{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:MBMUUXSXYTR4C7QZBC77DMUAMY","short_pith_number":"pith:MBMUUXSX","canonical_record":{"source":{"id":"1802.07668","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-02-21T17:07:06Z","cross_cats_sorted":[],"title_canon_sha256":"7254305d75495cf8e7f25c529f5e4b5d034a1b00005b96fd391d04de77baaca3","abstract_canon_sha256":"4059e5b8634b7dfb97d56a0418c8a982e3ad7c949e4ec14ea06550f3d96c6954"},"schema_version":"1.0"},"canonical_sha256":"60594a5e57c4e3c17e1908bff1b280662e8b7d9fe6ed1c70c240dbeb7743f1e4","source":{"kind":"arxiv","id":"1802.07668","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.07668","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"arxiv_version","alias_value":"1802.07668v1","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.07668","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"pith_short_12","alias_value":"MBMUUXSXYTR4","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"MBMUUXSXYTR4C7QZ","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"MBMUUXSX","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:MBMUUXSXYTR4C7QZBC77DMUAMY","target":"record","payload":{"canonical_record":{"source":{"id":"1802.07668","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-02-21T17:07:06Z","cross_cats_sorted":[],"title_canon_sha256":"7254305d75495cf8e7f25c529f5e4b5d034a1b00005b96fd391d04de77baaca3","abstract_canon_sha256":"4059e5b8634b7dfb97d56a0418c8a982e3ad7c949e4ec14ea06550f3d96c6954"},"schema_version":"1.0"},"canonical_sha256":"60594a5e57c4e3c17e1908bff1b280662e8b7d9fe6ed1c70c240dbeb7743f1e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:49.675652Z","signature_b64":"SsPKVKnxdPbWmgDycuJs1z83prRy9HD0xiIh8sHufKL+IDU6bJESYdTh7kiloWoqRm5UQ3cP4fdkCHVege3uCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60594a5e57c4e3c17e1908bff1b280662e8b7d9fe6ed1c70c240dbeb7743f1e4","last_reissued_at":"2026-05-18T00:22:49.675257Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:49.675257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.07668","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":"2026-05-18T00:22:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QWj2nMeb2vUi9nSCPSA5cRZZO6tzEQ7dKOvqFe3DXWh+TCasjPn/LvGvoHSaeYnVhkJvC8Vvd6P0WLQ1zN80Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T16:32:37.773599Z"},"content_sha256":"8b68c02df05218588cb4676a28dc062ac4825a85b0eee0f771433efd837177ea","schema_version":"1.0","event_id":"sha256:8b68c02df05218588cb4676a28dc062ac4825a85b0eee0f771433efd837177ea"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:MBMUUXSXYTR4C7QZBC77DMUAMY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A model for system uncertainty in reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Michele Palladino, Ryan Murray","submitted_at":"2018-02-21T17:07:06Z","abstract_excerpt":"This work provides a rigorous framework for studying continuous time control problems in uncertain environments. The framework considered models uncertainty in state dynamics as a measure on the space of functions. This measure is considered to change over time as agents learn their environment. This model can be seem as a variant of either Bayesian reinforcement learning or adaptive control. We study necessary conditions for locally optimal trajectories within this model, in particular deriving an appropriate dynamic programming principle and Hamilton-Jacobi equations. This model provides one"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.07668","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":"2026-05-18T00:22:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"amv4q03RgqkXkJ3u+J0M5l8j9ryjOS35H8/z5eiyH7bDRImEZ9wgcFq3vBuL1Rl2qXJzRYhrgNXqAJo0nvG2Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T16:32:37.773933Z"},"content_sha256":"f76ff356b861d01c2287b00b8e8b13ec1118abd6e21eed264fa4bef420862a75","schema_version":"1.0","event_id":"sha256:f76ff356b861d01c2287b00b8e8b13ec1118abd6e21eed264fa4bef420862a75"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MBMUUXSXYTR4C7QZBC77DMUAMY/bundle.json","state_url":"https://pith.science/pith/MBMUUXSXYTR4C7QZBC77DMUAMY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MBMUUXSXYTR4C7QZBC77DMUAMY/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":"2026-06-29T16:32:37Z","links":{"resolver":"https://pith.science/pith/MBMUUXSXYTR4C7QZBC77DMUAMY","bundle":"https://pith.science/pith/MBMUUXSXYTR4C7QZBC77DMUAMY/bundle.json","state":"https://pith.science/pith/MBMUUXSXYTR4C7QZBC77DMUAMY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MBMUUXSXYTR4C7QZBC77DMUAMY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:MBMUUXSXYTR4C7QZBC77DMUAMY","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":"4059e5b8634b7dfb97d56a0418c8a982e3ad7c949e4ec14ea06550f3d96c6954","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-02-21T17:07:06Z","title_canon_sha256":"7254305d75495cf8e7f25c529f5e4b5d034a1b00005b96fd391d04de77baaca3"},"schema_version":"1.0","source":{"id":"1802.07668","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.07668","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"arxiv_version","alias_value":"1802.07668v1","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.07668","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"pith_short_12","alias_value":"MBMUUXSXYTR4","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"MBMUUXSXYTR4C7QZ","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"MBMUUXSX","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:f76ff356b861d01c2287b00b8e8b13ec1118abd6e21eed264fa4bef420862a75","target":"graph","created_at":"2026-05-18T00:22:49Z","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":"This work provides a rigorous framework for studying continuous time control problems in uncertain environments. The framework considered models uncertainty in state dynamics as a measure on the space of functions. This measure is considered to change over time as agents learn their environment. This model can be seem as a variant of either Bayesian reinforcement learning or adaptive control. We study necessary conditions for locally optimal trajectories within this model, in particular deriving an appropriate dynamic programming principle and Hamilton-Jacobi equations. This model provides one","authors_text":"Michele Palladino, Ryan Murray","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-02-21T17:07:06Z","title":"A model for system uncertainty in reinforcement learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.07668","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":"sha256:8b68c02df05218588cb4676a28dc062ac4825a85b0eee0f771433efd837177ea","target":"record","created_at":"2026-05-18T00:22:49Z","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":"4059e5b8634b7dfb97d56a0418c8a982e3ad7c949e4ec14ea06550f3d96c6954","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-02-21T17:07:06Z","title_canon_sha256":"7254305d75495cf8e7f25c529f5e4b5d034a1b00005b96fd391d04de77baaca3"},"schema_version":"1.0","source":{"id":"1802.07668","kind":"arxiv","version":1}},"canonical_sha256":"60594a5e57c4e3c17e1908bff1b280662e8b7d9fe6ed1c70c240dbeb7743f1e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60594a5e57c4e3c17e1908bff1b280662e8b7d9fe6ed1c70c240dbeb7743f1e4","first_computed_at":"2026-05-18T00:22:49.675257Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:49.675257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SsPKVKnxdPbWmgDycuJs1z83prRy9HD0xiIh8sHufKL+IDU6bJESYdTh7kiloWoqRm5UQ3cP4fdkCHVege3uCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:49.675652Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.07668","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b68c02df05218588cb4676a28dc062ac4825a85b0eee0f771433efd837177ea","sha256:f76ff356b861d01c2287b00b8e8b13ec1118abd6e21eed264fa4bef420862a75"],"state_sha256":"955a7e55508baeb2535d09d1d4e58468c824c652e587a33439018d93086672f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/U1O8O0Y/zSdef7K//69H3zXnPrw76QsbcO2Yr+F2XwTERlfMSd5ToGaD8bAXJeJBO5hB5rkh+PTp+x8xy9JDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T16:32:37.775772Z","bundle_sha256":"98bbd9baf332dea70996d673840190725cec0d1f7fcf18f313598fe897ee9146"}}