{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:SFZIALG52DJDDVPO5I3IAI2VHR","short_pith_number":"pith:SFZIALG5","schema_version":"1.0","canonical_sha256":"9172802cddd0d231d5eeea368023553c43b76c513dc29aa2ed8ea9b18b627606","source":{"kind":"arxiv","id":"1807.11398","version":2},"attestation_state":"computed","paper":{"title":"Preference-based Online Learning with Dueling Bandits: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adil El Mesaoudi-Paul, Eyke H\\\"ullermeier, Robert Busa-Fekete, Viktor Bengs","submitted_at":"2018-07-30T15:40:54Z","abstract_excerpt":"In machine learning, the notion of multi-armed bandits refers to a class of online learning problems, in which an agent is supposed to simultaneously explore and exploit a given set of choice alternatives in the course of a sequential decision process. In the standard setting, the agent learns from stochastic feedback in the form of real-valued rewards. In many applications, however, numerical reward signals are not readily available -- instead, only weaker information is provided, in particular relative preferences in the form of qualitative comparisons between pairs of alternatives. This obs"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1807.11398","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-30T15:40:54Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c7ac0dccd1fcc737c6564d1473f26eda7321bdbae78cb1ae5cea17b51277a209","abstract_canon_sha256":"cf3af9ad5efb7f2f1a99b424fafc31f09ae1bc8186d33f938b1a0ab325117dba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:56:52.091904Z","signature_b64":"9EXs0I+aOYsSksoFqcULCLdqwq/5P+H4sbBXGzwuqr9wD6ZePfFGcFSxRAQAcF1B4N+4QcMC5rGCVpxVZsbEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9172802cddd0d231d5eeea368023553c43b76c513dc29aa2ed8ea9b18b627606","last_reissued_at":"2026-07-05T02:56:52.091463Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:56:52.091463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Preference-based Online Learning with Dueling Bandits: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adil El Mesaoudi-Paul, Eyke H\\\"ullermeier, Robert Busa-Fekete, Viktor Bengs","submitted_at":"2018-07-30T15:40:54Z","abstract_excerpt":"In machine learning, the notion of multi-armed bandits refers to a class of online learning problems, in which an agent is supposed to simultaneously explore and exploit a given set of choice alternatives in the course of a sequential decision process. In the standard setting, the agent learns from stochastic feedback in the form of real-valued rewards. In many applications, however, numerical reward signals are not readily available -- instead, only weaker information is provided, in particular relative preferences in the form of qualitative comparisons between pairs of alternatives. This obs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.11398","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1807.11398/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1807.11398","created_at":"2026-07-05T02:56:52.091528+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.11398v2","created_at":"2026-07-05T02:56:52.091528+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.11398","created_at":"2026-07-05T02:56:52.091528+00:00"},{"alias_kind":"pith_short_12","alias_value":"SFZIALG52DJD","created_at":"2026-07-05T02:56:52.091528+00:00"},{"alias_kind":"pith_short_16","alias_value":"SFZIALG52DJDDVPO","created_at":"2026-07-05T02:56:52.091528+00:00"},{"alias_kind":"pith_short_8","alias_value":"SFZIALG5","created_at":"2026-07-05T02:56:52.091528+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29998","citing_title":"Optimal Posterior E-values with Non-Convex Parameter Sets with Applications to Voting Systems","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SFZIALG52DJDDVPO5I3IAI2VHR","json":"https://pith.science/pith/SFZIALG52DJDDVPO5I3IAI2VHR.json","graph_json":"https://pith.science/api/pith-number/SFZIALG52DJDDVPO5I3IAI2VHR/graph.json","events_json":"https://pith.science/api/pith-number/SFZIALG52DJDDVPO5I3IAI2VHR/events.json","paper":"https://pith.science/paper/SFZIALG5"},"agent_actions":{"view_html":"https://pith.science/pith/SFZIALG52DJDDVPO5I3IAI2VHR","download_json":"https://pith.science/pith/SFZIALG52DJDDVPO5I3IAI2VHR.json","view_paper":"https://pith.science/paper/SFZIALG5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.11398&json=true","fetch_graph":"https://pith.science/api/pith-number/SFZIALG52DJDDVPO5I3IAI2VHR/graph.json","fetch_events":"https://pith.science/api/pith-number/SFZIALG52DJDDVPO5I3IAI2VHR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SFZIALG52DJDDVPO5I3IAI2VHR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SFZIALG52DJDDVPO5I3IAI2VHR/action/storage_attestation","attest_author":"https://pith.science/pith/SFZIALG52DJDDVPO5I3IAI2VHR/action/author_attestation","sign_citation":"https://pith.science/pith/SFZIALG52DJDDVPO5I3IAI2VHR/action/citation_signature","submit_replication":"https://pith.science/pith/SFZIALG52DJDDVPO5I3IAI2VHR/action/replication_record"}},"created_at":"2026-07-05T02:56:52.091528+00:00","updated_at":"2026-07-05T02:56:52.091528+00:00"}