{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:7YZKHVF4AUVB4WPSDXY7UK4JRF","short_pith_number":"pith:7YZKHVF4","canonical_record":{"source":{"id":"1709.05380","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-15T19:55:58Z","cross_cats_sorted":["cs.LG","math.OC","stat.ML"],"title_canon_sha256":"edc1b1528ff47f211084d84562649c158b519e7ca95af4ee18a81624f486505a","abstract_canon_sha256":"97b3de5284ddd2919fe34b67cd90db4b0ac7dbea6fcddec953487adcad542c8b"},"schema_version":"1.0"},"canonical_sha256":"fe32a3d4bc052a1e59f21df1fa2b8989520e1948f81fc981fcc6da7d0ac26217","source":{"kind":"arxiv","id":"1709.05380","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.05380","created_at":"2026-05-18T00:02:45Z"},{"alias_kind":"arxiv_version","alias_value":"1709.05380v4","created_at":"2026-05-18T00:02:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.05380","created_at":"2026-05-18T00:02:45Z"},{"alias_kind":"pith_short_12","alias_value":"7YZKHVF4AUVB","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"7YZKHVF4AUVB4WPS","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"7YZKHVF4","created_at":"2026-05-18T12:31:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:7YZKHVF4AUVB4WPSDXY7UK4JRF","target":"record","payload":{"canonical_record":{"source":{"id":"1709.05380","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-15T19:55:58Z","cross_cats_sorted":["cs.LG","math.OC","stat.ML"],"title_canon_sha256":"edc1b1528ff47f211084d84562649c158b519e7ca95af4ee18a81624f486505a","abstract_canon_sha256":"97b3de5284ddd2919fe34b67cd90db4b0ac7dbea6fcddec953487adcad542c8b"},"schema_version":"1.0"},"canonical_sha256":"fe32a3d4bc052a1e59f21df1fa2b8989520e1948f81fc981fcc6da7d0ac26217","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:45.596925Z","signature_b64":"PMS1pe+dJd0a05dtEt5L/quVSxBHZ3XgZKp92r7jqp1owFWM/Evw9DmmMfFPhAlag0oP1CTNcXd6bEVO7avlAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe32a3d4bc052a1e59f21df1fa2b8989520e1948f81fc981fcc6da7d0ac26217","last_reissued_at":"2026-05-18T00:02:45.596478Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:45.596478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.05380","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:02:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fSYvUDX7tedprtil4KgHd4HZWSiKLMPiFasBzBAQug6DZqa1duZmRiotQnJJvvJw/1Nyl1A7PhVPxhDFmhRHAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T02:22:20.538822Z"},"content_sha256":"5aeef7bd9789a2bd2358b5eac5a620d1a231e9ea8eaa61fbe548532bb5463e8f","schema_version":"1.0","event_id":"sha256:5aeef7bd9789a2bd2358b5eac5a620d1a231e9ea8eaa61fbe548532bb5463e8f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:7YZKHVF4AUVB4WPSDXY7UK4JRF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Uncertainty Bellman Equation and Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC","stat.ML"],"primary_cat":"cs.AI","authors_text":"Brendan O'Donoghue, Ian Osband, Remi Munos, Volodymyr Mnih","submitted_at":"2017-09-15T19:55:58Z","abstract_excerpt":"We consider the exploration/exploitation problem in reinforcement learning. For exploitation, it is well known that the Bellman equation connects the value at any time-step to the expected value at subsequent time-steps. In this paper we consider a similar \\textit{uncertainty} Bellman equation (UBE), which connects the uncertainty at any time-step to the expected uncertainties at subsequent time-steps, thereby extending the potential exploratory benefit of a policy beyond individual time-steps. We prove that the unique fixed point of the UBE yields an upper bound on the variance of the posteri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.05380","kind":"arxiv","version":4},"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":"2026-05-18T00:02:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MrDfBUBAA86pEfHhLvQ4lSBuhgdIJdhbGk/qHqIKpvzWyc4BfwOWNbFjdId31qwPNxTH58vPktOZP56KsWABDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T02:22:20.539473Z"},"content_sha256":"e14cb8fc8a7029d6b0fae1f90d5df06dba6ffb6d4083ce804288bf2af37679db","schema_version":"1.0","event_id":"sha256:e14cb8fc8a7029d6b0fae1f90d5df06dba6ffb6d4083ce804288bf2af37679db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7YZKHVF4AUVB4WPSDXY7UK4JRF/bundle.json","state_url":"https://pith