{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:DXDJP5J6OPIOSTANBTJR7RHBB4","short_pith_number":"pith:DXDJP5J6","canonical_record":{"source":{"id":"1811.12927","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-11-30T18:27:41Z","cross_cats_sorted":[],"title_canon_sha256":"4a40307f16be99a1c9b3de96eaa656e9d073923d6e2f6169acb7fd5087aec849","abstract_canon_sha256":"3014cd829780ed02b8e7262a1d63039f17a551e992ada9ba4ca02045da4142a6"},"schema_version":"1.0"},"canonical_sha256":"1dc697f53e73d0e94c0d0cd31fc4e10f2f04f66cb73c1f86facc21f6561e807e","source":{"kind":"arxiv","id":"1811.12927","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.12927","created_at":"2026-05-17T23:53:50Z"},{"alias_kind":"arxiv_version","alias_value":"1811.12927v2","created_at":"2026-05-17T23:53:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.12927","created_at":"2026-05-17T23:53:50Z"},{"alias_kind":"pith_short_12","alias_value":"DXDJP5J6OPIO","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DXDJP5J6OPIOSTAN","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DXDJP5J6","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:DXDJP5J6OPIOSTANBTJR7RHBB4","target":"record","payload":{"canonical_record":{"source":{"id":"1811.12927","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-11-30T18:27:41Z","cross_cats_sorted":[],"title_canon_sha256":"4a40307f16be99a1c9b3de96eaa656e9d073923d6e2f6169acb7fd5087aec849","abstract_canon_sha256":"3014cd829780ed02b8e7262a1d63039f17a551e992ada9ba4ca02045da4142a6"},"schema_version":"1.0"},"canonical_sha256":"1dc697f53e73d0e94c0d0cd31fc4e10f2f04f66cb73c1f86facc21f6561e807e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:50.006389Z","signature_b64":"+Ebrmy1+PWnO8ROdcPnhn9f9RBqayQqNh8AJVBWon1VzeC6CNqvHtHXKZCEZ5nxVUo5LElUEMTkpZHBECuxEAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1dc697f53e73d0e94c0d0cd31fc4e10f2f04f66cb73c1f86facc21f6561e807e","last_reissued_at":"2026-05-17T23:53:50.005712Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:50.005712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.12927","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":"2026-05-17T23:53:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ht9oUG0LFJh6FTSy+tXtCnKt59xUPHuDLCLtHUgGF1N4bfeZN0k88ycxMePzN263Opy0s8mA+iYVompbd2EuCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T10:18:46.574075Z"},"content_sha256":"acc6710ee755f8c992fbbd378763d99f0efb1cb07385d8aa4284c92676ca1fa7","schema_version":"1.0","event_id":"sha256:acc6710ee755f8c992fbbd378763d99f0efb1cb07385d8aa4284c92676ca1fa7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:DXDJP5J6OPIOSTANBTJR7RHBB4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical Policy Design for Sample-Efficient Learning of Robot Table Tennis Through Self-Play","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Navdeep Jaitly, Nevena Lazic, Reza Mahjourian, Risto Miikkulainen, Sergey Levine","submitted_at":"2018-11-30T18:27:41Z","abstract_excerpt":"Training robots with physical bodies requires developing new methods and action representations that allow the learning agents to explore the space of policies efficiently. This work studies sample-efficient learning of complex policies in the context of robot table tennis. It incorporates learning into a hierarchical control framework using a model-free strategy layer (which requires complex reasoning about opponents that is difficult to do in a model-based way), model-based prediction of external objects (which are difficult to control directly with analytic control methods, but governed by "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.12927","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":"2026-05-17T23:53:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aMNnAM7HC0blWUtoWgx9kYQuVyPGtqlUUlUemNsJrU1N+HtLmFD6zi5W3o8KSQja+Lez+soMYoU/parotnJ6CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T10:18:46.574455Z"},"content_sha256":"90ad5fc44330df121b54be6d92987bed120f8188ec8d92dba6ab73582c09dd79","schema_version":"1.0","event_id":"sha256:90ad5fc44330df121b54be6d92987bed120f8188ec8d92dba6ab73582c09dd79"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DXDJP5J6OPIOSTANBTJR7RHBB4/bundle.json","state_url":"https://pith.science