{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:MLDKJS2B5UX7W42PDQSZJMJEFE","short_pith_number":"pith:MLDKJS2B","canonical_record":{"source":{"id":"1811.07201","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-17T18:06:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7802e77b196804fc6f65b047cc459821e452bf24836f506ef2874700a4feab6a","abstract_canon_sha256":"621b0d98a0209dfcb2e68b246ef82d3771c79080e6e994af4844db81f20afa76"},"schema_version":"1.0"},"canonical_sha256":"62c6a4cb41ed2ffb734f1c2594b12429246cfd4ea131a29e50a3ac4f00fb2e41","source":{"kind":"arxiv","id":"1811.07201","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.07201","created_at":"2026-05-18T00:00:28Z"},{"alias_kind":"arxiv_version","alias_value":"1811.07201v1","created_at":"2026-05-18T00:00:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.07201","created_at":"2026-05-18T00:00:28Z"},{"alias_kind":"pith_short_12","alias_value":"MLDKJS2B5UX7","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"MLDKJS2B5UX7W42P","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"MLDKJS2B","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:MLDKJS2B5UX7W42PDQSZJMJEFE","target":"record","payload":{"canonical_record":{"source":{"id":"1811.07201","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-17T18:06:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7802e77b196804fc6f65b047cc459821e452bf24836f506ef2874700a4feab6a","abstract_canon_sha256":"621b0d98a0209dfcb2e68b246ef82d3771c79080e6e994af4844db81f20afa76"},"schema_version":"1.0"},"canonical_sha256":"62c6a4cb41ed2ffb734f1c2594b12429246cfd4ea131a29e50a3ac4f00fb2e41","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:28.642856Z","signature_b64":"ZbwUo5JrbIMVqwnmaQuoNth+l5EiR01WMUoVWtYPjpRWlGRsQE8qemn4xebdsvZ/B6wQ3QzJg+2Ls2WCH04WCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62c6a4cb41ed2ffb734f1c2594b12429246cfd4ea131a29e50a3ac4f00fb2e41","last_reissued_at":"2026-05-18T00:00:28.642365Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:28.642365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.07201","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":"2026-05-18T00:00:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i869T3UGMwPCqvI4Mon7XD7LjXPnHJWd/wEBV7qWdUgi7y147sY1y34aiYsznK+xpsljWs9b4JpJk3HUIuUABA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T20:09:03.347628Z"},"content_sha256":"80e94358c999b476e5adce05a98a04752e334f6532775af7fb93a34e28c8257b","schema_version":"1.0","event_id":"sha256:80e94358c999b476e5adce05a98a04752e334f6532775af7fb93a34e28c8257b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:MLDKJS2B5UX7W42PDQSZJMJEFE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Recursive Sparse Pseudo-input Gaussian Process SARSA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Brendan Englot, John Martin","submitted_at":"2018-11-17T18:06:37Z","abstract_excerpt":"The class of Gaussian Process (GP) methods for Temporal Difference learning has shown promise for data-efficient model-free Reinforcement Learning. In this paper, we consider a recent variant of the GP-SARSA algorithm, called Sparse Pseudo-input Gaussian Process SARSA (SPGP-SARSA), and derive recursive formulas for its predictive moments. This extension promotes greater memory efficiency, since previous computations can be reused and, interestingly, it provides a technique for updating value estimates on a multiple timescales"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.07201","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":"2026-05-18T00:00:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3Cu1z61+wNzar3kszhzz0QCrG3LTc+eN32LfSWO9bW4lJ7NvgauLKqNNHqPKA3oyBxFIhrj0U9IjEdz7t9wwBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T20:09:03.348350Z"},"content_sha256":"eac4df4ef8a008d230383d2781e7184dfdb21f13308931f1047d78de662275c7","schema_version":"1.0","event_id":"sha256:eac4df4ef8a008d230383d2781e7184dfdb21f13308931f1047d78de662275c7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MLDKJS2B5UX7W42PDQSZJMJEFE/bundle.json","state_url":"https://pith.science/