{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:WZHJJWGCDZ7Q2EWSZ7JDAKS3TS","short_pith_number":"pith:WZHJJWGC","canonical_record":{"source":{"id":"1903.05803","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-14T03:37:49Z","cross_cats_sorted":["cs.SY","stat.ML"],"title_canon_sha256":"db9f93250acd8095451b670f7d78b4ebc9d07c794be2dcc8c9d017d9a8794e45","abstract_canon_sha256":"b1ce03a444e90db54db74b819ed403c7405478a60ba7c8c704212ac85252ae7f"},"schema_version":"1.0"},"canonical_sha256":"b64e94d8c21e7f0d12d2cfd2302a5b9ca1a9485ae3268afba5ec639d313f9986","source":{"kind":"arxiv","id":"1903.05803","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.05803","created_at":"2026-05-17T23:48:04Z"},{"alias_kind":"arxiv_version","alias_value":"1903.05803v2","created_at":"2026-05-17T23:48:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.05803","created_at":"2026-05-17T23:48:04Z"},{"alias_kind":"pith_short_12","alias_value":"WZHJJWGCDZ7Q","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"WZHJJWGCDZ7Q2EWS","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"WZHJJWGC","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:WZHJJWGCDZ7Q2EWSZ7JDAKS3TS","target":"record","payload":{"canonical_record":{"source":{"id":"1903.05803","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-14T03:37:49Z","cross_cats_sorted":["cs.SY","stat.ML"],"title_canon_sha256":"db9f93250acd8095451b670f7d78b4ebc9d07c794be2dcc8c9d017d9a8794e45","abstract_canon_sha256":"b1ce03a444e90db54db74b819ed403c7405478a60ba7c8c704212ac85252ae7f"},"schema_version":"1.0"},"canonical_sha256":"b64e94d8c21e7f0d12d2cfd2302a5b9ca1a9485ae3268afba5ec639d313f9986","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:04.478368Z","signature_b64":"NQmRwbAVnvRYwmUrKQnsclEzO5PmzEcJBCMi3fGxEExSlO9EvNGPfUrFXrjpIIg1BeCoECusE1U8AR6sF4maAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b64e94d8c21e7f0d12d2cfd2302a5b9ca1a9485ae3268afba5ec639d313f9986","last_reissued_at":"2026-05-17T23:48:04.477965Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:04.477965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.05803","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":"2026-05-17T23:48:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hIWzW255UQvBza5W+frzjvTGCErme5IE+YENBJf7pP2h6pX/4M2dmEmbRz02NCnIG1s9m2pa2hkMUru+ll06CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T16:33:35.976239Z"},"content_sha256":"baa79cb77191818a45a704ffaff4b0f7e41a050c501247ecdefe6b4e531864b4","schema_version":"1.0","event_id":"sha256:baa79cb77191818a45a704ffaff4b0f7e41a050c501247ecdefe6b4e531864b4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:WZHJJWGCDZ7Q2EWSZ7JDAKS3TS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Applications of Bootstrap in Continuous Space Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ambuj Tewari, George Michailidis, Mohamad Kazem Shirani Faradonbeh","submitted_at":"2019-03-14T03:37:49Z","abstract_excerpt":"In decision making problems for continuous state and action spaces, linear dynamical models are widely employed. Specifically, policies for stochastic linear systems subject to quadratic cost functions capture a large number of applications in reinforcement learning. Selected randomized policies have been studied in the literature recently that address the trade-off between identification and control. However, little is known about policies based on bootstrapping observed states and actions. In this work, we show that bootstrap-based policies achieve a square root scaling of regret with respec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.05803","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":"2026-05-17T23:48:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XPF0sxAywUFiWgSuLhkMFddMUWZxNkFFsNoIKRxaUWxMSF+s7a3AufHJkATu0WDsaj7U39Ah0a+HWnlRmJbyDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T16:33:35.976909Z"},"content_sha256":"266870a86edfecf92338baa8b7c19126edca0e103b55a65f98e8a929e77e6dc2","schema_version":"1.0","event_id":"sha256:266870a86edfecf92338baa8b7c19126edca0e103b55a65f98e8a929e77e6dc2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WZHJJWGCDZ7Q2EWSZ7JDAKS3TS/bundle.json","state_url":"https://pith.science/pith/WZHJJWGCDZ7Q2EWSZ7JDAKS3TS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WZHJJWGCDZ7Q2EWSZ7JDAKS3TS/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":"2026-05-31T16:33:35Z","links":{"resolver":"https://pith.science/pith/WZHJJWGCDZ7Q2EWSZ7JDAKS3TS","bundle":"https://pith.science/pith/WZHJJWGCDZ7Q2EWSZ7JDAKS3TS/bundle.json","state":"https://pith.science/pith/WZHJJWGCDZ7Q2EWSZ7JDAKS3TS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WZHJJWGCDZ7Q2EWSZ7JDAKS3TS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:WZHJJWGCDZ7Q2EWSZ7JDAKS3TS","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":"b1ce03a444e90db54db74b819ed403c7405478a60ba7c8c704212ac85252ae7f","cross_cats_sorted":["cs.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-14T03:37:49Z","title_canon_sha256":"db9f93250acd8095451b670f7d78b4ebc9d07c794be2dcc8c9d017d9a8794e45"},"schema_version":"1.0","source":{"id":"1903.05803","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.05803","created_at":"2026-05-17T23:48:04Z"},{"alias_kind":"arxiv_version","alias_value":"1903.05803v2","created_at":"2026-05-17T23:48:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.05803","created_at":"2026-05-17T23:48:04Z"},{"alias_kind":"pith_short_12","alias_value":"WZHJJWGCDZ7Q","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"WZHJJWGCDZ7Q2EWS","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"WZHJJWGC","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:266870a86edfecf92338baa8b7c19126edca0e103b55a65f98e8a929e77e6dc2","target":"graph","created_at":"2026-05-17T23:48:04Z","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":"In decision making problems for continuous state and action spaces, linear dynamical models are widely employed. Specifically, policies for stochastic linear systems subject to quadratic cost functions capture a large number of applications in reinforcement learning. Selected randomized policies have been studied in the literature recently that address the trade-off between identification and control. However, little is known about policies based on bootstrapping observed states and actions. In this work, we show that bootstrap-based policies achieve a square root scaling of regret with respec","authors_text":"Ambuj Tewari, George Michailidis, Mohamad Kazem Shirani Faradonbeh","cross_cats":["cs.SY","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-14T03:37:49Z","title":"On Applications of Bootstrap in Continuous Space Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.05803","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:baa79cb77191818a45a704ffaff4b0f7e41a050c501247ecdefe6b4e531864b4","target":"record","created_at":"2026-05-17T23:48:04Z","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":"b1ce03a444e90db54db74b819ed403c7405478a60ba7c8c704212ac85252ae7f","cross_cats_sorted":["cs.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-14T03:37:49Z","title_canon_sha256":"db9f93250acd8095451b670f7d78b4ebc9d07c794be2dcc8c9d017d9a8794e45"},"schema_version":"1.0","source":{"id":"1903.05803","kind":"arxiv","version":2}},"canonical_sha256":"b64e94d8c21e7f0d12d2cfd2302a5b9ca1a9485ae3268afba5ec639d313f9986","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b64e94d8c21e7f0d12d2cfd2302a5b9ca1a9485ae3268afba5ec639d313f9986","first_computed_at":"2026-05-17T23:48:04.477965Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:48:04.477965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NQmRwbAVnvRYwmUrKQnsclEzO5PmzEcJBCMi3fGxEExSlO9EvNGPfUrFXrjpIIg1BeCoECusE1U8AR6sF4maAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:48:04.478368Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.05803","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:baa79cb77191818a45a704ffaff4b0f7e41a050c501247ecdefe6b4e531864b4","sha256:266870a86edfecf92338baa8b7c19126edca0e103b55a65f98e8a929e77e6dc2"],"state_sha256":"46713005f296f260bed9dbb95b7c79eeee165a36b5bf29b58dadb8c040a2125f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"scOG/Q+OFNJElCx6lIo/XfT0nXoHJ78RNfs50EsRT95f+YgNCZIzv3A1dESmFtUEgkJhjFdgcbjRbQOxXWiCDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T16:33:35.980975Z","bundle_sha256":"33a9ca80a6d589c14431013fd08541d85245ed9110f022d021a7abcc3433aea0"}}