{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:Z47DP2QXTJ6ORY3Y35CYKSHXWL","short_pith_number":"pith:Z47DP2QX","canonical_record":{"source":{"id":"1506.02550","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-06-08T15:28:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3105f14bf4493ab418e259a9c2b086e0735f26da85e2a1cdafdad4a5f6fa7ce2","abstract_canon_sha256":"19212a29f58af2e7a54e4fb2dd80a48b3cc606a2cea585033c688c6ef9f2ab86"},"schema_version":"1.0"},"canonical_sha256":"cf3e37ea179a7ce8e378df458548f7b2f7ca5113fc7b1e49703aa9421063eedb","source":{"kind":"arxiv","id":"1506.02550","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.02550","created_at":"2026-05-18T01:37:44Z"},{"alias_kind":"arxiv_version","alias_value":"1506.02550v3","created_at":"2026-05-18T01:37:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.02550","created_at":"2026-05-18T01:37:44Z"},{"alias_kind":"pith_short_12","alias_value":"Z47DP2QXTJ6O","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_16","alias_value":"Z47DP2QXTJ6ORY3Y","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_8","alias_value":"Z47DP2QX","created_at":"2026-05-18T12:29:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:Z47DP2QXTJ6ORY3Y35CYKSHXWL","target":"record","payload":{"canonical_record":{"source":{"id":"1506.02550","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-06-08T15:28:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3105f14bf4493ab418e259a9c2b086e0735f26da85e2a1cdafdad4a5f6fa7ce2","abstract_canon_sha256":"19212a29f58af2e7a54e4fb2dd80a48b3cc606a2cea585033c688c6ef9f2ab86"},"schema_version":"1.0"},"canonical_sha256":"cf3e37ea179a7ce8e378df458548f7b2f7ca5113fc7b1e49703aa9421063eedb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:37:44.198592Z","signature_b64":"iLHPbF8UfJO6lGXAudef0e7X0p+K58WZxxxjO0h43F+Hi9YdXVfC1vI55ZD5cbE3QUX+wg8p7jBwpMhQn1dlCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf3e37ea179a7ce8e378df458548f7b2f7ca5113fc7b1e49703aa9421063eedb","last_reissued_at":"2026-05-18T01:37:44.197966Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:37:44.197966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1506.02550","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:37:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pjfyeQGK6kNV1DptoOl3za7XMPcAi9R/Oj2rOkdZ6zGKJ8F9BcCCFPg7e/6PMzR173pcpZUYU8KzMLIF8Ax6DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T15:30:01.420604Z"},"content_sha256":"0c1013c67f430e9c288901e55af0cc31bcd3f02ce990b35e607ce4f90970b889","schema_version":"1.0","event_id":"sha256:0c1013c67f430e9c288901e55af0cc31bcd3f02ce990b35e607ce4f90970b889"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:Z47DP2QXTJ6ORY3Y35CYKSHXWL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Regret Lower Bound and Optimal Algorithm in Dueling Bandit Problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Hiroshi Nakagawa, Hisashi Kashima, Junpei Komiyama, Junya Honda","submitted_at":"2015-06-08T15:28:39Z","abstract_excerpt":"We study the $K$-armed dueling bandit problem, a variation of the standard stochastic bandit problem where the feedback is limited to relative comparisons of a pair of arms. We introduce a tight asymptotic regret lower bound that is based on the information divergence. An algorithm that is inspired by the Deterministic Minimum Empirical Divergence algorithm (Honda and Takemura, 2010) is proposed, and its regret is analyzed. The proposed algorithm is found to be the first one with a regret upper bound that matches the lower bound. Experimental comparisons of dueling bandit algorithms show that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.02550","kind":"arxiv","version":3},"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":"2026-05-18T01:37:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p9GaPLXKvYV09HR+BSnZixCIEgNzhbtWJVM7a3DBH7jLvP7zdDX8KDg4ojVyb6gfDZVZyrGjIY+vGew/HwBTCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T15:30:01.421260Z"},"content_sha256":"3f56480ff1cbaf0095b08408a760933ad8560654beabcded3ac73d4b6c25dc59","schema_version":"1.0","event_id":"sha256:3f56480ff1cbaf0095b08408a760933ad8560654beabcded3ac73d4b6c25dc59"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z47DP2QXTJ6ORY3Y35CYKSHXWL/bundle.json","state_url":"https://pith.science/pith