pith/MLDKJS2B5UX7W42PDQSZJMJEFE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MLDKJS2B5UX7W42PDQSZJMJEFE/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":"2026-05-27T20:09:03Z","links":{"resolver":"https://pith.science/pith/MLDKJS2B5UX7W42PDQSZJMJEFE","bundle":"https://pith.science/pith/MLDKJS2B5UX7W42PDQSZJMJEFE/bundle.json","state":"https://pith.science/pith/MLDKJS2B5UX7W42PDQSZJMJEFE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MLDKJS2B5UX7W42PDQSZJMJEFE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:MLDKJS2B5UX7W42PDQSZJMJEFE","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":"621b0d98a0209dfcb2e68b246ef82d3771c79080e6e994af4844db81f20afa76","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-17T18:06:37Z","title_canon_sha256":"7802e77b196804fc6f65b047cc459821e452bf24836f506ef2874700a4feab6a"},"schema_version":"1.0","source":{"id":"1811.07201","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.07201","created_at":"2026-05-18T00:00:28Z"},{"alias_kind":"arxiv_version","alias_value":"1811.07201v1","created_at":"2026-05-18T00:00:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.07201","created_at":"2026-05-18T00:00:28Z"},{"alias_kind":"pith_short_12","alias_value":"MLDKJS2B5UX7","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"MLDKJS2B5UX7W42P","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"MLDKJS2B","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:eac4df4ef8a008d230383d2781e7184dfdb21f13308931f1047d78de662275c7","target":"graph","created_at":"2026-05-18T00:00:28Z","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":"The class of Gaussian Process (GP) methods for Temporal Difference learning has shown promise for data-efficient model-free Reinforcement Learning. In this paper, we consider a recent variant of the GP-SARSA algorithm, called Sparse Pseudo-input Gaussian Process SARSA (SPGP-SARSA), and derive recursive formulas for its predictive moments. This extension promotes greater memory efficiency, since previous computations can be reused and, interestingly, it provides a technique for updating value estimates on a multiple timescales","authors_text":"Brendan Englot, John Martin","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-17T18:06:37Z","title":"Recursive Sparse Pseudo-input Gaussian Process SARSA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.07201","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":"sha256:80e94358c999b476e5adce05a98a04752e334f6532775af7fb93a34e28c8257b","target":"record","created_at":"2026-05-18T00:00:28Z","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":"621b0d98a0209dfcb2e68b246ef82d3771c79080e6e994af4844db81f20afa76","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-17T18:06:37Z","title_canon_sha256":"7802e77b196804fc6f65b047cc459821e452bf24836f506ef2874700a4feab6a"},"schema_version":"1.0","source":{"id":"1811.07201","kind":"arxiv","version":1}},"canonical_sha256":"62c6a4cb41ed2ffb734f1c2594b12429246cfd4ea131a29e50a3ac4f00fb2e41","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"62c6a4cb41ed2ffb734f1c2594b12429246cfd4ea131a29e50a3ac4f00fb2e41","first_computed_at":"2026-05-18T00:00:28.642365Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:00:28.642365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZbwUo5JrbIMVqwnmaQuoNth+l5EiR01WMUoVWtYPjpRWlGRsQE8qemn4xebdsvZ/B6wQ3QzJg+2Ls2WCH04WCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:00:28.642856Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.07201","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80e94358c999b476e5adce05a98a04752e334f6532775af7fb93a34e28c8257b","sha256:eac4df4ef8a008d230383d2781e7184dfdb21f13308931f1047d78de662275c7"],"state_sha256":"3e4fa43379541a5e42c1fb2f9a36ad7cb46b60809ddcc16fd5f7a9ea5eed2c0f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wVkp9rL8fM/71n0lf6dGrGiyus6UMJCmp4AF0Xswtzr1SCU5pkA75Sw1TG5FJOFOTERl5Um7IIpZARiHGZXRCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T20:09:03.352364Z","bundle_sha256":"2b54933774dc2a1e3e00c83b14ca7d8a6e690341c74e6bf5943880cce43c9a61"}}