{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:U7XAVTGZLQHEJLIJK2O2BMWYLI","short_pith_number":"pith:U7XAVTGZ","canonical_record":{"source":{"id":"1602.02523","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-08T11:08:49Z","cross_cats_sorted":["cs.LG","cs.SY"],"title_canon_sha256":"2c6b8d13deea22b41ba293847323aa47bbe649ead0e5ac97a49c3372761995fa","abstract_canon_sha256":"8d4153b5a70fac3d736c87a4d966a26359289ecaac5518b589e1c45ec3a8700b"},"schema_version":"1.0"},"canonical_sha256":"a7ee0accd95c0e44ad09569da0b2d85a02a327685a217acdd7bb19177d86e7d7","source":{"kind":"arxiv","id":"1602.02523","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.02523","created_at":"2026-05-18T01:21:09Z"},{"alias_kind":"arxiv_version","alias_value":"1602.02523v1","created_at":"2026-05-18T01:21:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.02523","created_at":"2026-05-18T01:21:09Z"},{"alias_kind":"pith_short_12","alias_value":"U7XAVTGZLQHE","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"U7XAVTGZLQHEJLIJ","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"U7XAVTGZ","created_at":"2026-05-18T12:30:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:U7XAVTGZLQHEJLIJK2O2BMWYLI","target":"record","payload":{"canonical_record":{"source":{"id":"1602.02523","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-08T11:08:49Z","cross_cats_sorted":["cs.LG","cs.SY"],"title_canon_sha256":"2c6b8d13deea22b41ba293847323aa47bbe649ead0e5ac97a49c3372761995fa","abstract_canon_sha256":"8d4153b5a70fac3d736c87a4d966a26359289ecaac5518b589e1c45ec3a8700b"},"schema_version":"1.0"},"canonical_sha256":"a7ee0accd95c0e44ad09569da0b2d85a02a327685a217acdd7bb19177d86e7d7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:21:09.596442Z","signature_b64":"DBQevPNAkrWqV4NgQKErEA50CIDcU0KyhsbJFccne1A8GPk7AOtPvBMbLb9w+p55mPVVvUciYKGglBwHSxBDDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7ee0accd95c0e44ad09569da0b2d85a02a327685a217acdd7bb19177d86e7d7","last_reissued_at":"2026-05-18T01:21:09.595893Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:21:09.595893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1602.02523","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:21:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HEM8w5cNvjynKn+Jwyh57BVXHrbvVDHArBxrVEa9dpt6SmkBqBDxnewX5AqQ1Na5TeoYBCvRSDQ/eU9vXgotAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T07:24:33.303194Z"},"content_sha256":"725bff79b9542a491a6eb4186f9279220ff859d05e009f6b6dab4ac87a2d0a05","schema_version":"1.0","event_id":"sha256:725bff79b9542a491a6eb4186f9279220ff859d05e009f6b6dab4ac87a2d0a05"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:U7XAVTGZLQHEJLIJK2O2BMWYLI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data-Efficient Reinforcement Learning in Continuous-State POMDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY"],"primary_cat":"stat.ML","authors_text":"Carl Edward Rasmussen, Rowan McAllister","submitted_at":"2016-02-08T11:08:49Z","abstract_excerpt":"We present a data-efficient reinforcement learning algorithm resistant to observation noise. Our method extends the highly data-efficient PILCO algorithm (Deisenroth & Rasmussen, 2011) into partially observed Markov decision processes (POMDPs) by considering the filtering process during policy evaluation. PILCO conducts policy search, evaluating each policy by first predicting an analytic distribution of possible system trajectories. We additionally predict trajectories w.r.t. a filtering process, achieving significantly higher performance than combining a filter with a policy optimised by the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.02523","kind":"arxiv","version":1},"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":"2026-05-18T01:21:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kCS0Us3H1ToUKVqGvhBNL//4XzZT+pBd1i7SBkAhAEak1QPmx1XAUcA8FPl3YdcCe7VX8BRwjWgx8l2bHeTDAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T07:24:33.303568Z"},"content_sha256":"6e199fffb74115ac035b537ca6089146f3fd8a31bbb5b7a4b337d1a00a8a13ff","schema_version":"1.0","event_id":"sha256:6e199fffb74115ac035b537ca6089146f3fd8a31bbb5b7a4b337d1a00a8a13ff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U7XAVTGZLQHEJLIJK2O2BMWYLI/bundle.json","state_url":"https://pith.science/pith/U7XAVTGZLQHEJLIJK2O2BMWYLI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U7XAVTGZLQHEJLIJK2O2BMWYLI/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":"2026-06-03T07:24:33Z","links":{"resolver":"https://pith.science/pith/U7XAVTGZLQHEJLIJK2O2BMWYLI","bundle":"https://pith.science/pith/U7XAVTGZLQHEJLIJK2O2BMWYLI/bundle.json","state":"https://pith.science/pith/U7XAVTGZLQHEJLIJK2O2BMWYLI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U7XAVTGZLQHEJLIJK2O2BMWYLI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:U7XAVTGZLQHEJLIJK2O2BMWYLI","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":"8d4153b5a70fac3d736c87a4d966a26359289ecaac5518b589e1c45ec3a8700b","cross_cats_sorted":["cs.LG","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-08T11:08:49Z","title_canon_sha256":"2c6b8d13deea22b41ba293847323aa47bbe649ead0e5ac97a49c3372761995fa"},"schema_version":"1.0","source":{"id":"1602.02523","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.02523","created_at":"2026-05-18T01:21:09Z"},{"alias_kind":"arxiv_version","alias_value":"1602.02523v1","created_at":"2026-05-18T01:21:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.02523","created_at":"2026-05-18T01:21:09Z"},{"alias_kind":"pith_short_12","alias_value":"U7XAVTGZLQHE","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"U7XAVTGZLQHEJLIJ","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"U7XAVTGZ","created_at":"2026-05-18T12:30:46Z"}],"graph_snapshots":[{"event_id":"sha256:6e199fffb74115ac035b537ca6089146f3fd8a31bbb5b7a4b337d1a00a8a13ff","target":"graph","created_at":"2026-05-18T01:21:09Z","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":"We present a data-efficient reinforcement learning algorithm resistant to observation noise. Our method extends the highly data-efficient PILCO algorithm (Deisenroth & Rasmussen, 2011) into partially observed Markov decision processes (POMDPs) by considering the filtering process during policy evaluation. PILCO conducts policy search, evaluating each policy by first predicting an analytic distribution of possible system trajectories. We additionally predict trajectories w.r.t. a filtering process, achieving significantly higher performance than combining a filter with a policy optimised by the","authors_text":"Carl Edward Rasmussen, Rowan McAllister","cross_cats":["cs.LG","cs.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-08T11:08:49Z","title":"Data-Efficient Reinforcement Learning in Continuous-State POMDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.02523","kind":"arxiv","version":1},"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":"sha256:725bff79b9542a491a6eb4186f9279220ff859d05e009f6b6dab4ac87a2d0a05","target":"record","created_at":"2026-05-18T01:21:09Z","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":"8d4153b5a70fac3d736c87a4d966a26359289ecaac5518b589e1c45ec3a8700b","cross_cats_sorted":["cs.LG","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-08T11:08:49Z","title_canon_sha256":"2c6b8d13deea22b41ba293847323aa47bbe649ead0e5ac97a49c3372761995fa"},"schema_version":"1.0","source":{"id":"1602.02523","kind":"arxiv","version":1}},"canonical_sha256":"a7ee0accd95c0e44ad09569da0b2d85a02a327685a217acdd7bb19177d86e7d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7ee0accd95c0e44ad09569da0b2d85a02a327685a217acdd7bb19177d86e7d7","first_computed_at":"2026-05-18T01:21:09.595893Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:21:09.595893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DBQevPNAkrWqV4NgQKErEA50CIDcU0KyhsbJFccne1A8GPk7AOtPvBMbLb9w+p55mPVVvUciYKGglBwHSxBDDg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:21:09.596442Z","signed_message":"canonical_sha256_bytes"},"source_id":"1602.02523","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:725bff79b9542a491a6eb4186f9279220ff859d05e009f6b6dab4ac87a2d0a05","sha256:6e199fffb74115ac035b537ca6089146f3fd8a31bbb5b7a4b337d1a00a8a13ff"],"state_sha256":"149246489e20560312fa4748f1afb9aca42ce462967a87a5ceb47dc2864277b7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nLX8MywNJl18UG2pWevTazgx7Y5BHNhdV4WZVYVkvrN5bUvoNOtxMbOp29JFHHOPVNuus4Crfl6ilEGYBcV+Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T07:24:33.305599Z","bundle_sha256":"1e0b0c46993e2a588afee52a3254063c51940dcc76171f99af30ef1cef46ba34"}}