{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:B7JLMWSIYCUYJ7NPJJ4NPCB2PB","short_pith_number":"pith:B7JLMWSI","canonical_record":{"source":{"id":"1812.03201","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-12-07T20:10:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f3a99f4fea7d9b04bcb0385b9e3afbf4d8af5177f04de53c06c16c69ed0d580b","abstract_canon_sha256":"a14896df29e3541e5b06860b0b9f75fef05a8706e761e3cf996ac570fa84465d"},"schema_version":"1.0"},"canonical_sha256":"0fd2b65a48c0a984fdaf4a78d7883a7849f6b3817e45c4bba52473c0c717ae7b","source":{"kind":"arxiv","id":"1812.03201","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.03201","created_at":"2026-05-17T23:57:56Z"},{"alias_kind":"arxiv_version","alias_value":"1812.03201v2","created_at":"2026-05-17T23:57:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.03201","created_at":"2026-05-17T23:57:56Z"},{"alias_kind":"pith_short_12","alias_value":"B7JLMWSIYCUY","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"B7JLMWSIYCUYJ7NP","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"B7JLMWSI","created_at":"2026-05-18T12:32:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:B7JLMWSIYCUYJ7NPJJ4NPCB2PB","target":"record","payload":{"canonical_record":{"source":{"id":"1812.03201","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-12-07T20:10:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f3a99f4fea7d9b04bcb0385b9e3afbf4d8af5177f04de53c06c16c69ed0d580b","abstract_canon_sha256":"a14896df29e3541e5b06860b0b9f75fef05a8706e761e3cf996ac570fa84465d"},"schema_version":"1.0"},"canonical_sha256":"0fd2b65a48c0a984fdaf4a78d7883a7849f6b3817e45c4bba52473c0c717ae7b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:56.800787Z","signature_b64":"kFxCXJ4oUElUEfbsW4jztOvWUf7tW09X25XqNu4HAxvb0aQtCBNMCEjrKadvxD4/uplchP7gSYfeictJBPwiAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fd2b65a48c0a984fdaf4a78d7883a7849f6b3817e45c4bba52473c0c717ae7b","last_reissued_at":"2026-05-17T23:57:56.800157Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:56.800157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.03201","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":"2026-05-17T23:57:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1nW7DzXAsu5UXtZ7Yv8PPDbIErTfNsJPTvLGOtI+HQQ0bbuBK+aMwTcB0g/nQrd38mRaZ0psfCDRBlM/Cc4NCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:31:59.952584Z"},"content_sha256":"e4165b8510e44f4d55f34100e6012c292f92ad14734d3c62dd165823222c84ff","schema_version":"1.0","event_id":"sha256:e4165b8510e44f4d55f34100e6012c292f92ad14734d3c62dd165823222c84ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:B7JLMWSIYCUYJ7NPJJ4NPCB2PB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Residual Reinforcement Learning for Robot Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Ashvin Nair, Avinash Kumar, Eugen Solowjow, Jianlan Luo, Juan Aparicio Ojea, Matthias Loskyll, Sergey Levine, Shikhar Bahl, Tobias Johannink","submitted_at":"2018-12-07T20:10:23Z","abstract_excerpt":"Conventional feedback control methods can solve various types of robot control problems very efficiently by capturing the structure with explicit models, such as rigid body equations of motion. However, many control problems in modern manufacturing deal with contacts and friction, which are difficult to capture with first-order physical modeling. Hence, applying control design methodologies to these kinds of problems often results in brittle and inaccurate controllers, which have to be manually tuned for deployment. Reinforcement learning (RL) methods have been demonstrated to be capable of le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.03201","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":""},"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":"2026-05-17T23:57:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s8fQvD9xWlK5G68zGJc+ZYKhZ4ZQwF3nay6WvcgagvW84sbO6N/9JFjfByhIs7oChPzJoax1inlBwQ7DVRgRAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:31:59.952934Z"},"content_sha256":"0eace318a7acaa419b033cb55c35377a664b4e5c323b1f4c22cc793f3686302d","schema_version":"1.0","event_id":"sha256:0eace318a7acaa419b033cb55c35377a664b4e5c323b1f4c22cc793f3686302d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B7JLMWSIYCUYJ7NPJJ4NPCB2PB/bundle.json","state