{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:RDM4Z4DZEIVHWQOTNH74Z74FRG","short_pith_number":"pith:RDM4Z4DZ","canonical_record":{"source":{"id":"1709.10087","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-28T17:51:13Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"c443997d3b5e23b00301e2f0db94e1e167243f2ad10c5bb479592b071fa46518","abstract_canon_sha256":"23a5690f9ca56f1e359d2f682487312c79a548f6cf023d4b69cfcec318fe4230"},"schema_version":"1.0"},"canonical_sha256":"88d9ccf079222a7b41d369ffccff858980657ca7623927e799f94128781e307a","source":{"kind":"arxiv","id":"1709.10087","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.10087","created_at":"2026-05-18T00:12:24Z"},{"alias_kind":"arxiv_version","alias_value":"1709.10087v2","created_at":"2026-05-18T00:12:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.10087","created_at":"2026-05-18T00:12:24Z"},{"alias_kind":"pith_short_12","alias_value":"RDM4Z4DZEIVH","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"RDM4Z4DZEIVHWQOT","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"RDM4Z4DZ","created_at":"2026-05-18T12:31:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:RDM4Z4DZEIVHWQOTNH74Z74FRG","target":"record","payload":{"canonical_record":{"source":{"id":"1709.10087","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-28T17:51:13Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"c443997d3b5e23b00301e2f0db94e1e167243f2ad10c5bb479592b071fa46518","abstract_canon_sha256":"23a5690f9ca56f1e359d2f682487312c79a548f6cf023d4b69cfcec318fe4230"},"schema_version":"1.0"},"canonical_sha256":"88d9ccf079222a7b41d369ffccff858980657ca7623927e799f94128781e307a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:24.862794Z","signature_b64":"Cc/z+9zEa8ggioba5n+hXo0XiTeLljQ/fpkPulhTy25Mg4jQYyRO1OolvEyv3T62hh+mCAVQgVIXlOuLycnHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88d9ccf079222a7b41d369ffccff858980657ca7623927e799f94128781e307a","last_reissued_at":"2026-05-18T00:12:24.862201Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:24.862201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.10087","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":"2026-05-18T00:12:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W1KTBy9PnCYg/lW9O7Iit/uEAxrlh6TyRsYBmXLpVI7gcEo2+NPfw++J8scCTT1iCHlADlXv+0tY1u7iGm6DAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T22:02:52.057034Z"},"content_sha256":"b05d1f659a76acd2dc3c41410955f36dcfcf8b3888b948468428eb3fcab5d1ed","schema_version":"1.0","event_id":"sha256:b05d1f659a76acd2dc3c41410955f36dcfcf8b3888b948468428eb3fcab5d1ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:RDM4Z4DZEIVHWQOTNH74Z74FRG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Aravind Rajeswaran, Emanuel Todorov, Giulia Vezzani, John Schulman, Sergey Levine, Vikash Kumar","submitted_at":"2017-09-28T17:51:13Z","abstract_excerpt":"Dexterous multi-fingered hands are extremely versatile and provide a generic way to perform a multitude of tasks in human-centric environments. However, effectively controlling them remains challenging due to their high dimensionality and large number of potential contacts. Deep reinforcement learning (DRL) provides a model-agnostic approach to control complex dynamical systems, but has not been shown to scale to high-dimensional dexterous manipulation. Furthermore, deployment of DRL on physical systems remains challenging due to sample inefficiency. Consequently, the success of DRL in robotic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.10087","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":"2026-05-18T00:12:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wJj6v5CPB/OM7DYR6BcSM1f47AaGozVA/0fioSgwCb7fWXlXfG89xDlU4jKZJWhGdY+rVfP66PWR/cHo5TQPAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T22:02:52.057401Z"},"content_sha256":"b29dd53aebe4e954c4642f729f36d51f41d6c4a17e4f3065970d4e52de5d7bc0","schema_version":"1.0","event_id":"sha256:b29dd53aebe4e954c4642f729f36d51f41d6c4a17e4f3065970d4e52de5d7bc0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RDM4Z4DZEIVHWQOTNH74Z74FRG/bundle.json","state_url":"https://pith.science/pith/RDM4Z4DZEIVHWQOTNH74