{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:SRNDI2E5CLIAYMW2EYTOGRR4CY","short_pith_number":"pith:SRNDI2E5","canonical_record":{"source":{"id":"1903.07839","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-19T05:16:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"87a6d1af337e137c93cf77feba680c9932b5052df0ad6a4908f176970b81d46e","abstract_canon_sha256":"79c88fca26c40a9e9ba62dac88486cc6419d418d44120c4c92de898a89fe0879"},"schema_version":"1.0"},"canonical_sha256":"945a34689d12d00c32da2626e3463c161324c542d363f411477e2b6f07449963","source":{"kind":"arxiv","id":"1903.07839","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.07839","created_at":"2026-05-17T23:50:48Z"},{"alias_kind":"arxiv_version","alias_value":"1903.07839v2","created_at":"2026-05-17T23:50:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.07839","created_at":"2026-05-17T23:50:48Z"},{"alias_kind":"pith_short_12","alias_value":"SRNDI2E5CLIA","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SRNDI2E5CLIAYMW2","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SRNDI2E5","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:SRNDI2E5CLIAYMW2EYTOGRR4CY","target":"record","payload":{"canonical_record":{"source":{"id":"1903.07839","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-19T05:16:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"87a6d1af337e137c93cf77feba680c9932b5052df0ad6a4908f176970b81d46e","abstract_canon_sha256":"79c88fca26c40a9e9ba62dac88486cc6419d418d44120c4c92de898a89fe0879"},"schema_version":"1.0"},"canonical_sha256":"945a34689d12d00c32da2626e3463c161324c542d363f411477e2b6f07449963","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:48.428953Z","signature_b64":"axSx1YOZIpPGB3YzTe2BFuGrshFAJaUyCJSV1cPUffUzfto8g6bokCT3rfGx/ZsIuuzikJeHO/3AEReRRjyhAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"945a34689d12d00c32da2626e3463c161324c542d363f411477e2b6f07449963","last_reissued_at":"2026-05-17T23:50:48.428287Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:48.428287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.07839","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":"2026-05-17T23:50:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1UeWf+3iODSJsDfkquKVZgFjovXotMeTgyTRFcJHB8ktvfCyJN3Ckw2Eg0+7z8wQELO6G9CrHrmzongtUBM5Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T00:27:27.492286Z"},"content_sha256":"bfa3f54ee5474cc4e49d01b64e4dd9e225113e961d526a938522ef22599789c7","schema_version":"1.0","event_id":"sha256:bfa3f54ee5474cc4e49d01b64e4dd9e225113e961d526a938522ef22599789c7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:SRNDI2E5CLIAYMW2EYTOGRR4CY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Note on KL-UCB+ Policy for the Stochastic Bandit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Junya Honda","submitted_at":"2019-03-19T05:16:43Z","abstract_excerpt":"A classic setting of the stochastic K-armed bandit problem is considered in this note. In this problem it has been known that KL-UCB policy achieves the asymptotically optimal regret bound and KL-UCB+ policy empirically performs better than the KL-UCB policy although the regret bound for the original form of the KL-UCB+ policy has been unknown. This note demonstrates that a simple proof of the asymptotic optimality of the KL-UCB+ policy can be given by the same technique as those used for analyses of other known policies."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.07839","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":"2026-05-17T23:50:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5/OrSUO9YUK2XeZvp8xpL1hEHEr9VFJcxVEEbQvl41m6SNdZiG6vKsR4uEZ6FnpkkpwGzmWg/t/erpDELzC9Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T00:27:27.492741Z"},"content_sha256":"4910936839f9c48c3a1e2799505d69254561c0ca3a998842d0a5d598818f219d","schema_version":"1.0","event_id":"sha256:4910936839f9c48c3a1e2799505d69254561c0ca3a998842d0a5d598818f219d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SRNDI2E5CLIAYMW2EYTOGRR4CY/bundle.json","state_url":"https://pith.science