{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:D4CDDBJBTGZ4RK3DV5YLEET6TK","short_pith_number":"pith:D4CDDBJB","canonical_record":{"source":{"id":"1502.06362","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-02-23T09:47:54Z","cross_cats_sorted":[],"title_canon_sha256":"49360cce6c9b6fe02cf7015c4d278515c139b85ac4953074b9eeeb3f1eddd46c","abstract_canon_sha256":"2ef24eeb1f14fc3103b6e0dbf9c928ceedaf047e4e6c3e80597620dfe32b7b30"},"schema_version":"1.0"},"canonical_sha256":"1f0431852199b3c8ab63af70b2127e9aa9906f1d989cdcfcdb9a7c394cebfad3","source":{"kind":"arxiv","id":"1502.06362","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:D4CDDBJBTGZ4RK3DV5YLEET6TK","target":"record","payload":{"canonical_record":{"source":{"id":"1502.06362","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-02-23T09:47:54Z","cross_cats_sorted":[],"title_canon_sha256":"49360cce6c9b6fe02cf7015c4d278515c139b85ac4953074b9eeeb3f1eddd46c","abstract_canon_sha256":"2ef24eeb1f14fc3103b6e0dbf9c928ceedaf047e4e6c3e80597620dfe32b7b30"},"schema_version":"1.0"},"canonical_sha256":"1f0431852199b3c8ab63af70b2127e9aa9906f1d989cdcfcdb9a7c394cebfad3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:49:55.685093Z","signature_b64":"TTyHB518NUceM+9SOlAh9cQt1qsOsr1TxM1T9LUURHCqCEoDptrkbXuprKshdTSnovPXNXLryuc0khpeofqBBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f0431852199b3c8ab63af70b2127e9aa9906f1d989cdcfcdb9a7c394cebfad3","last_reissued_at":"2026-05-18T01:49:55.684398Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:49:55.684398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1502.06362","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":"2026-05-18T01:49:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5iVkTsD49LF4UVXjd8wOsXkfo3pE2g9F4uOwQISN9spKp+erWF92OwFII1H/li/lyhfcU3MZtXVMOijVTjDDDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T08:02:46.829107Z"},"content_sha256":"afe407fc4bb320f560b57fc05c540ce296d8dfb81ecd6311aa8ebc9ce755ba81","schema_version":"1.0","event_id":"sha256:afe407fc4bb320f560b57fc05c540ce296d8dfb81ecd6311aa8ebc9ce755ba81"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:D4CDDBJBTGZ4RK3DV5YLEET6TK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Contextual Dueling Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aleksandrs Slivkins, Katja Hofmann, Masrour Zoghi, Miroslav Dud\\'ik, Robert E. Schapire","submitted_at":"2015-02-23T09:47:54Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.06362","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":"2026-05-18T01:49:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u1Dh/k4s2cbraepa1sYTu6QNNFZQTMaQ9NCsMPQw9j2+H2qtRKq4Ffo3gGKEgA33V4mFFuGi2M/Sce9TzaxrBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T08:02:46.829875Z"},"content_sha256":"7ec99355a482310f7f008288d7caae2955d61d7dc47526b1635d9f557faa64dc","schema_version":"1.0","event_id":"sha256:7ec99355a482310f7f008288d7caae2955d61d7dc47526b1635d9f557faa64dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D4CDDBJBTGZ4RK3DV5YLEET6TK/bundle.json","state_url":"https://pith.science/pith/D4CDDBJBTGZ4RK3DV5YLEET6TK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D4CDDBJBTGZ4RK3DV5YLEET6TK/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":"2026-06-09T08:02:46Z","links":{"resolver":"https://pith.science/pith/D4CDDBJBTGZ4RK3DV5YLEET6TK","bundle":"https://pith.science/pith/D4CDDBJBTGZ4RK3DV5YLEET6TK/bundle.json","state":"https://pith.science/pith/D4CDDBJBTGZ4RK3DV5YLEET6TK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D4CDDBJBTGZ4RK3DV5YLEET6TK/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tDHMnGXRPlXqOM4k5GkMf+HRd5ywS+nAf47PCw/nsJ9rZq9ZOZUPoIw5DWgpyaIJ2nFHoP7gV0Ta8Sog8hXDBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T08:02:46.834249Z","bundle_sha256":"1dd38fc23bfe4876b77914d49ea06dcee2b0b8f362b929344977e31fe284adcd"}}