{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2009:IUT7JOOXVRXBD2YETIUADJ6ZD2","short_pith_number":"pith:IUT7JOOX","canonical_record":{"source":{"id":"0902.0392","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2009-02-02T22:37:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c7e8c7c83dc365674b53c10dc8f78ed3301bc8ffcd3eb35b66e61a4cfaf3bc8b","abstract_canon_sha256":"ae27407b7d7b6bcd73233130b63f5c91870675d9d251554a6b75ba9db265b2ab"},"schema_version":"1.0"},"canonical_sha256":"4527f4b9d7ac6e11eb049a2801a7d91ebe150f49efebdc4d3271c41604dde281","source":{"kind":"arxiv","id":"0902.0392","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"0902.0392","created_at":"2026-05-18T04:12:43Z"},{"alias_kind":"arxiv_version","alias_value":"0902.0392v2","created_at":"2026-05-18T04:12:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.0902.0392","created_at":"2026-05-18T04:12:43Z"},{"alias_kind":"pith_short_12","alias_value":"IUT7JOOXVRXB","created_at":"2026-05-18T12:26:00Z"},{"alias_kind":"pith_short_16","alias_value":"IUT7JOOXVRXBD2YE","created_at":"2026-05-18T12:26:00Z"},{"alias_kind":"pith_short_8","alias_value":"IUT7JOOX","created_at":"2026-05-18T12:26:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2009:IUT7JOOXVRXBD2YETIUADJ6ZD2","target":"record","payload":{"canonical_record":{"source":{"id":"0902.0392","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2009-02-02T22:37:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c7e8c7c83dc365674b53c10dc8f78ed3301bc8ffcd3eb35b66e61a4cfaf3bc8b","abstract_canon_sha256":"ae27407b7d7b6bcd73233130b63f5c91870675d9d251554a6b75ba9db265b2ab"},"schema_version":"1.0"},"canonical_sha256":"4527f4b9d7ac6e11eb049a2801a7d91ebe150f49efebdc4d3271c41604dde281","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:12:43.196475Z","signature_b64":"Rnx4fwfghk/+hkjvZAa133lebo+Ll5wNkg+DY6RrGozm+lkFb3L31tR3JDVjuk5xjX6a6uZ8usS2EIUM+xVbCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4527f4b9d7ac6e11eb049a2801a7d91ebe150f49efebdc4d3271c41604dde281","last_reissued_at":"2026-05-18T04:12:43.195865Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:12:43.195865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"0902.0392","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":"2026-05-18T04:12:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ExYdFKuPfKdkQjmbm51TEOng+3H0d9Y9yssXc1kfezgfn03el4yjHUqgZdZz7+8qm1qUBt3iDxqPJUwoukUADg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T14:58:38.602609Z"},"content_sha256":"e9625e19e968a9914dd19f3e76177fda542fc716acc5c053d8c02a241e41bd5e","schema_version":"1.0","event_id":"sha256:e9625e19e968a9914dd19f3e76177fda542fc716acc5c053d8c02a241e41bd5e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2009:IUT7JOOXVRXBD2YETIUADJ6ZD2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tree Exploration for Bayesian RL Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Christos Dimitrakakis","submitted_at":"2009-02-02T22:37:23Z","abstract_excerpt":"Research in reinforcement learning has produced algorithms for optimal decision making under uncertainty that fall within two main types. The first employs a Bayesian framework, where optimality improves with increased computational time. This is because the resulting planning task takes the form of a dynamic programming problem on a belief tree with an infinite number of states. The second type employs relatively simple algorithm which are shown to suffer small regret within a distribution-free framework. This paper presents a lower bound and a high probability upper bound on the optimal valu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"0902.0392","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":"2026-05-18T04:12:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oRyTkl1VKR6yr8QDqwbcEtKw5Y10i2VUW6CCRKJjqwd3Ggoxcj9V00f5pY9ltFPMprHcF45y92yXufvVm6uFCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T14:58:38.602972Z"},"content_sha256":"e4439ae4583758e469eb8511d99a23303f4edbee68d02501b222a51adb04a0fb","schema_version":"1.0","event_id":"sha256:e4439ae4583758e469eb8511d99a23303f4edbee68d02501b222a51adb04a0fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IUT7JOOXVRXBD2YETIUADJ6ZD2/bundle.json","state_url":"https://pith.science