/Z47DP2QXTJ6ORY3Y35CYKSHXWL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z47DP2QXTJ6ORY3Y35CYKSHXWL/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":"2026-06-07T15:30:01Z","links":{"resolver":"https://pith.science/pith/Z47DP2QXTJ6ORY3Y35CYKSHXWL","bundle":"https://pith.science/pith/Z47DP2QXTJ6ORY3Y35CYKSHXWL/bundle.json","state":"https://pith.science/pith/Z47DP2QXTJ6ORY3Y35CYKSHXWL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z47DP2QXTJ6ORY3Y35CYKSHXWL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:Z47DP2QXTJ6ORY3Y35CYKSHXWL","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":"19212a29f58af2e7a54e4fb2dd80a48b3cc606a2cea585033c688c6ef9f2ab86","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-06-08T15:28:39Z","title_canon_sha256":"3105f14bf4493ab418e259a9c2b086e0735f26da85e2a1cdafdad4a5f6fa7ce2"},"schema_version":"1.0","source":{"id":"1506.02550","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.02550","created_at":"2026-05-18T01:37:44Z"},{"alias_kind":"arxiv_version","alias_value":"1506.02550v3","created_at":"2026-05-18T01:37:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.02550","created_at":"2026-05-18T01:37:44Z"},{"alias_kind":"pith_short_12","alias_value":"Z47DP2QXTJ6O","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_16","alias_value":"Z47DP2QXTJ6ORY3Y","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_8","alias_value":"Z47DP2QX","created_at":"2026-05-18T12:29:52Z"}],"graph_snapshots":[{"event_id":"sha256:3f56480ff1cbaf0095b08408a760933ad8560654beabcded3ac73d4b6c25dc59","target":"graph","created_at":"2026-05-18T01:37:44Z","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 study the $K$-armed dueling bandit problem, a variation of the standard stochastic bandit problem where the feedback is limited to relative comparisons of a pair of arms. We introduce a tight asymptotic regret lower bound that is based on the information divergence. An algorithm that is inspired by the Deterministic Minimum Empirical Divergence algorithm (Honda and Takemura, 2010) is proposed, and its regret is analyzed. The proposed algorithm is found to be the first one with a regret upper bound that matches the lower bound. Experimental comparisons of dueling bandit algorithms show that ","authors_text":"Hiroshi Nakagawa, Hisashi Kashima, Junpei Komiyama, Junya Honda","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-06-08T15:28:39Z","title":"Regret Lower Bound and Optimal Algorithm in Dueling Bandit Problem"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.02550","kind":"arxiv","version":3},"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":"sha256:0c1013c67f430e9c288901e55af0cc31bcd3f02ce990b35e607ce4f90970b889","target":"record","created_at":"2026-05-18T01:37:44Z","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":"19212a29f58af2e7a54e4fb2dd80a48b3cc606a2cea585033c688c6ef9f2ab86","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-06-08T15:28:39Z","title_canon_sha256":"3105f14bf4493ab418e259a9c2b086e0735f26da85e2a1cdafdad4a5f6fa7ce2"},"schema_version":"1.0","source":{"id":"1506.02550","kind":"arxiv","version":3}},"canonical_sha256":"cf3e37ea179a7ce8e378df458548f7b2f7ca5113fc7b1e49703aa9421063eedb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf3e37ea179a7ce8e378df458548f7b2f7ca5113fc7b1e49703aa9421063eedb","first_computed_at":"2026-05-18T01:37:44.197966Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:37:44.197966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iLHPbF8UfJO6lGXAudef0e7X0p+K58WZxxxjO0h43F+Hi9YdXVfC1vI55ZD5cbE3QUX+wg8p7jBwpMhQn1dlCA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:37:44.198592Z","signed_message":"canonical_sha256_bytes"},"source_id":"1506.02550","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c1013c67f430e9c288901e55af0cc31bcd3f02ce990b35e607ce4f90970b889","sha256:3f56480ff1cbaf0095b08408a760933ad8560654beabcded3ac73d4b6c25dc59"],"state_sha256":"ceece86d38def8074978617dab251afb54cbfa3d47bce067153f9749eba6bd8d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4QSXysLvmH2S+sG6wHWQJtujKRU0j+kX/DymZmkeHQEz9TsfRbVdbIGTNAZRom4kErUtTHVWzEAGoLACmyTcAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T15:30:01.425200Z","bundle_sha256":"a70883783ce313636a1f4a6b096572f0710ac10051a69f56d15dbbbdced14c7b"}}