/pith/SRNDI2E5CLIAYMW2EYTOGRR4CY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SRNDI2E5CLIAYMW2EYTOGRR4CY/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":"2026-08-19T00:27:27Z","links":{"resolver":"https://pith.science/pith/SRNDI2E5CLIAYMW2EYTOGRR4CY","bundle":"https://pith.science/pith/SRNDI2E5CLIAYMW2EYTOGRR4CY/bundle.json","state":"https://pith.science/pith/SRNDI2E5CLIAYMW2EYTOGRR4CY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SRNDI2E5CLIAYMW2EYTOGRR4CY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:SRNDI2E5CLIAYMW2EYTOGRR4CY","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":"79c88fca26c40a9e9ba62dac88486cc6419d418d44120c4c92de898a89fe0879","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-19T05:16:43Z","title_canon_sha256":"87a6d1af337e137c93cf77feba680c9932b5052df0ad6a4908f176970b81d46e"},"schema_version":"1.0","source":{"id":"1903.07839","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.07839","created_at":"2026-05-17T23:50:48Z"},{"alias_kind":"arxiv_version","alias_value":"1903.07839v2","created_at":"2026-05-17T23:50:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.07839","created_at":"2026-05-17T23:50:48Z"},{"alias_kind":"pith_short_12","alias_value":"SRNDI2E5CLIA","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SRNDI2E5CLIAYMW2","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SRNDI2E5","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:4910936839f9c48c3a1e2799505d69254561c0ca3a998842d0a5d598818f219d","target":"graph","created_at":"2026-05-17T23:50:48Z","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":"A classic setting of the stochastic K-armed bandit problem is considered in this note. In this problem it has been known that KL-UCB policy achieves the asymptotically optimal regret bound and KL-UCB+ policy empirically performs better than the KL-UCB policy although the regret bound for the original form of the KL-UCB+ policy has been unknown. This note demonstrates that a simple proof of the asymptotic optimality of the KL-UCB+ policy can be given by the same technique as those used for analyses of other known policies.","authors_text":"Junya Honda","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-19T05:16:43Z","title":"A Note on KL-UCB+ Policy for the Stochastic Bandit"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.07839","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:bfa3f54ee5474cc4e49d01b64e4dd9e225113e961d526a938522ef22599789c7","target":"record","created_at":"2026-05-17T23:50:48Z","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":"79c88fca26c40a9e9ba62dac88486cc6419d418d44120c4c92de898a89fe0879","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-19T05:16:43Z","title_canon_sha256":"87a6d1af337e137c93cf77feba680c9932b5052df0ad6a4908f176970b81d46e"},"schema_version":"1.0","source":{"id":"1903.07839","kind":"arxiv","version":2}},"canonical_sha256":"945a34689d12d00c32da2626e3463c161324c542d363f411477e2b6f07449963","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"945a34689d12d00c32da2626e3463c161324c542d363f411477e2b6f07449963","first_computed_at":"2026-05-17T23:50:48.428287Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:50:48.428287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"axSx1YOZIpPGB3YzTe2BFuGrshFAJaUyCJSV1cPUffUzfto8g6bokCT3rfGx/ZsIuuzikJeHO/3AEReRRjyhAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:50:48.428953Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.07839","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bfa3f54ee5474cc4e49d01b64e4dd9e225113e961d526a938522ef22599789c7","sha256:4910936839f9c48c3a1e2799505d69254561c0ca3a998842d0a5d598818f219d"],"state_sha256":"4a2b1b47ac3fa0c2ccb4185a4473e8554453b61b5c6dfe0dc154172120d90610"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kpNwif+qX6k4vRQqd68y7K9yoJe6E2hUXFGHk6n5bbA4NRDKjjXvSoR6CU9m52nMNy8pldujGRnSIjam+nbVBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T00:27:27.496403Z","bundle_sha256":"f80944845dfee2ff1fcfd78012d4603abc790b9399a6d2d0d9231c42baca159a"}}