{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:3RFEKAYMCEAYONSXRYX6AZDHKW","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":"d8bba6b221f27b7928fd79b531000d80b829629408834382666c62dd82b082a0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-18T14:35:10Z","title_canon_sha256":"0b7d719fc5b6e6ee770760042833fb6509a01a26fde0dee36f828a1770e280af"},"schema_version":"1.0","source":{"id":"1906.07611","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.07611","created_at":"2026-05-17T23:42:59Z"},{"alias_kind":"arxiv_version","alias_value":"1906.07611v1","created_at":"2026-05-17T23:42:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.07611","created_at":"2026-05-17T23:42:59Z"},{"alias_kind":"pith_short_12","alias_value":"3RFEKAYMCEAY","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"3RFEKAYMCEAYONSX","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"3RFEKAYM","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:62562a9415559efb9df833a11d3d214abe88310b61866e14728d16e9420e3013","target":"graph","created_at":"2026-05-17T23:42:59Z","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":"In this paper, we present simple algorithms for Dueling Bandits. We prove that the algorithms have regret bounds for time horizon T of order O(T^rho ) with 1/2 <= rho <= 3/4, which importantly do not depend on any preference gap between actions, Delta. Dueling Bandits is an important extension of the Multi-Armed Bandit problem, in which the algorithm must select two actions at a time and only receives binary feedback for the duel outcome. This is analogous to comparisons in which the rater can only provide yes/no or better/worse type responses. We compare our simple algorithms to the current s","authors_text":"Andrew Lamperski, Tyler Lekang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-18T14:35:10Z","title":"Simple Algorithms for Dueling Bandits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.07611","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:fa291ccff06cd5ad1707c745cc01e25de4be401cd07243b1fefd53dfce601652","target":"record","created_at":"2026-05-17T23:42:59Z","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":"d8bba6b221f27b7928fd79b531000d80b829629408834382666c62dd82b082a0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-18T14:35:10Z","title_canon_sha256":"0b7d719fc5b6e6ee770760042833fb6509a01a26fde0dee36f828a1770e280af"},"schema_version":"1.0","source":{"id":"1906.07611","kind":"arxiv","version":1}},"canonical_sha256":"dc4a45030c11018736578e2fe0646755ba1ebae5b28c919db65fa7208d0e28b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc4a45030c11018736578e2fe0646755ba1ebae5b28c919db65fa7208d0e28b6","first_computed_at":"2026-05-17T23:42:59.723557Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:59.723557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vRiLBRU2/93BBiCURO/OLr/GxgKGCPFoA049P19Ob/07x0kINyVTypF5slqrd6bL2pB3QMSthMWAinzxc49HBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:59.724051Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.07611","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa291ccff06cd5ad1707c745cc01e25de4be401cd07243b1fefd53dfce601652","sha256:62562a9415559efb9df833a11d3d214abe88310b61866e14728d16e9420e3013"],"state_sha256":"3bd48a5df3a58305e5922f019afb88a54cd26279793f133a978e5001915cebab"}