_url":"https://pith.science/pith/B7JLMWSIYCUYJ7NPJJ4NPCB2PB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B7JLMWSIYCUYJ7NPJJ4NPCB2PB/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":"2026-05-25T23:31:59Z","links":{"resolver":"https://pith.science/pith/B7JLMWSIYCUYJ7NPJJ4NPCB2PB","bundle":"https://pith.science/pith/B7JLMWSIYCUYJ7NPJJ4NPCB2PB/bundle.json","state":"https://pith.science/pith/B7JLMWSIYCUYJ7NPJJ4NPCB2PB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B7JLMWSIYCUYJ7NPJJ4NPCB2PB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:B7JLMWSIYCUYJ7NPJJ4NPCB2PB","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":"a14896df29e3541e5b06860b0b9f75fef05a8706e761e3cf996ac570fa84465d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-12-07T20:10:23Z","title_canon_sha256":"f3a99f4fea7d9b04bcb0385b9e3afbf4d8af5177f04de53c06c16c69ed0d580b"},"schema_version":"1.0","source":{"id":"1812.03201","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.03201","created_at":"2026-05-17T23:57:56Z"},{"alias_kind":"arxiv_version","alias_value":"1812.03201v2","created_at":"2026-05-17T23:57:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.03201","created_at":"2026-05-17T23:57:56Z"},{"alias_kind":"pith_short_12","alias_value":"B7JLMWSIYCUY","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"B7JLMWSIYCUYJ7NP","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"B7JLMWSI","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:0eace318a7acaa419b033cb55c35377a664b4e5c323b1f4c22cc793f3686302d","target":"graph","created_at":"2026-05-17T23:57:56Z","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"},"paper":{"abstract_excerpt":"Conventional feedback control methods can solve various types of robot control problems very efficiently by capturing the structure with explicit models, such as rigid body equations of motion. However, many control problems in modern manufacturing deal with contacts and friction, which are difficult to capture with first-order physical modeling. Hence, applying control design methodologies to these kinds of problems often results in brittle and inaccurate controllers, which have to be manually tuned for deployment. Reinforcement learning (RL) methods have been demonstrated to be capable of le","authors_text":"Ashvin Nair, Avinash Kumar, Eugen Solowjow, Jianlan Luo, Juan Aparicio Ojea, Matthias Loskyll, Sergey Levine, Shikhar Bahl, Tobias Johannink","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-12-07T20:10:23Z","title":"Residual Reinforcement Learning for Robot Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.03201","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:e4165b8510e44f4d55f34100e6012c292f92ad14734d3c62dd165823222c84ff","target":"record","created_at":"2026-05-17T23:57:56Z","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":"a14896df29e3541e5b06860b0b9f75fef05a8706e761e3cf996ac570fa84465d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-12-07T20:10:23Z","title_canon_sha256":"f3a99f4fea7d9b04bcb0385b9e3afbf4d8af5177f04de53c06c16c69ed0d580b"},"schema_version":"1.0","source":{"id":"1812.03201","kind":"arxiv","version":2}},"canonical_sha256":"0fd2b65a48c0a984fdaf4a78d7883a7849f6b3817e45c4bba52473c0c717ae7b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0fd2b65a48c0a984fdaf4a78d7883a7849f6b3817e45c4bba52473c0c717ae7b","first_computed_at":"2026-05-17T23:57:56.800157Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:57:56.800157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kFxCXJ4oUElUEfbsW4jztOvWUf7tW09X25XqNu4HAxvb0aQtCBNMCEjrKadvxD4/uplchP7gSYfeictJBPwiAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:57:56.800787Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.03201","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4165b8510e44f4d55f34100e6012c292f92ad14734d3c62dd165823222c84ff","sha256:0eace318a7acaa419b033cb55c35377a664b4e5c323b1f4c22cc793f3686302d"],"state_sha256":"dafc11701bacaae07d38780576744ee579fdcb75cc68b8e2c494e71da9bf3b27"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5s4TxbFd8GOGN8jtRwlP+abcWLQk4SagSF86zvVQAcVUUyjKlDcrJ/vucbLd2HWsjyQHZgFW6FiQdwWJEVhJDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T23:31:59.955370Z","bundle_sha256":"87eb78d13dcf4107468b69382d7af13b9e3f2453589aeece2a33f6228fc89a61"}}