{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:P7RIVRJ344FX4TWB7JX6E2YWI6","short_pith_number":"pith:P7RIVRJ3","canonical_record":{"source":{"id":"1602.07905","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-25T12:37:21Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"89a5d1e6e955cf81127b5c038ece984ac099ecdd90608049d995f6d611b7cd59","abstract_canon_sha256":"808585175f3d05ba09e571f90712d077359af4306dca5e9f3a7e016ac858577f"},"schema_version":"1.0"},"canonical_sha256":"7fe28ac53be70b7e4ec1fa6fe26b164792df8c4e3b8b07610d6c2d8368140a32","source":{"kind":"arxiv","id":"1602.07905","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.07905","created_at":"2026-05-18T01:12:59Z"},{"alias_kind":"arxiv_version","alias_value":"1602.07905v2","created_at":"2026-05-18T01:12:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.07905","created_at":"2026-05-18T01:12:59Z"},{"alias_kind":"pith_short_12","alias_value":"P7RIVRJ344FX","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_16","alias_value":"P7RIVRJ344FX4TWB","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_8","alias_value":"P7RIVRJ3","created_at":"2026-05-18T12:30:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:P7RIVRJ344FX4TWB7JX6E2YWI6","target":"record","payload":{"canonical_record":{"source":{"id":"1602.07905","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-25T12:37:21Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"89a5d1e6e955cf81127b5c038ece984ac099ecdd90608049d995f6d611b7cd59","abstract_canon_sha256":"808585175f3d05ba09e571f90712d077359af4306dca5e9f3a7e016ac858577f"},"schema_version":"1.0"},"canonical_sha256":"7fe28ac53be70b7e4ec1fa6fe26b164792df8c4e3b8b07610d6c2d8368140a32","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:59.592115Z","signature_b64":"yOfehVThQKRBzL9lpQoSrYABjxt+mMXYA2L7iPAm8sxb6c0d2I7qgvC+oS7Rfz2m4ZCbEipccEWeFa3lJlq9Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fe28ac53be70b7e4ec1fa6fe26b164792df8c4e3b8b07610d6c2d8368140a32","last_reissued_at":"2026-05-18T01:12:59.591664Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:59.591664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1602.07905","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":"2026-05-18T01:12:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YjWE2P7j+y7spxsip/FeuTj84KoO+/+BjKxI4hryIFCXJBNRthf4FNo7NMPyexgQFpzDy8jtVQB0gtkHXXPJAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T20:09:32.059566Z"},"content_sha256":"7e6965f028af6aad505507cc0b8c8e3a73f8d368c13b6037f6129a14b26ba9ec","schema_version":"1.0","event_id":"sha256:7e6965f028af6aad505507cc0b8c8e3a73f8d368c13b6037f6129a14b26ba9ec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:P7RIVRJ344FX4TWB7JX6E2YWI6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Thompson Sampling is Asymptotically Optimal in General Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jan Leike, Laurent Orseau, Marcus Hutter, Tor Lattimore","submitted_at":"2016-02-25T12:37:21Z","abstract_excerpt":"We discuss a variant of Thompson sampling for nonparametric reinforcement learning in a countable classes of general stochastic environments. These environments can be non-Markov, non-ergodic, and partially observable. We show that Thompson sampling learns the environment class in the sense that (1) asymptotically its value converges to the optimal value in mean and (2) given a recoverability assumption regret is sublinear."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.07905","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":"2026-05-18T01:12:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VAL9i3+OWFYewlZWq+riwbxGtF1XXLgGdukE6pc1fHzPz/4ktV0FruoujlEl88Gcp8gX2D1izvqVlaNGe6vQBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T20:09:32.060192Z"},"content_sha256":"9dadadf23cfdb85a017949cad7ee1285e537a6994a76f0bc90695b9852e3f3f1","schema_version":"1.0","event_id":"sha256:9dadadf23cfdb85a017949cad7ee1285e537a6994a76f0bc90695b9852e3f3f1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P7RIVRJ344FX4TWB7JX6E2YWI6/bundle.json","state_url":"https://pith.science