{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:5JS75PXTIGPZ3ML3DDQYQU4OVJ","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":"f8edf407023eae8b2fd8a822817c7bbcb9ec55863eda7353ee36f832c120d365","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-01-15T09:50:07Z","title_canon_sha256":"6ad6e05746de64cf3589005fcead484c0f851b6ac4e0c88c261eed1f1df2b6a8"},"schema_version":"1.0","source":{"id":"1601.03855","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1601.03855","created_at":"2026-05-18T01:22:49Z"},{"alias_kind":"arxiv_version","alias_value":"1601.03855v1","created_at":"2026-05-18T01:22:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1601.03855","created_at":"2026-05-18T01:22:49Z"},{"alias_kind":"pith_short_12","alias_value":"5JS75PXTIGPZ","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_16","alias_value":"5JS75PXTIGPZ3ML3","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_8","alias_value":"5JS75PXT","created_at":"2026-05-18T12:30:01Z"}],"graph_snapshots":[{"event_id":"sha256:f5465da03390080e2d17cc9f56310daefc607c13616f12659f51c98b7ee48a08","target":"graph","created_at":"2026-05-18T01:22:49Z","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 which is a variation of the classical Multi-Armed Bandit (MAB) problem in which the learner receives only relative feedback about the selected pairs of arms. We propose a new algorithm called Relative Exponential-weight algorithm for Exploration and Exploitation (REX3) to handle the adversarial utility-based formulation of this problem. This algorithm is a non-trivial extension of the Exponential-weight algorithm for Exploration and Exploitation (EXP3) algorithm. We prove a finite time expected regret upper bound of order O(sqrt(K ln(K)T)) for this a","authors_text":"D), Fabrice Cl\\'erot (FT R, Pratik Gajane, Tanguy Urvoy","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-01-15T09:50:07Z","title":"A Relative Exponential Weighing Algorithm for Adversarial Utility-based Dueling Bandits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1601.03855","kind":"arxiv","version":1},"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":"sha256:51db772e0e53545110a3c0c86c9566e24c0b0353c67ef5466d3e8f13a85484d9","target":"record","created_at":"2026-05-18T01:22:49Z","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":"f8edf407023eae8b2fd8a822817c7bbcb9ec55863eda7353ee36f832c120d365","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-01-15T09:50:07Z","title_canon_sha256":"6ad6e05746de64cf3589005fcead484c0f851b6ac4e0c88c261eed1f1df2b6a8"},"schema_version":"1.0","source":{"id":"1601.03855","kind":"arxiv","version":1}},"canonical_sha256":"ea65febef3419f9db17b18e188538eaa7296cdd26d933441b08530b025bcb02b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea65febef3419f9db17b18e188538eaa7296cdd26d933441b08530b025bcb02b","first_computed_at":"2026-05-18T01:22:49.843344Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:22:49.843344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FOSDMfERvQ09DFKLu9dU73Ha7EcBGMIY3il96dWG27dBVJfU68nf0b9QbFZiBRYmFuIljylO8s+RYMWOBdiXAw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:22:49.843915Z","signed_message":"canonical_sha256_bytes"},"source_id":"1601.03855","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:51db772e0e53545110a3c0c86c9566e24c0b0353c67ef5466d3e8f13a85484d9","sha256:f5465da03390080e2d17cc9f56310daefc607c13616f12659f51c98b7ee48a08"],"state_sha256":"76b48280bc7dbcd7516e8379158e9c001a5a4c13b13945e26b2af0950210db63"}