{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:JFHS3YUP76QVUXULQ2HC5JQS7Y","short_pith_number":"pith:JFHS3YUP","canonical_record":{"source":{"id":"1608.02731","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-08-09T09:01:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8eea998ac80b609921d952c5fe4115d93bba1bde423c12756adae929985dfb76","abstract_canon_sha256":"41bf29dd54d0b71e9bd1c5fbff9cbe30d61afe0673be4b2dc9fc69e63b4e2244"},"schema_version":"1.0"},"canonical_sha256":"494f2de28fffa15a5e8b868e2ea612fe1de1f5ba518e5949525fdd07a2c4d4e7","source":{"kind":"arxiv","id":"1608.02731","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.02731","created_at":"2026-05-18T01:09:33Z"},{"alias_kind":"arxiv_version","alias_value":"1608.02731v1","created_at":"2026-05-18T01:09:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.02731","created_at":"2026-05-18T01:09:33Z"},{"alias_kind":"pith_short_12","alias_value":"JFHS3YUP76QV","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_16","alias_value":"JFHS3YUP76QVUXUL","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_8","alias_value":"JFHS3YUP","created_at":"2026-05-18T12:30:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:JFHS3YUP76QVUXULQ2HC5JQS7Y","target":"record","payload":{"canonical_record":{"source":{"id":"1608.02731","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-08-09T09:01:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8eea998ac80b609921d952c5fe4115d93bba1bde423c12756adae929985dfb76","abstract_canon_sha256":"41bf29dd54d0b71e9bd1c5fbff9cbe30d61afe0673be4b2dc9fc69e63b4e2244"},"schema_version":"1.0"},"canonical_sha256":"494f2de28fffa15a5e8b868e2ea612fe1de1f5ba518e5949525fdd07a2c4d4e7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:09:33.807605Z","signature_b64":"Bru5Rooddz3K58m52VvVoLz3nbthhHlH0sF8hUlCLyTlkz+UUUX2qA6vRGUUhwQeKutzfm6J0z/aHi71PtDDDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"494f2de28fffa15a5e8b868e2ea612fe1de1f5ba518e5949525fdd07a2c4d4e7","last_reissued_at":"2026-05-18T01:09:33.807159Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:09:33.807159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1608.02731","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":"2026-05-18T01:09:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xmr5nhUvZ98OKgyNGzbzvxZRN7+YRv89kG4E8Hy5mjbZCgt0QQZV0cNZKp6T7ulEfvZ+8sSN90OXs7vdCrpMBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T06:00:46.735097Z"},"content_sha256":"8815d0df28cef4df3666796b78a091143b378521f2ee1815e922dfa9e005bd30","schema_version":"1.0","event_id":"sha256:8815d0df28cef4df3666796b78a091143b378521f2ee1815e922dfa9e005bd30"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:JFHS3YUP76QVUXULQ2HC5JQS7Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Posterior Sampling for Reinforcement Learning Without Episodes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Benjamin Van Roy, Ian Osband","submitted_at":"2016-08-09T09:01:13Z","abstract_excerpt":"This is a brief technical note to clarify some of the issues with applying the application of the algorithm posterior sampling for reinforcement learning (PSRL) in environments without fixed episodes. In particular, this paper aims to:\n  - Review some of results which have been proven for finite horizon MDPs (Osband et al 2013, 2014a, 2014b, 2016) and also for MDPs with finite ergodic structure (Gopalan et al 2014).\n  - Review similar results for optimistic algorithms in infinite horizon problems (Jaksch et al 2010, Bartlett and Tewari 2009, Abbasi-Yadkori and Szepesvari 2011), with particular"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.02731","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":"2026-05-18T01:09:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0BmAieUq+ZdSYWjeAGMnM+vkbW6uUDhTmedjIoygzh4MVxR6ikvBOTt+zP5nDDg+jT/qwY3zC+JLDf99JrfiCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T06:00:46.735754Z"},"content_sha256":"80572f04b9eb278fcfd340daef58928b76070e1370efbfbf9a9e7d23f60294b9","schema_version":"1.0","event_id":"sha256:80572f04b9eb278fcfd340daef58928b76070e1370efbfbf9a9e7d23f60294b9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JFHS3YUP76QVUXULQ2HC5JQS7Y/bundle.json","state_url":"https://pith.