{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:IAJLR7JEFYG36EVR5CK6B33WRD","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":"469fc41c1b8b3294b36332a83b3e11a7f0e3151544ed85d3848bccc883c8419b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2012-05-18T19:00:51Z","title_canon_sha256":"4315d78b7d418f278920b818db7beb94f88394b3d951b09fb62f2943f2a8f1a2"},"schema_version":"1.0","source":{"id":"1205.4217","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1205.4217","created_at":"2026-05-18T03:50:37Z"},{"alias_kind":"arxiv_version","alias_value":"1205.4217v2","created_at":"2026-05-18T03:50:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1205.4217","created_at":"2026-05-18T03:50:37Z"},{"alias_kind":"pith_short_12","alias_value":"IAJLR7JEFYG3","created_at":"2026-05-18T12:27:09Z"},{"alias_kind":"pith_short_16","alias_value":"IAJLR7JEFYG36EVR","created_at":"2026-05-18T12:27:09Z"},{"alias_kind":"pith_short_8","alias_value":"IAJLR7JE","created_at":"2026-05-18T12:27:09Z"}],"graph_snapshots":[{"event_id":"sha256:33ed06a8932e49a902cbed141fdae2f8ddea1c3541ef689ac8c3fe62a4418d3a","target":"graph","created_at":"2026-05-18T03:50:37Z","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":"The question of the optimality of Thompson Sampling for solving the stochastic multi-armed bandit problem had been open since 1933. In this paper we answer it positively for the case of Bernoulli rewards by providing the first finite-time analysis that matches the asymptotic rate given in the Lai and Robbins lower bound for the cumulative regret. The proof is accompanied by a numerical comparison with other optimal policies, experiments that have been lacking in the literature until now for the Bernoulli case.","authors_text":"Emilie Kaufmann, Nathaniel Korda, R\\'emi Munos","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2012-05-18T19:00:51Z","title":"Thompson Sampling: An Asymptotically Optimal Finite Time Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1205.4217","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:f8549a2e7ccb1cb249058ee0e1ef67ca3465f8371f8046005336a1fb2d1193f4","target":"record","created_at":"2026-05-18T03:50:37Z","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":"469fc41c1b8b3294b36332a83b3e11a7f0e3151544ed85d3848bccc883c8419b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2012-05-18T19:00:51Z","title_canon_sha256":"4315d78b7d418f278920b818db7beb94f88394b3d951b09fb62f2943f2a8f1a2"},"schema_version":"1.0","source":{"id":"1205.4217","kind":"arxiv","version":2}},"canonical_sha256":"4012b8fd242e0dbf12b1e895e0ef7688cd1501b39bc9e4fe22ce54a2746da821","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4012b8fd242e0dbf12b1e895e0ef7688cd1501b39bc9e4fe22ce54a2746da821","first_computed_at":"2026-05-18T03:50:37.094375Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:50:37.094375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Sz8G22Y6AOvpsXjWrWaE+TMIPrcUQgsuD34DpzeZv+EoRNV+rtYjTVkC6hSXXvOqmxQ+siUsey6A5P0zp6jyDg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:50:37.095022Z","signed_message":"canonical_sha256_bytes"},"source_id":"1205.4217","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8549a2e7ccb1cb249058ee0e1ef67ca3465f8371f8046005336a1fb2d1193f4","sha256:33ed06a8932e49a902cbed141fdae2f8ddea1c3541ef689ac8c3fe62a4418d3a"],"state_sha256":"ba2b37bdbcea677b47c84023acd3176f9c7f23aa1498109fdec29e1ce9140969"}