{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2013:HYLKUE2MZYNNLUH5RHQ24GGFOL","short_pith_number":"pith:HYLKUE2M","canonical_record":{"source":{"id":"1306.1553","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-06-06T20:57:19Z","cross_cats_sorted":[],"title_canon_sha256":"2e91559149cd211ec60e5be3f64d843b1e3103104fca6afda4e0f7d3cb8a84a8","abstract_canon_sha256":"ec8c3660164d3e703861646b786d054e704c0ced1c7d5556f241e5a337c29936"},"schema_version":"1.0"},"canonical_sha256":"3e16aa134cce1ad5d0fd89e1ae18c572c4b3c20ca6bf470bdb05c7f22127ef40","source":{"kind":"arxiv","id":"1306.1553","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1306.1553","created_at":"2026-05-18T03:19:58Z"},{"alias_kind":"arxiv_version","alias_value":"1306.1553v2","created_at":"2026-05-18T03:19:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1306.1553","created_at":"2026-05-18T03:19:58Z"},{"alias_kind":"pith_short_12","alias_value":"HYLKUE2MZYNN","created_at":"2026-05-18T12:27:46Z"},{"alias_kind":"pith_short_16","alias_value":"HYLKUE2MZYNNLUH5","created_at":"2026-05-18T12:27:46Z"},{"alias_kind":"pith_short_8","alias_value":"HYLKUE2M","created_at":"2026-05-18T12:27:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2013:HYLKUE2MZYNNLUH5RHQ24GGFOL","target":"record","payload":{"canonical_record":{"source":{"id":"1306.1553","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-06-06T20:57:19Z","cross_cats_sorted":[],"title_canon_sha256":"2e91559149cd211ec60e5be3f64d843b1e3103104fca6afda4e0f7d3cb8a84a8","abstract_canon_sha256":"ec8c3660164d3e703861646b786d054e704c0ced1c7d5556f241e5a337c29936"},"schema_version":"1.0"},"canonical_sha256":"3e16aa134cce1ad5d0fd89e1ae18c572c4b3c20ca6bf470bdb05c7f22127ef40","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:19:58.713110Z","signature_b64":"gNn7h7J5Z/EOYc4VXjSFvPfrvBbXAaO+UoTtBdJWU1LPes3YBTDcKTGwOYsOCtCPs4GZ7VqYV9BpfZy2OlcxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e16aa134cce1ad5d0fd89e1ae18c572c4b3c20ca6bf470bdb05c7f22127ef40","last_reissued_at":"2026-05-18T03:19:58.712500Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:19:58.712500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1306.1553","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":"2026-05-18T03:19:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"91bkUCS9L7XHjkdsb1c042qjS2RCRwsJK6nusdRuBAMmIiUxZPuOIoixr0BJU5W+OmyNUs/8m9fYh3kHwI/0Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T15:01:04.429079Z"},"content_sha256":"0b372be8b9b96104c90998c3fb3d1cdc92f7816a592d2cf2bf1965e06b5e49d3","schema_version":"1.0","event_id":"sha256:0b372be8b9b96104c90998c3fb3d1cdc92f7816a592d2cf2bf1965e06b5e49d3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2013:HYLKUE2MZYNNLUH5RHQ24GGFOL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Direct Uncertainty Estimation in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alexey Potapov, Sergey Rodionov, Yurii Vinogradov","submitted_at":"2013-06-06T20:57:19Z","abstract_excerpt":"Optimal probabilistic approach in reinforcement learning is computationally infeasible. Its simplification consisting in neglecting difference between true environment and its model estimated using limited number of observations causes exploration vs exploitation problem. Uncertainty can be expressed in terms of a probability distribution over the space of environment models, and this uncertainty can be propagated to the action-value function via Bellman iterations, which are computationally insufficiently efficient though. We consider possibility of directly measuring uncertainty of the actio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1306.1553","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":"2026-05-18T03:19:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"es5VgaGjFosOccjPnMWxzPbpLh1RQqhg3Iz4W30wy4G8RuiN7kDJOtUSC7AHQeZ15FKgUvLR0ZaPEelfJ0f0DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T15:01:04.429433Z"},"content_sha256":"06fa523c24224f702f16227ef71a13f491a7ca82ee407298979b5878b6f29955","schema_version":"1.0","event_id":"sha256:06fa523c24224f702f16227ef71a13f491a7ca82ee407298979b5878b6f29955"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HYLKUE2MZYNNLUH5RHQ24GGFOL/bundle.json","state_url":"https://pith.science