{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LYA7Q7EJ3V5OIOLR573Z35MYYU","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":"fd5f52d68e22524c4fb13126113500eb197f8be8ef406ff177cf58b0e2a189e3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-10-01T01:37:02Z","title_canon_sha256":"cefcdf4adc0a0212a481652d8235381d937681ccd66a31120738a356a3e8f1d9"},"schema_version":"1.0","source":{"id":"2310.00539","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.00539","created_at":"2026-07-05T11:51:13Z"},{"alias_kind":"arxiv_version","alias_value":"2310.00539v4","created_at":"2026-07-05T11:51:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00539","created_at":"2026-07-05T11:51:13Z"},{"alias_kind":"pith_short_12","alias_value":"LYA7Q7EJ3V5O","created_at":"2026-07-05T11:51:13Z"},{"alias_kind":"pith_short_16","alias_value":"LYA7Q7EJ3V5OIOLR","created_at":"2026-07-05T11:51:13Z"},{"alias_kind":"pith_short_8","alias_value":"LYA7Q7EJ","created_at":"2026-07-05T11:51:13Z"}],"graph_snapshots":[{"event_id":"sha256:33e5d9ef2d404d502ce40d5b05193d3e754e956da45dd87a5dfd291bd6a03b52","target":"graph","created_at":"2026-07-05T11:51:13Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.00539/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper studies the fixed-confidence best arm identification (BAI) problem in the bandit framework in the canonical single-parameter exponential models. For this problem, many policies have been proposed, but most of them require solving an optimization problem at every round and/or are forced to explore an arm at least a certain number of times except those restricted to the Gaussian model. To address these limitations, we propose a novel policy that combines Thompson sampling with a computationally efficient approach known as the best challenger rule. While Thompson sampling was originall","authors_text":"Jongyeong Lee, Junya Honda, Masashi Sugiyama","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-10-01T01:37:02Z","title":"Thompson Exploration with Best Challenger Rule in Best Arm Identification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00539","kind":"arxiv","version":4},"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":"sha256:27f3cdf115e07a92f4d1cad2fba85cc0528fbe2be173d758f3b09cffa657fd3e","target":"record","created_at":"2026-07-05T11:51:13Z","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":"fd5f52d68e22524c4fb13126113500eb197f8be8ef406ff177cf58b0e2a189e3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-10-01T01:37:02Z","title_canon_sha256":"cefcdf4adc0a0212a481652d8235381d937681ccd66a31120738a356a3e8f1d9"},"schema_version":"1.0","source":{"id":"2310.00539","kind":"arxiv","version":4}},"canonical_sha256":"5e01f87c89dd7ae43971eff79df598c509363d84bc6fd1b84099ff2169253ac3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e01f87c89dd7ae43971eff79df598c509363d84bc6fd1b84099ff2169253ac3","first_computed_at":"2026-07-05T11:51:13.647193Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:51:13.647193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vqjCNOZISScxxTFBe6rwUYGQvwQ2JbcLqb5FncZ8sjqdT8zW93uRPjiDCbU6exArjI9D9aA3Fl+aA6Hjzac3Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:51:13.647703Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.00539","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27f3cdf115e07a92f4d1cad2fba85cc0528fbe2be173d758f3b09cffa657fd3e","sha256:33e5d9ef2d404d502ce40d5b05193d3e754e956da45dd87a5dfd291bd6a03b52"],"state_sha256":"53e507e1989733906634609f3c33fe6fa8d91240be3ca40d204b0a2c619500f1"}