science/pith/JFHS3YUP76QVUXULQ2HC5JQS7Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JFHS3YUP76QVUXULQ2HC5JQS7Y/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":"2026-05-26T06:00:46Z","links":{"resolver":"https://pith.science/pith/JFHS3YUP76QVUXULQ2HC5JQS7Y","bundle":"https://pith.science/pith/JFHS3YUP76QVUXULQ2HC5JQS7Y/bundle.json","state":"https://pith.science/pith/JFHS3YUP76QVUXULQ2HC5JQS7Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JFHS3YUP76QVUXULQ2HC5JQS7Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:JFHS3YUP76QVUXULQ2HC5JQS7Y","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":"41bf29dd54d0b71e9bd1c5fbff9cbe30d61afe0673be4b2dc9fc69e63b4e2244","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-08-09T09:01:13Z","title_canon_sha256":"8eea998ac80b609921d952c5fe4115d93bba1bde423c12756adae929985dfb76"},"schema_version":"1.0","source":{"id":"1608.02731","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.02731","created_at":"2026-05-18T01:09:33Z"},{"alias_kind":"arxiv_version","alias_value":"1608.02731v1","created_at":"2026-05-18T01:09:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.02731","created_at":"2026-05-18T01:09:33Z"},{"alias_kind":"pith_short_12","alias_value":"JFHS3YUP76QV","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_16","alias_value":"JFHS3YUP76QVUXUL","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_8","alias_value":"JFHS3YUP","created_at":"2026-05-18T12:30:25Z"}],"graph_snapshots":[{"event_id":"sha256:80572f04b9eb278fcfd340daef58928b76070e1370efbfbf9a9e7d23f60294b9","target":"graph","created_at":"2026-05-18T01:09:33Z","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 is a brief technical note to clarify some of the issues with applying the application of the algorithm posterior sampling for reinforcement learning (PSRL) in environments without fixed episodes. In particular, this paper aims to:\n  - Review some of results which have been proven for finite horizon MDPs (Osband et al 2013, 2014a, 2014b, 2016) and also for MDPs with finite ergodic structure (Gopalan et al 2014).\n  - Review similar results for optimistic algorithms in infinite horizon problems (Jaksch et al 2010, Bartlett and Tewari 2009, Abbasi-Yadkori and Szepesvari 2011), with particular","authors_text":"Benjamin Van Roy, Ian Osband","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-08-09T09:01:13Z","title":"Posterior Sampling for Reinforcement Learning Without Episodes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.02731","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":"sha256:8815d0df28cef4df3666796b78a091143b378521f2ee1815e922dfa9e005bd30","target":"record","created_at":"2026-05-18T01:09:33Z","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":"41bf29dd54d0b71e9bd1c5fbff9cbe30d61afe0673be4b2dc9fc69e63b4e2244","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-08-09T09:01:13Z","title_canon_sha256":"8eea998ac80b609921d952c5fe4115d93bba1bde423c12756adae929985dfb76"},"schema_version":"1.0","source":{"id":"1608.02731","kind":"arxiv","version":1}},"canonical_sha256":"494f2de28fffa15a5e8b868e2ea612fe1de1f5ba518e5949525fdd07a2c4d4e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"494f2de28fffa15a5e8b868e2ea612fe1de1f5ba518e5949525fdd07a2c4d4e7","first_computed_at":"2026-05-18T01:09:33.807159Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:09:33.807159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Bru5Rooddz3K58m52VvVoLz3nbthhHlH0sF8hUlCLyTlkz+UUUX2qA6vRGUUhwQeKutzfm6J0z/aHi71PtDDDA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:09:33.807605Z","signed_message":"canonical_sha256_bytes"},"source_id":"1608.02731","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8815d0df28cef4df3666796b78a091143b378521f2ee1815e922dfa9e005bd30","sha256:80572f04b9eb278fcfd340daef58928b76070e1370efbfbf9a9e7d23f60294b9"],"state_sha256":"45d4196abbfd6f247e6883ce21f98a5f78a87efbb08e54dafa806ed57cda9004"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fqWS6kvLzY6r2zdSbsi5344XARIi5WVHueWyrc+yK3c1xo4PlZLgjTpnMdG9Y49tv1IwuuMvu/jBPsCU+Fz6Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T06:00:46.739296Z","bundle_sha256":"946d888d49b90617fa1294618ceee7e9b6c2922e58bbea417b6fb395789008cc"}}