{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:D4CDDBJBTGZ4RK3DV5YLEET6TK","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":"2ef24eeb1f14fc3103b6e0dbf9c928ceedaf047e4e6c3e80597620dfe32b7b30","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-02-23T09:47:54Z","title_canon_sha256":"49360cce6c9b6fe02cf7015c4d278515c139b85ac4953074b9eeeb3f1eddd46c"},"schema_version":"1.0","source":{"id":"1502.06362","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1502.06362","created_at":"2026-05-18T01:49:55Z"},{"alias_kind":"arxiv_version","alias_value":"1502.06362v2","created_at":"2026-05-18T01:49:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.06362","created_at":"2026-05-18T01:49:55Z"},{"alias_kind":"pith_short_12","alias_value":"D4CDDBJBTGZ4","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_16","alias_value":"D4CDDBJBTGZ4RK3D","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_8","alias_value":"D4CDDBJB","created_at":"2026-05-18T12:29:17Z"}],"graph_snapshots":[{"event_id":"sha256:7ec99355a482310f7f008288d7caae2955d61d7dc47526b1635d9f557faa64dc","target":"graph","created_at":"2026-05-18T01:49:55Z","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 consider the problem of learning to choose actions using contextual information when provided with limited feedback in the form of relative pairwise comparisons. We study this problem in the dueling-bandits framework of Yue et al. (2009), which we extend to incorporate context. Roughly, the learner's goal is to find the best policy, or way of behaving, in some space of policies, although \"best\" is not always so clearly defined. Here, we propose a new and natural solution concept, rooted in game theory, called a von Neumann winner, a randomized policy that beats or ties every other policy. W","authors_text":"Aleksandrs Slivkins, Katja Hofmann, Masrour Zoghi, Miroslav Dud\\'ik, Robert E. Schapire","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-02-23T09:47:54Z","title":"Contextual Dueling Bandits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.06362","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:afe407fc4bb320f560b57fc05c540ce296d8dfb81ecd6311aa8ebc9ce755ba81","target":"record","created_at":"2026-05-18T01:49:55Z","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":"2ef24eeb1f14fc3103b6e0dbf9c928ceedaf047e4e6c3e80597620dfe32b7b30","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-02-23T09:47:54Z","title_canon_sha256":"49360cce6c9b6fe02cf7015c4d278515c139b85ac4953074b9eeeb3f1eddd46c"},"schema_version":"1.0","source":{"id":"1502.06362","kind":"arxiv","version":2}},"canonical_sha256":"1f0431852199b3c8ab63af70b2127e9aa9906f1d989cdcfcdb9a7c394cebfad3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f0431852199b3c8ab63af70b2127e9aa9906f1d989cdcfcdb9a7c394cebfad3","first_computed_at":"2026-05-18T01:49:55.684398Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:49:55.684398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TTyHB518NUceM+9SOlAh9cQt1qsOsr1TxM1T9LUURHCqCEoDptrkbXuprKshdTSnovPXNXLryuc0khpeofqBBg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:49:55.685093Z","signed_message":"canonical_sha256_bytes"},"source_id":"1502.06362","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:afe407fc4bb320f560b57fc05c540ce296d8dfb81ecd6311aa8ebc9ce755ba81","sha256:7ec99355a482310f7f008288d7caae2955d61d7dc47526b1635d9f557faa64dc"],"state_sha256":"97e9dddf0696bdab9b4c8d6158c0fa62aef5316d84a4268899794551456d5d88"}