{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NSZDLFJMPHEW7F67XQYHUVIDH7","short_pith_number":"pith:NSZDLFJM","schema_version":"1.0","canonical_sha256":"6cb235952c79c96f97dfbc307a55033ff43c4db0027da3de69a23119f9f7aea0","source":{"kind":"arxiv","id":"2605.26554","version":1},"attestation_state":"computed","paper":{"title":"Linear and Neural Dueling Bandits with Delayed Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jie Mao, Mingze Kong, Pingchen Lu, Xiangyi Wang, Zhi Hong, Zhiyong Wang, Zhongxiang Dai","submitted_at":"2026-05-26T05:07:25Z","abstract_excerpt":"Contextual dueling bandits form a cornerstone of preference-based decision-making, with critical applications in\n  recommender systems and large language model alignment. However, standard algorithms rely on the idealized assumption\n  of immediate feedback, a condition frequently violated in real-world scenarios such as prompt optimization. This\n  setting introduces a unique theoretical challenge: unlike linear bandits, dueling bandit estimators lack closed-form\n  solutions, rendering naive adaptations of standard weighting techniques biased. To address this, we formalize the\n  problem of Cont"},"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":"2605.26554","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T05:07:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cf8ffe090250c59d8c973a3f1ef6e794f70b9486b9eb1a1ce42c0d5779354f76","abstract_canon_sha256":"cbe992b86069925f9ae01a3c3555a0d471d48438d97c3e366241c0f929be806c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:26.167568Z","signature_b64":"uRcqrHukr4rr/VpKkTuj7pUgOjbvGTLkJX8M1vlDK/3tNJKXRUAY4v22b4z2fRahydEPw+4uaWHGTq5bwrMbDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cb235952c79c96f97dfbc307a55033ff43c4db0027da3de69a23119f9f7aea0","last_reissued_at":"2026-05-27T01:05:26.167096Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:26.167096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Linear and Neural Dueling Bandits with Delayed Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jie Mao, Mingze Kong, Pingchen Lu, Xiangyi Wang, Zhi Hong, Zhiyong Wang, Zhongxiang Dai","submitted_at":"2026-05-26T05:07:25Z","abstract_excerpt":"Contextual dueling bandits form a cornerstone of preference-based decision-making, with critical applications in\n  recommender systems and large language model alignment. However, standard algorithms rely on the idealized assumption\n  of immediate feedback, a condition frequently violated in real-world scenarios such as prompt optimization. This\n  setting introduces a unique theoretical challenge: unlike linear bandits, dueling bandit estimators lack closed-form\n  solutions, rendering naive adaptations of standard weighting techniques biased. To address this, we formalize the\n  problem of Cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26554","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.26554/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":"2605.26554","created_at":"2026-05-27T01:05:26.167167+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26554v1","created_at":"2026-05-27T01:05:26.167167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26554","created_at":"2026-05-27T01:05:26.167167+00:00"},{"alias_kind":"pith_short_12","alias_value":"NSZDLFJMPHEW","created_at":"2026-05-27T01:05:26.167167+00:00"},{"alias_kind":"pith_short_16","alias_value":"NSZDLFJMPHEW7F67","created_at":"2026-05-27T01:05:26.167167+00:00"},{"alias_kind":"pith_short_8","alias_value":"NSZDLFJM","created_at":"2026-05-27T01:05:26.167167+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/NSZDLFJMPHEW7F67XQYHUVIDH7","json":"https://pith.science/pith/NSZDLFJMPHEW7F67XQYHUVIDH7.json","graph_json":"https://pith.science/api/pith-number/NSZDLFJMPHEW7F67XQYHUVIDH7/graph.json","events_json":"https://pith.science/api/pith-number/NSZDLFJMPHEW7F67XQYHUVIDH7/events.json","paper":"https://pith.science/paper/NSZDLFJM"},"agent_actions":{"view_html":"https://pith.science/pith/NSZDLFJMPHEW7F67XQYHUVIDH7","download_json":"https://pith.science/pith/NSZDLFJMPHEW7F67XQYHUVIDH7.json","view_paper":"https://pith.science/paper/NSZDLFJM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26554&json=true","fetch_graph":"https://pith.science/api/pith-number/NSZDLFJMPHEW7F67XQYHUVIDH7/graph.json","fetch_events":"https://pith.science/api/pith-number/NSZDLFJMPHEW7F67XQYHUVIDH7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NSZDLFJMPHEW7F67XQYHUVIDH7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NSZDLFJMPHEW7F67XQYHUVIDH7/action/storage_attestation","attest_author":"https://pith.science/pith/NSZDLFJMPHEW7F67XQYHUVIDH7/action/author_attestation","sign_citation":"https://pith.science/pith/NSZDLFJMPHEW7F67XQYHUVIDH7/action/citation_signature","submit_replication":"https://pith.science/pith/NSZDLFJMPHEW7F67XQYHUVIDH7/action/replication_record"}},"created_at":"2026-05-27T01:05:26.167167+00:00","updated_at":"2026-05-27T01:05:26.167167+00:00"}