/pith/HYLKUE2MZYNNLUH5RHQ24GGFOL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HYLKUE2MZYNNLUH5RHQ24GGFOL/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":"2026-05-28T15:01:04Z","links":{"resolver":"https://pith.science/pith/HYLKUE2MZYNNLUH5RHQ24GGFOL","bundle":"https://pith.science/pith/HYLKUE2MZYNNLUH5RHQ24GGFOL/bundle.json","state":"https://pith.science/pith/HYLKUE2MZYNNLUH5RHQ24GGFOL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HYLKUE2MZYNNLUH5RHQ24GGFOL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:HYLKUE2MZYNNLUH5RHQ24GGFOL","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":"ec8c3660164d3e703861646b786d054e704c0ced1c7d5556f241e5a337c29936","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-06-06T20:57:19Z","title_canon_sha256":"2e91559149cd211ec60e5be3f64d843b1e3103104fca6afda4e0f7d3cb8a84a8"},"schema_version":"1.0","source":{"id":"1306.1553","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1306.1553","created_at":"2026-05-18T03:19:58Z"},{"alias_kind":"arxiv_version","alias_value":"1306.1553v2","created_at":"2026-05-18T03:19:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1306.1553","created_at":"2026-05-18T03:19:58Z"},{"alias_kind":"pith_short_12","alias_value":"HYLKUE2MZYNN","created_at":"2026-05-18T12:27:46Z"},{"alias_kind":"pith_short_16","alias_value":"HYLKUE2MZYNNLUH5","created_at":"2026-05-18T12:27:46Z"},{"alias_kind":"pith_short_8","alias_value":"HYLKUE2M","created_at":"2026-05-18T12:27:46Z"}],"graph_snapshots":[{"event_id":"sha256:06fa523c24224f702f16227ef71a13f491a7ca82ee407298979b5878b6f29955","target":"graph","created_at":"2026-05-18T03:19:58Z","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":"Optimal probabilistic approach in reinforcement learning is computationally infeasible. Its simplification consisting in neglecting difference between true environment and its model estimated using limited number of observations causes exploration vs exploitation problem. Uncertainty can be expressed in terms of a probability distribution over the space of environment models, and this uncertainty can be propagated to the action-value function via Bellman iterations, which are computationally insufficiently efficient though. We consider possibility of directly measuring uncertainty of the actio","authors_text":"Alexey Potapov, Sergey Rodionov, Yurii Vinogradov","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-06-06T20:57:19Z","title":"Direct Uncertainty Estimation in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1306.1553","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":"sha256:0b372be8b9b96104c90998c3fb3d1cdc92f7816a592d2cf2bf1965e06b5e49d3","target":"record","created_at":"2026-05-18T03:19:58Z","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":"ec8c3660164d3e703861646b786d054e704c0ced1c7d5556f241e5a337c29936","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-06-06T20:57:19Z","title_canon_sha256":"2e91559149cd211ec60e5be3f64d843b1e3103104fca6afda4e0f7d3cb8a84a8"},"schema_version":"1.0","source":{"id":"1306.1553","kind":"arxiv","version":2}},"canonical_sha256":"3e16aa134cce1ad5d0fd89e1ae18c572c4b3c20ca6bf470bdb05c7f22127ef40","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e16aa134cce1ad5d0fd89e1ae18c572c4b3c20ca6bf470bdb05c7f22127ef40","first_computed_at":"2026-05-18T03:19:58.712500Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:19:58.712500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gNn7h7J5Z/EOYc4VXjSFvPfrvBbXAaO+UoTtBdJWU1LPes3YBTDcKTGwOYsOCtCPs4GZ7VqYV9BpfZy2OlcxAA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:19:58.713110Z","signed_message":"canonical_sha256_bytes"},"source_id":"1306.1553","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b372be8b9b96104c90998c3fb3d1cdc92f7816a592d2cf2bf1965e06b5e49d3","sha256:06fa523c24224f702f16227ef71a13f491a7ca82ee407298979b5878b6f29955"],"state_sha256":"c023fd85864f82b1c33cb6e9656bdbda1cebb5010ec5d5461933122d47061478"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"87snHUOF6C2aO9M/hxHr3gTRvAxMRNAb5LEDtbh9Mva4t0aOCtuP1fgq9peCKQrkbG1pWcJIwR/UIiWf/WRoCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T15:01:04.431338Z","bundle_sha256":"9c324ec931522ed8b6c54651082d91259c4bc1e4a26a1d88ae4a7f2512ac9fab"}}