{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:BOFFCX3NJ2FJKCPEOE2KTOW7KQ","short_pith_number":"pith:BOFFCX3N","canonical_record":{"source":{"id":"1607.00215","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-07-01T11:58:28Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"72a8e3d460cca5919721760020a62f3f01e1119ce938359a9ebbe70080411613","abstract_canon_sha256":"af5fb3fd692ad05c50076d745f646abcece506c4dcfd4aa90ac2e2e410ade0fc"},"schema_version":"1.0"},"canonical_sha256":"0b8a515f6d4e8a9509e47134a9badf54162df1d716d0635d439266a90daf4a96","source":{"kind":"arxiv","id":"1607.00215","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1607.00215","created_at":"2026-05-18T00:42:32Z"},{"alias_kind":"arxiv_version","alias_value":"1607.00215v3","created_at":"2026-05-18T00:42:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.00215","created_at":"2026-05-18T00:42:32Z"},{"alias_kind":"pith_short_12","alias_value":"BOFFCX3NJ2FJ","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_16","alias_value":"BOFFCX3NJ2FJKCPE","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_8","alias_value":"BOFFCX3N","created_at":"2026-05-18T12:30:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:BOFFCX3NJ2FJKCPEOE2KTOW7KQ","target":"record","payload":{"canonical_record":{"source":{"id":"1607.00215","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-07-01T11:58:28Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"72a8e3d460cca5919721760020a62f3f01e1119ce938359a9ebbe70080411613","abstract_canon_sha256":"af5fb3fd692ad05c50076d745f646abcece506c4dcfd4aa90ac2e2e410ade0fc"},"schema_version":"1.0"},"canonical_sha256":"0b8a515f6d4e8a9509e47134a9badf54162df1d716d0635d439266a90daf4a96","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:32.742688Z","signature_b64":"tfNGjSBv2s9lxEcwmwJ5IpIbU+vVFtEoAirr3l92S3CDpQ22W9t79ufqR23tL/WMx2IXjrkoSsai760I4P4fDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b8a515f6d4e8a9509e47134a9badf54162df1d716d0635d439266a90daf4a96","last_reissued_at":"2026-05-18T00:42:32.742040Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:32.742040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1607.00215","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:42:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"69mw0oh6Szr1NsT6Nj/0/yVlL+4OmiuWxx91EtjSULtW48e02UTF6DvnJDU2LwFVlFJCwvX/Xtqiizwz3CrECQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:07:09.536281Z"},"content_sha256":"43463e13cdf93cdec147b5a6bbffc34298bc837018437fcb2a2f2672d98ecb61","schema_version":"1.0","event_id":"sha256:43463e13cdf93cdec147b5a6bbffc34298bc837018437fcb2a2f2672d98ecb61"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:BOFFCX3NJ2FJKCPEOE2KTOW7KQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Why is Posterior Sampling Better than Optimism for Reinforcement Learning?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Benjamin Van Roy, Ian Osband","submitted_at":"2016-07-01T11:58:28Z","abstract_excerpt":"Computational results demonstrate that posterior sampling for reinforcement learning (PSRL) dramatically outperforms algorithms driven by optimism, such as UCRL2. We provide insight into the extent of this performance boost and the phenomenon that drives it. We leverage this insight to establish an $\\tilde{O}(H\\sqrt{SAT})$ Bayesian expected regret bound for PSRL in finite-horizon episodic Markov decision processes, where $H$ is the horizon, $S$ is the number of states, $A$ is the number of actions and $T$ is the time elapsed. This improves upon the best previous bound of $\\tilde{O}(H S \\sqrt{A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.00215","kind":"arxiv","version":3},"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":"2026-05-18T00:42:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b7ifpy1H8T4SqVUTVK/r+sLi7pbsFYIIsMsUNJRVEcHt67M2PAt/9khSCr5aN29i+AGt+3a3n3hGtst+Z1TRCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:07:09.536749Z"},"content_sha256":"1ba0afdcc4033e37bafe3fe426413265c2bf0e1264b338b102681de662adec88","schema_version":"1.0","event_id":"sha256:1ba0afdcc4033e37bafe3fe426413265c2bf0e1264b338b102681de662adec88"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BOFFCX3NJ2FJKCPEOE2KTOW7KQ/bundle.json","state_url":"https://pith.science/pith/BOFFCX3NJ2FJKCPEOE2KTOW7KQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BOFFCX3NJ2FJKCPEOE2KTOW7KQ/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":"2026-08-08T11:07:09Z","links":{"resolver":"https://pith.science/pith/BOFFCX3NJ2FJKCPEOE2KTOW7KQ","bundle":"https://pith.science/pith/BOFFCX3NJ2FJKCPEOE2KTOW7KQ/bundle.json","state":"https://pith.science/pith/BOFFCX3NJ2FJKCPEOE2KTOW7KQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BOFFCX3NJ2FJKCPEOE2KTOW7KQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:BOFFCX3NJ2FJKCPEOE2KTOW7KQ","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":"af5fb3fd692ad05c50076d745f646abcece506c4dcfd4aa90ac2e2e410ade0fc","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-07-01T11:58:28Z","title_canon_sha256":"72a8e3d460cca5919721760020a62f3f01e1119ce938359a9ebbe70080411613"},"schema_version":"1.0","source":{"id":"1607.00215","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1607.00215","created_at":"2026-05-18T00:42:32Z"},{"alias_kind":"arxiv_version","alias_value":"1607.00215v3","created_at":"2026-05-18T00:42:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.00215","created_at":"2026-05-18T00:42:32Z"},{"alias_kind":"pith_short_12","alias_value":"BOFFCX3NJ2FJ","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_16","alias_value":"BOFFCX3NJ2FJKCPE","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_8","alias_value":"BOFFCX3N","created_at":"2026-05-18T12:30:07Z"}],"graph_snapshots":[{"event_id":"sha256:1ba0afdcc4033e37bafe3fe426413265c2bf0e1264b338b102681de662adec88","target":"graph","created_at":"2026-05-18T00:42:32Z","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":"Computational results demonstrate that posterior sampling for reinforcement learning (PSRL) dramatically outperforms algorithms driven by optimism, such as UCRL2. We provide insight into the extent of this performance boost and the phenomenon that drives it. We leverage this insight to establish an $\\tilde{O}(H\\sqrt{SAT})$ Bayesian expected regret bound for PSRL in finite-horizon episodic Markov decision processes, where $H$ is the horizon, $S$ is the number of states, $A$ is the number of actions and $T$ is the time elapsed. This improves upon the best previous bound of $\\tilde{O}(H S \\sqrt{A","authors_text":"Benjamin Van Roy, Ian Osband","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-07-01T11:58:28Z","title":"Why is Posterior Sampling Better than Optimism for Reinforcement Learning?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.00215","kind":"arxiv","version":3},"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":"sha256:43463e13cdf93cdec147b5a6bbffc34298bc837018437fcb2a2f2672d98ecb61","target":"record","created_at":"2026-05-18T00:42:32Z","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":"af5fb3fd692ad05c50076d745f646abcece506c4dcfd4aa90ac2e2e410ade0fc","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-07-01T11:58:28Z","title_canon_sha256":"72a8e3d460cca5919721760020a62f3f01e1119ce938359a9ebbe70080411613"},"schema_version":"1.0","source":{"id":"1607.00215","kind":"arxiv","version":3}},"canonical_sha256":"0b8a515f6d4e8a9509e47134a9badf54162df1d716d0635d439266a90daf4a96","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b8a515f6d4e8a9509e47134a9badf54162df1d716d0635d439266a90daf4a96","first_computed_at":"2026-05-18T00:42:32.742040Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:42:32.742040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tfNGjSBv2s9lxEcwmwJ5IpIbU+vVFtEoAirr3l92S3CDpQ22W9t79ufqR23tL/WMx2IXjrkoSsai760I4P4fDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:42:32.742688Z","signed_message":"canonical_sha256_bytes"},"source_id":"1607.00215","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43463e13cdf93cdec147b5a6bbffc34298bc837018437fcb2a2f2672d98ecb61","sha256:1ba0afdcc4033e37bafe3fe426413265c2bf0e1264b338b102681de662adec88"],"state_sha256":"b24854a24610e47e7160a9d0e7c1cfa9780303a3b620307c1b3f294faa3aa423"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0gipvkghtCaUCJGoBdgZ0Iw+1o0UIXNNpkwaOO6j9Vadzai3sU3n0G5mOnz+hUstROQFCILM9+5lL3tmZTBxDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:07:09.540513Z","bundle_sha256":"0cb70c768c7d54ebd3557106d76c5101366f40848401f1318941f2e601111b3a"}}