{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:N2YAJZYZLJTTASCTG7TEMKU3OT","short_pith_number":"pith:N2YAJZYZ","schema_version":"1.0","canonical_sha256":"6eb004e7195a6730485337e6462a9b74f6f338885d38f110d64299667d237f76","source":{"kind":"arxiv","id":"2303.08816","version":2},"attestation_state":"computed","paper":{"title":"Borda Regret Minimization for Generalized Linear Dueling Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Farzad Farnoud, Hao Lou, Quanquan Gu, Tao Jin, Yue Wu","submitted_at":"2023-03-15T17:59:27Z","abstract_excerpt":"Dueling bandits are widely used to model preferential feedback prevalent in many applications such as recommendation systems and ranking. In this paper, we study the Borda regret minimization problem for dueling bandits, which aims to identify the item with the highest Borda score while minimizing the cumulative regret. We propose a rich class of generalized linear dueling bandit models, which cover many existing models. We first prove a regret lower bound of order $\\Omega(d^{2/3} T^{2/3})$ for the Borda regret minimization problem, where $d$ is the dimension of contextual vectors and $T$ is t"},"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":"2303.08816","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-15T17:59:27Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"36e47a466dc67ee70e22ef63785e7c33955836fc9afdd13e1ae280f8836f7a7d","abstract_canon_sha256":"1b5d8078e326b1a2c32f95cf59b79fae9e42035873e84b8390e19eeb62920ddb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:15.319699Z","signature_b64":"fhR9LRmVuaVhlykwCr8J8QJTPIa+tp2v2u+O7iHl49OK1f88FFBQAKnQaxFYEToD6xmMl3ZOOuSlKzB/HVzOCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6eb004e7195a6730485337e6462a9b74f6f338885d38f110d64299667d237f76","last_reissued_at":"2026-07-05T06:54:15.319235Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:15.319235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Borda Regret Minimization for Generalized Linear Dueling Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Farzad Farnoud, Hao Lou, Quanquan Gu, Tao Jin, Yue Wu","submitted_at":"2023-03-15T17:59:27Z","abstract_excerpt":"Dueling bandits are widely used to model preferential feedback prevalent in many applications such as recommendation systems and ranking. In this paper, we study the Borda regret minimization problem for dueling bandits, which aims to identify the item with the highest Borda score while minimizing the cumulative regret. We propose a rich class of generalized linear dueling bandit models, which cover many existing models. We first prove a regret lower bound of order $\\Omega(d^{2/3} T^{2/3})$ for the Borda regret minimization problem, where $d$ is the dimension of contextual vectors and $T$ is t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.08816","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/2303.08816/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":"2303.08816","created_at":"2026-07-05T06:54:15.319295+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.08816v2","created_at":"2026-07-05T06:54:15.319295+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.08816","created_at":"2026-07-05T06:54:15.319295+00:00"},{"alias_kind":"pith_short_12","alias_value":"N2YAJZYZLJTT","created_at":"2026-07-05T06:54:15.319295+00:00"},{"alias_kind":"pith_short_16","alias_value":"N2YAJZYZLJTTASCT","created_at":"2026-07-05T06:54:15.319295+00:00"},{"alias_kind":"pith_short_8","alias_value":"N2YAJZYZ","created_at":"2026-07-05T06:54:15.319295+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.08759","citing_title":"Contextual bandits with entropy-based human feedback","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N2YAJZYZLJTTASCTG7TEMKU3OT","json":"https://pith.science/pith/N2YAJZYZLJTTASCTG7TEMKU3OT.json","graph_json":"https://pith.science/api/pith-number/N2YAJZYZLJTTASCTG7TEMKU3OT/graph.json","events_json":"https://pith.science/api/pith-number/N2YAJZYZLJTTASCTG7TEMKU3OT/events.json","paper":"https://pith.science/paper/N2YAJZYZ"},"agent_actions":{"view_html":"https://pith.science/pith/N2YAJZYZLJTTASCTG7TEMKU3OT","download_json":"https://pith.science/pith/N2YAJZYZLJTTASCTG7TEMKU3OT.json","view_paper":"https://pith.science/paper/N2YAJZYZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.08816&json=true","fetch_graph":"https://pith.science/api/pith-number/N2YAJZYZLJTTASCTG7TEMKU3OT/graph.json","fetch_events":"https://pith.science/api/pith-number/N2YAJZYZLJTTASCTG7TEMKU3OT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N2YAJZYZLJTTASCTG7TEMKU3OT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N2YAJZYZLJTTASCTG7TEMKU3OT/action/storage_attestation","attest_author":"https://pith.science/pith/N2YAJZYZLJTTASCTG7TEMKU3OT/action/author_attestation","sign_citation":"https://pith.science/pith/N2YAJZYZLJTTASCTG7TEMKU3OT/action/citation_signature","submit_replication":"https://pith.science/pith/N2YAJZYZLJTTASCTG7TEMKU3OT/action/replication_record"}},"created_at":"2026-07-05T06:54:15.319295+00:00","updated_at":"2026-07-05T06:54:15.319295+00:00"}