.science/pith/7YZKHVF4AUVB4WPSDXY7UK4JRF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7YZKHVF4AUVB4WPSDXY7UK4JRF/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":"2026-05-26T02:22:20Z","links":{"resolver":"https://pith.science/pith/7YZKHVF4AUVB4WPSDXY7UK4JRF","bundle":"https://pith.science/pith/7YZKHVF4AUVB4WPSDXY7UK4JRF/bundle.json","state":"https://pith.science/pith/7YZKHVF4AUVB4WPSDXY7UK4JRF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7YZKHVF4AUVB4WPSDXY7UK4JRF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:7YZKHVF4AUVB4WPSDXY7UK4JRF","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":"97b3de5284ddd2919fe34b67cd90db4b0ac7dbea6fcddec953487adcad542c8b","cross_cats_sorted":["cs.LG","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-15T19:55:58Z","title_canon_sha256":"edc1b1528ff47f211084d84562649c158b519e7ca95af4ee18a81624f486505a"},"schema_version":"1.0","source":{"id":"1709.05380","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.05380","created_at":"2026-05-18T00:02:45Z"},{"alias_kind":"arxiv_version","alias_value":"1709.05380v4","created_at":"2026-05-18T00:02:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.05380","created_at":"2026-05-18T00:02:45Z"},{"alias_kind":"pith_short_12","alias_value":"7YZKHVF4AUVB","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"7YZKHVF4AUVB4WPS","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"7YZKHVF4","created_at":"2026-05-18T12:31:05Z"}],"graph_snapshots":[{"event_id":"sha256:e14cb8fc8a7029d6b0fae1f90d5df06dba6ffb6d4083ce804288bf2af37679db","target":"graph","created_at":"2026-05-18T00:02:45Z","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 consider the exploration/exploitation problem in reinforcement learning. For exploitation, it is well known that the Bellman equation connects the value at any time-step to the expected value at subsequent time-steps. In this paper we consider a similar \\textit{uncertainty} Bellman equation (UBE), which connects the uncertainty at any time-step to the expected uncertainties at subsequent time-steps, thereby extending the potential exploratory benefit of a policy beyond individual time-steps. We prove that the unique fixed point of the UBE yields an upper bound on the variance of the posteri","authors_text":"Brendan O'Donoghue, Ian Osband, Remi Munos, Volodymyr Mnih","cross_cats":["cs.LG","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-15T19:55:58Z","title":"The Uncertainty Bellman Equation and Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.05380","kind":"arxiv","version":4},"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":"sha256:5aeef7bd9789a2bd2358b5eac5a620d1a231e9ea8eaa61fbe548532bb5463e8f","target":"record","created_at":"2026-05-18T00:02:45Z","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":"97b3de5284ddd2919fe34b67cd90db4b0ac7dbea6fcddec953487adcad542c8b","cross_cats_sorted":["cs.LG","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-15T19:55:58Z","title_canon_sha256":"edc1b1528ff47f211084d84562649c158b519e7ca95af4ee18a81624f486505a"},"schema_version":"1.0","source":{"id":"1709.05380","kind":"arxiv","version":4}},"canonical_sha256":"fe32a3d4bc052a1e59f21df1fa2b8989520e1948f81fc981fcc6da7d0ac26217","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe32a3d4bc052a1e59f21df1fa2b8989520e1948f81fc981fcc6da7d0ac26217","first_computed_at":"2026-05-18T00:02:45.596478Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:45.596478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PMS1pe+dJd0a05dtEt5L/quVSxBHZ3XgZKp92r7jqp1owFWM/Evw9DmmMfFPhAlag0oP1CTNcXd6bEVO7avlAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:45.596925Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.05380","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5aeef7bd9789a2bd2358b5eac5a620d1a231e9ea8eaa61fbe548532bb5463e8f","sha256:e14cb8fc8a7029d6b0fae1f90d5df06dba6ffb6d4083ce804288bf2af37679db"],"state_sha256":"68a41f51e89a6d22fbe6463c670cd9f720808b9c5f716526b3c6ac3e3eb04cb2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oR7XgrSX9+9OEGIcUEPgLtanVJhNsui2kfkl0/Uac/f6Nuk3blgVewQ8oRBtH6L7UcYxoMAlHadcS4HX0VtCBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T02:22:20.541984Z","bundle_sha256":"cb7c5f0bab4987958881b07192959aa625d89fc69715b25cd321864e0392c998"}}