/pith/DXDJP5J6OPIOSTANBTJR7RHBB4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DXDJP5J6OPIOSTANBTJR7RHBB4/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":"2026-05-19T10:18:46Z","links":{"resolver":"https://pith.science/pith/DXDJP5J6OPIOSTANBTJR7RHBB4","bundle":"https://pith.science/pith/DXDJP5J6OPIOSTANBTJR7RHBB4/bundle.json","state":"https://pith.science/pith/DXDJP5J6OPIOSTANBTJR7RHBB4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DXDJP5J6OPIOSTANBTJR7RHBB4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DXDJP5J6OPIOSTANBTJR7RHBB4","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":"3014cd829780ed02b8e7262a1d63039f17a551e992ada9ba4ca02045da4142a6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-11-30T18:27:41Z","title_canon_sha256":"4a40307f16be99a1c9b3de96eaa656e9d073923d6e2f6169acb7fd5087aec849"},"schema_version":"1.0","source":{"id":"1811.12927","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.12927","created_at":"2026-05-17T23:53:50Z"},{"alias_kind":"arxiv_version","alias_value":"1811.12927v2","created_at":"2026-05-17T23:53:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.12927","created_at":"2026-05-17T23:53:50Z"},{"alias_kind":"pith_short_12","alias_value":"DXDJP5J6OPIO","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DXDJP5J6OPIOSTAN","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DXDJP5J6","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:90ad5fc44330df121b54be6d92987bed120f8188ec8d92dba6ab73582c09dd79","target":"graph","created_at":"2026-05-17T23:53:50Z","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":"Training robots with physical bodies requires developing new methods and action representations that allow the learning agents to explore the space of policies efficiently. This work studies sample-efficient learning of complex policies in the context of robot table tennis. It incorporates learning into a hierarchical control framework using a model-free strategy layer (which requires complex reasoning about opponents that is difficult to do in a model-based way), model-based prediction of external objects (which are difficult to control directly with analytic control methods, but governed by ","authors_text":"Navdeep Jaitly, Nevena Lazic, Reza Mahjourian, Risto Miikkulainen, Sergey Levine","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-11-30T18:27:41Z","title":"Hierarchical Policy Design for Sample-Efficient Learning of Robot Table Tennis Through Self-Play"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.12927","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:acc6710ee755f8c992fbbd378763d99f0efb1cb07385d8aa4284c92676ca1fa7","target":"record","created_at":"2026-05-17T23:53:50Z","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":"3014cd829780ed02b8e7262a1d63039f17a551e992ada9ba4ca02045da4142a6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-11-30T18:27:41Z","title_canon_sha256":"4a40307f16be99a1c9b3de96eaa656e9d073923d6e2f6169acb7fd5087aec849"},"schema_version":"1.0","source":{"id":"1811.12927","kind":"arxiv","version":2}},"canonical_sha256":"1dc697f53e73d0e94c0d0cd31fc4e10f2f04f66cb73c1f86facc21f6561e807e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1dc697f53e73d0e94c0d0cd31fc4e10f2f04f66cb73c1f86facc21f6561e807e","first_computed_at":"2026-05-17T23:53:50.005712Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:53:50.005712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+Ebrmy1+PWnO8ROdcPnhn9f9RBqayQqNh8AJVBWon1VzeC6CNqvHtHXKZCEZ5nxVUo5LElUEMTkpZHBECuxEAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:53:50.006389Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.12927","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:acc6710ee755f8c992fbbd378763d99f0efb1cb07385d8aa4284c92676ca1fa7","sha256:90ad5fc44330df121b54be6d92987bed120f8188ec8d92dba6ab73582c09dd79"],"state_sha256":"c60d4588600e9cede343464f83bf6ee6c56aa418247fad17b03eb0ed3b59badd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/+45Ojn9cyMUWYe+oMd0uJTcMX/+cGlHqyh0W+Zf5Efx00Sx5WlH6Cng/0jg84zc13J4GX3NPdnwgZZPZKh7AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T10:18:46.576460Z","bundle_sha256":"5ca7b2a6adbcf8b8190a6e6b5600b871407736f63b75bbe81e17572ec48d7c16"}}