/pith/P7RIVRJ344FX4TWB7JX6E2YWI6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P7RIVRJ344FX4TWB7JX6E2YWI6/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":"2026-06-06T20:09:32Z","links":{"resolver":"https://pith.science/pith/P7RIVRJ344FX4TWB7JX6E2YWI6","bundle":"https://pith.science/pith/P7RIVRJ344FX4TWB7JX6E2YWI6/bundle.json","state":"https://pith.science/pith/P7RIVRJ344FX4TWB7JX6E2YWI6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P7RIVRJ344FX4TWB7JX6E2YWI6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:P7RIVRJ344FX4TWB7JX6E2YWI6","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":"808585175f3d05ba09e571f90712d077359af4306dca5e9f3a7e016ac858577f","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-25T12:37:21Z","title_canon_sha256":"89a5d1e6e955cf81127b5c038ece984ac099ecdd90608049d995f6d611b7cd59"},"schema_version":"1.0","source":{"id":"1602.07905","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.07905","created_at":"2026-05-18T01:12:59Z"},{"alias_kind":"arxiv_version","alias_value":"1602.07905v2","created_at":"2026-05-18T01:12:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.07905","created_at":"2026-05-18T01:12:59Z"},{"alias_kind":"pith_short_12","alias_value":"P7RIVRJ344FX","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_16","alias_value":"P7RIVRJ344FX4TWB","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_8","alias_value":"P7RIVRJ3","created_at":"2026-05-18T12:30:39Z"}],"graph_snapshots":[{"event_id":"sha256:9dadadf23cfdb85a017949cad7ee1285e537a6994a76f0bc90695b9852e3f3f1","target":"graph","created_at":"2026-05-18T01:12:59Z","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 discuss a variant of Thompson sampling for nonparametric reinforcement learning in a countable classes of general stochastic environments. These environments can be non-Markov, non-ergodic, and partially observable. We show that Thompson sampling learns the environment class in the sense that (1) asymptotically its value converges to the optimal value in mean and (2) given a recoverability assumption regret is sublinear.","authors_text":"Jan Leike, Laurent Orseau, Marcus Hutter, Tor Lattimore","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-25T12:37:21Z","title":"Thompson Sampling is Asymptotically Optimal in General Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.07905","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":"sha256:7e6965f028af6aad505507cc0b8c8e3a73f8d368c13b6037f6129a14b26ba9ec","target":"record","created_at":"2026-05-18T01:12:59Z","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":"808585175f3d05ba09e571f90712d077359af4306dca5e9f3a7e016ac858577f","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-25T12:37:21Z","title_canon_sha256":"89a5d1e6e955cf81127b5c038ece984ac099ecdd90608049d995f6d611b7cd59"},"schema_version":"1.0","source":{"id":"1602.07905","kind":"arxiv","version":2}},"canonical_sha256":"7fe28ac53be70b7e4ec1fa6fe26b164792df8c4e3b8b07610d6c2d8368140a32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7fe28ac53be70b7e4ec1fa6fe26b164792df8c4e3b8b07610d6c2d8368140a32","first_computed_at":"2026-05-18T01:12:59.591664Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:12:59.591664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yOfehVThQKRBzL9lpQoSrYABjxt+mMXYA2L7iPAm8sxb6c0d2I7qgvC+oS7Rfz2m4ZCbEipccEWeFa3lJlq9Bw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:12:59.592115Z","signed_message":"canonical_sha256_bytes"},"source_id":"1602.07905","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e6965f028af6aad505507cc0b8c8e3a73f8d368c13b6037f6129a14b26ba9ec","sha256:9dadadf23cfdb85a017949cad7ee1285e537a6994a76f0bc90695b9852e3f3f1"],"state_sha256":"18145adfd74adc1ef6ea1b462a8a2f8c15a60b5d17bdbe557ddefd191da53393"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"plq7oXfp/WL5KFTu+ZjltuaMKvvGniq0nxTaOMLNLS/h0G+26FJPnWD66jwo40DA+mU9Gawx+ASnhOpcfD3eBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T20:09:32.063443Z","bundle_sha256":"8573268604eaa98961281a5999cc3ec78d872936746b2f76686d4eddafb43ffa"}}