Z74FRG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RDM4Z4DZEIVHWQOTNH74Z74FRG/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":"2026-05-19T22:02:52Z","links":{"resolver":"https://pith.science/pith/RDM4Z4DZEIVHWQOTNH74Z74FRG","bundle":"https://pith.science/pith/RDM4Z4DZEIVHWQOTNH74Z74FRG/bundle.json","state":"https://pith.science/pith/RDM4Z4DZEIVHWQOTNH74Z74FRG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RDM4Z4DZEIVHWQOTNH74Z74FRG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:RDM4Z4DZEIVHWQOTNH74Z74FRG","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":"23a5690f9ca56f1e359d2f682487312c79a548f6cf023d4b69cfcec318fe4230","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-28T17:51:13Z","title_canon_sha256":"c443997d3b5e23b00301e2f0db94e1e167243f2ad10c5bb479592b071fa46518"},"schema_version":"1.0","source":{"id":"1709.10087","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.10087","created_at":"2026-05-18T00:12:24Z"},{"alias_kind":"arxiv_version","alias_value":"1709.10087v2","created_at":"2026-05-18T00:12:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.10087","created_at":"2026-05-18T00:12:24Z"},{"alias_kind":"pith_short_12","alias_value":"RDM4Z4DZEIVH","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"RDM4Z4DZEIVHWQOT","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"RDM4Z4DZ","created_at":"2026-05-18T12:31:39Z"}],"graph_snapshots":[{"event_id":"sha256:b29dd53aebe4e954c4642f729f36d51f41d6c4a17e4f3065970d4e52de5d7bc0","target":"graph","created_at":"2026-05-18T00:12:24Z","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":"Dexterous multi-fingered hands are extremely versatile and provide a generic way to perform a multitude of tasks in human-centric environments. However, effectively controlling them remains challenging due to their high dimensionality and large number of potential contacts. Deep reinforcement learning (DRL) provides a model-agnostic approach to control complex dynamical systems, but has not been shown to scale to high-dimensional dexterous manipulation. Furthermore, deployment of DRL on physical systems remains challenging due to sample inefficiency. Consequently, the success of DRL in robotic","authors_text":"Abhishek Gupta, Aravind Rajeswaran, Emanuel Todorov, Giulia Vezzani, John Schulman, Sergey Levine, Vikash Kumar","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-28T17:51:13Z","title":"Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.10087","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:b05d1f659a76acd2dc3c41410955f36dcfcf8b3888b948468428eb3fcab5d1ed","target":"record","created_at":"2026-05-18T00:12:24Z","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":"23a5690f9ca56f1e359d2f682487312c79a548f6cf023d4b69cfcec318fe4230","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-28T17:51:13Z","title_canon_sha256":"c443997d3b5e23b00301e2f0db94e1e167243f2ad10c5bb479592b071fa46518"},"schema_version":"1.0","source":{"id":"1709.10087","kind":"arxiv","version":2}},"canonical_sha256":"88d9ccf079222a7b41d369ffccff858980657ca7623927e799f94128781e307a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88d9ccf079222a7b41d369ffccff858980657ca7623927e799f94128781e307a","first_computed_at":"2026-05-18T00:12:24.862201Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:12:24.862201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Cc/z+9zEa8ggioba5n+hXo0XiTeLljQ/fpkPulhTy25Mg4jQYyRO1OolvEyv3T62hh+mCAVQgVIXlOuLycnHAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:12:24.862794Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.10087","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b05d1f659a76acd2dc3c41410955f36dcfcf8b3888b948468428eb3fcab5d1ed","sha256:b29dd53aebe4e954c4642f729f36d51f41d6c4a17e4f3065970d4e52de5d7bc0"],"state_sha256":"951bdcbd98095d0315d0bf0d61d6040ac9c7149f2ec1a9ff73e190dbcb50949c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kc4Zd3uzZkssHSnc31trUrJl97XuyMkejYVIc6xQeWZIVGDyRNLHjmjMFuRT4M4tLpbPDv/DUKkVSSX4foTOBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T22:02:52.059356Z","bundle_sha256":"770fff78ddaab3c7fad70d237d1a3ec4b3d7fe440fbcaeb304c2c0eb6155167b"}}