as simply specifying the desired end-effector foot movement or ground reaction forces. In this work, we propose an approach for integrating knowledge of the robot system into RL to all"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.04741","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/2011.04741/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":"2026-07-05T02:37:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/eidZGdXLboh4UpPr203JdXMZNOElGV4Vn+IkwzkBPw3t3adkXMf/aX9TuDScjXE69MKSzZXz1MmudWWOJbMDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T21:12:02.347615Z"},"content_sha256":"76dbdf90672998d5836d797d1b702b890e2bbccda9d49972284ab03f2fa17d68","schema_version":"1.0","event_id":"sha256:76dbdf90672998d5836d797d1b702b890e2bbccda9d49972284ab03f2fa17d68"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XB5ZKLH34P57ZB7ZJJ272A6345/bundle.json","state_url":"https://pith.science/pith/XB5ZKLH34P57ZB7ZJJ272A6345/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XB5ZKLH34P57ZB7ZJJ272A6345/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":"2026-08-12T21:12:02Z","links":{"resolver":"https://pith.science/pith/XB5ZKLH34P57ZB7ZJJ272A6345","bundle":"https://pith.science/pith/XB5ZKLH34P57ZB7ZJJ272A6345/bundle.json","state":"https://pith.science/pith/XB5ZKLH34P57ZB7ZJJ272A6345/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XB5ZKLH34P57ZB7ZJJ272A6345/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:XB5ZKLH34P57ZB7ZJJ272A6345","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":"39926a613abef2690410bb50bc59b4631a40897c01e3e0cbb4302c7d1cea2e65","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-09T20:35:33Z","title_canon_sha256":"dba64348cd9512b54807a7d8426f31f27250dd653f86b1a64a4ad3cad862a8d2"},"schema_version":"1.0","source":{"id":"2011.04741","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.04741","created_at":"2026-07-05T02:37:56Z"},{"alias_kind":"arxiv_version","alias_value":"2011.04741v2","created_at":"2026-07-05T02:37:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.04741","created_at":"2026-07-05T02:37:56Z"},{"alias_kind":"pith_short_12","alias_value":"XB5ZKLH34P57","created_at":"2026-07-05T02:37:56Z"},{"alias_kind":"pith_short_16","alias_value":"XB5ZKLH34P57ZB7Z","created_at":"2026-07-05T02:37:56Z"},{"alias_kind":"pith_short_8","alias_value":"XB5ZKLH3","created_at":"2026-07-05T02:37:56Z"}],"graph_snapshots":[{"event_id":"sha256:76dbdf90672998d5836d797d1b702b890e2bbccda9d49972284ab03f2fa17d68","target":"graph","created_at":"2026-07-05T02:37:56Z","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/2011.04741/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work has demonstrated the success of reinforcement learning (RL) for training bipedal locomotion policies for real robots. This prior work, however, has focused on learning joint-coordination controllers based on an objective of following joint trajectories produced by already available controllers. As such, it is difficult to train these approaches to achieve higher-level goals of legged locomotion, such as simply specifying the desired end-effector foot movement or ground reaction forces. In this work, we propose an approach for integrating knowledge of the robot system into RL to all","authors_text":"Alan Fern, Helei Duan, Jeremy Dao, Jonathan Hurst, Kevin Green, Taylor Apgar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-09T20:35:33Z","title":"Learning Task Space Actions for Bipedal Locomotion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.04741","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:db4b49e935c39b74ecff2b3b272b26d513efbc104cce157c2625afb350fe6992","target":"record","created_at":"2026-07-05T02:37:56Z","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":"39926a613abef2690410bb50bc59b4631a40897c01e3e0cbb4302c7d1cea2e65","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-09T20:35:33Z","title_canon_sha256":"dba64348cd9512b54807a7d8426f31f27250dd653f86b1a64a4ad3cad862a8d2"},"schema_version":"1.0","source":{"id":"2011.04741","kind":"arxiv","version":2}},"canonical_sha256":"b87b952cfbe3fbfc87f94a75fd03dbe7582267c22ee03af9643e99277a837b25","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b87b952cfbe3fbfc87f94a75fd03dbe7582267c22ee03af9643e99277a837b25","first_computed_at":"2026-07-05T02:37:56.807332Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:37:56.807332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xLqUqI7a3A1N+WR8BxVIyipm7dXUXKYF4e4cGC3pytuWAl2gktW6xXQIDLJfeIn+Ye3yHTCekk202ScUz9IWDw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:37:56.807804Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.04741","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db4b49e935c39b74ecff2b3b272b26d513efbc104cce157c2625afb350fe6992","sha256:76dbdf90672998d5836d797d1b702b890e2bbccda9d49972284ab03f2fa17d68"],"state_sha256":"409ca29489fe4ba0c92fc4ef5069e3182114fc7a407619171b73a6989f8b8346"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H9KlmC+MN5iTp0Q0ZvJ1aXfuwoOWZ+fIlPDcgVQ/UJtgVITMXD8+l2C8BKGIFoHho8WkSgtbqgqDt7z9+Y9uBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T21:12:02.352619Z","bundle_sha256":"e23cddabb2c7e778c27885742978e2333840e836aeee280fc37b307b6b687551"}}