{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:WUHXH3QCPGQAPDTN7CSXCU3KUV","short_pith_number":"pith:WUHXH3QC","schema_version":"1.0","canonical_sha256":"b50f73ee0279a0078e6df8a571536aa55939630ef930f723d76d0bb7621be6b1","source":{"kind":"arxiv","id":"1510.08974","version":1},"attestation_state":"computed","paper":{"title":"CONQUER: Confusion Queried Online Bandit Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Barsky, Koby Crammer","submitted_at":"2015-10-30T05:46:23Z","abstract_excerpt":"We present a new recommendation setting for picking out two items from a given set to be highlighted to a user, based on contextual input. These two items are presented to a user who chooses one of them, possibly stochastically, with a bias that favours the item with the higher value. We propose a second-order algorithm framework that members of it use uses relative upper-confidence bounds to trade off exploration and exploitation, and some explore via sampling. We analyze one algorithm in this framework in an adversarial setting with only mild assumption on the data, and prove a regret bound "},"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":"1510.08974","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-10-30T05:46:23Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1378ffbbf69a0c92cd0ea014cc74ee5b142abb799a32f330d8890b8bad631e0b","abstract_canon_sha256":"6fef74378311c2d14aece50ecdb56bff52c0ba35bda8a5a259aadedfb07d3db0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:22:05.804613Z","signature_b64":"4YEOb6EBTk4GjGIEelQSCorb3GPu93biYJ4jjobwMLylul2IF9+GmCC0T2gArdW+YeH14tIOdOBDrceifkYfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b50f73ee0279a0078e6df8a571536aa55939630ef930f723d76d0bb7621be6b1","last_reissued_at":"2026-05-18T01:22:05.804150Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:22:05.804150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CONQUER: Confusion Queried Online Bandit Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Barsky, Koby Crammer","submitted_at":"2015-10-30T05:46:23Z","abstract_excerpt":"We present a new recommendation setting for picking out two items from a given set to be highlighted to a user, based on contextual input. These two items are presented to a user who chooses one of them, possibly stochastically, with a bias that favours the item with the higher value. We propose a second-order algorithm framework that members of it use uses relative upper-confidence bounds to trade off exploration and exploitation, and some explore via sampling. We analyze one algorithm in this framework in an adversarial setting with only mild assumption on the data, and prove a regret bound "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1510.08974","kind":"arxiv","version":1},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1510.08974","created_at":"2026-05-18T01:22:05.804213+00:00"},{"alias_kind":"arxiv_version","alias_value":"1510.08974v1","created_at":"2026-05-18T01:22:05.804213+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1510.08974","created_at":"2026-05-18T01:22:05.804213+00:00"},{"alias_kind":"pith_short_12","alias_value":"WUHXH3QCPGQA","created_at":"2026-05-18T12:29:47.479230+00:00"},{"alias_kind":"pith_short_16","alias_value":"WUHXH3QCPGQAPDTN","created_at":"2026-05-18T12:29:47.479230+00:00"},{"alias_kind":"pith_short_8","alias_value":"WUHXH3QC","created_at":"2026-05-18T12:29:47.479230+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WUHXH3QCPGQAPDTN7CSXCU3KUV","json":"https://pith.science/pith/WUHXH3QCPGQAPDTN7CSXCU3KUV.json","graph_json":"https://pith.science/api/pith-number/WUHXH3QCPGQAPDTN7CSXCU3KUV/graph.json","events_json":"https://pith.science/api/pith-number/WUHXH3QCPGQAPDTN7CSXCU3KUV/events.json","paper":"https://pith.science/paper/WUHXH3QC"},"agent_actions":{"view_html":"https://pith.science/pith/WUHXH3QCPGQAPDTN7CSXCU3KUV","download_json":"https://pith.science/pith/WUHXH3QCPGQAPDTN7CSXCU3KUV.json","view_paper":"https://pith.science/paper/WUHXH3QC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1510.08974&json=true","fetch_graph":"https://pith.science/api/pith-number/WUHXH3QCPGQAPDTN7CSXCU3KUV/graph.json","fetch_events":"https://pith.science/api/pith-number/WUHXH3QCPGQAPDTN7CSXCU3KUV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WUHXH3QCPGQAPDTN7CSXCU3KUV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WUHXH3QCPGQAPDTN7CSXCU3KUV/action/storage_attestation","attest_author":"https://pith.science/pith/WUHXH3QCPGQAPDTN7CSXCU3KUV/action/author_attestation","sign_citation":"https://pith.science/pith/WUHXH3QCPGQAPDTN7CSXCU3KUV/action/citation_signature","submit_replication":"https://pith.science/pith/WUHXH3QCPGQAPDTN7CSXCU3KUV/action/replication_record"}},"created_at":"2026-05-18T01:22:05.804213+00:00","updated_at":"2026-05-18T01:22:05.804213+00:00"}