/pith/IUT7JOOXVRXBD2YETIUADJ6ZD2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IUT7JOOXVRXBD2YETIUADJ6ZD2/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":"2026-06-11T14:58:38Z","links":{"resolver":"https://pith.science/pith/IUT7JOOXVRXBD2YETIUADJ6ZD2","bundle":"https://pith.science/pith/IUT7JOOXVRXBD2YETIUADJ6ZD2/bundle.json","state":"https://pith.science/pith/IUT7JOOXVRXBD2YETIUADJ6ZD2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IUT7JOOXVRXBD2YETIUADJ6ZD2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2009:IUT7JOOXVRXBD2YETIUADJ6ZD2","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":"ae27407b7d7b6bcd73233130b63f5c91870675d9d251554a6b75ba9db265b2ab","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2009-02-02T22:37:23Z","title_canon_sha256":"c7e8c7c83dc365674b53c10dc8f78ed3301bc8ffcd3eb35b66e61a4cfaf3bc8b"},"schema_version":"1.0","source":{"id":"0902.0392","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"0902.0392","created_at":"2026-05-18T04:12:43Z"},{"alias_kind":"arxiv_version","alias_value":"0902.0392v2","created_at":"2026-05-18T04:12:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.0902.0392","created_at":"2026-05-18T04:12:43Z"},{"alias_kind":"pith_short_12","alias_value":"IUT7JOOXVRXB","created_at":"2026-05-18T12:26:00Z"},{"alias_kind":"pith_short_16","alias_value":"IUT7JOOXVRXBD2YE","created_at":"2026-05-18T12:26:00Z"},{"alias_kind":"pith_short_8","alias_value":"IUT7JOOX","created_at":"2026-05-18T12:26:00Z"}],"graph_snapshots":[{"event_id":"sha256:e4439ae4583758e469eb8511d99a23303f4edbee68d02501b222a51adb04a0fb","target":"graph","created_at":"2026-05-18T04:12:43Z","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":"Research in reinforcement learning has produced algorithms for optimal decision making under uncertainty that fall within two main types. The first employs a Bayesian framework, where optimality improves with increased computational time. This is because the resulting planning task takes the form of a dynamic programming problem on a belief tree with an infinite number of states. The second type employs relatively simple algorithm which are shown to suffer small regret within a distribution-free framework. This paper presents a lower bound and a high probability upper bound on the optimal valu","authors_text":"Christos Dimitrakakis","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2009-02-02T22:37:23Z","title":"Tree Exploration for Bayesian RL Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"0902.0392","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:e9625e19e968a9914dd19f3e76177fda542fc716acc5c053d8c02a241e41bd5e","target":"record","created_at":"2026-05-18T04:12:43Z","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":"ae27407b7d7b6bcd73233130b63f5c91870675d9d251554a6b75ba9db265b2ab","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2009-02-02T22:37:23Z","title_canon_sha256":"c7e8c7c83dc365674b53c10dc8f78ed3301bc8ffcd3eb35b66e61a4cfaf3bc8b"},"schema_version":"1.0","source":{"id":"0902.0392","kind":"arxiv","version":2}},"canonical_sha256":"4527f4b9d7ac6e11eb049a2801a7d91ebe150f49efebdc4d3271c41604dde281","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4527f4b9d7ac6e11eb049a2801a7d91ebe150f49efebdc4d3271c41604dde281","first_computed_at":"2026-05-18T04:12:43.195865Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:12:43.195865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Rnx4fwfghk/+hkjvZAa133lebo+Ll5wNkg+DY6RrGozm+lkFb3L31tR3JDVjuk5xjX6a6uZ8usS2EIUM+xVbCg==","signature_status":"signed_v1","signed_at":"2026-05-18T04:12:43.196475Z","signed_message":"canonical_sha256_bytes"},"source_id":"0902.0392","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9625e19e968a9914dd19f3e76177fda542fc716acc5c053d8c02a241e41bd5e","sha256:e4439ae4583758e469eb8511d99a23303f4edbee68d02501b222a51adb04a0fb"],"state_sha256":"553b2cac34ac5466abe9e537ac4407703b20da5420d24a1de57d895c56962d42"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tomNRFviXfiqeQm44Vm95TmcmCfTFaiH0OyTAKEBCKb/HCNlFw7G4lij+sBEEtEW+XZ5xBSkQA82FZAEtaLNCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T14:58:38.606418Z","bundle_sha256":"732b34cae302513c9db8e9635a0dae54fdc6b197dba8090d22838da04584c9b9"}}