{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PTWHMVSEWAOH7GMLCYJYF3X7Q4","short_pith_number":"pith:PTWHMVSE","schema_version":"1.0","canonical_sha256":"7cec765644b01c7f998b161382eeff870704dadd34f7e28d1470db938f921690","source":{"kind":"arxiv","id":"2404.06013","version":1},"attestation_state":"computed","paper":{"title":"Feel-Good Thompson Sampling for Contextual Dueling Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Heyang Zhao, Quanquan Gu, Xuheng Li","submitted_at":"2024-04-09T04:45:18Z","abstract_excerpt":"Contextual dueling bandits, where a learner compares two options based on context and receives feedback indicating which was preferred, extends classic dueling bandits by incorporating contextual information for decision-making and preference learning. Several algorithms based on the upper confidence bound (UCB) have been proposed for linear contextual dueling bandits. However, no algorithm based on posterior sampling has been developed in this setting, despite the empirical success observed in traditional contextual bandits. In this paper, we propose a Thompson sampling algorithm, named FGTS."},"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":"2404.06013","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-09T04:45:18Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"26897e4890f7ce14254614ff2c260c7a9365da47a1a9fc61be7627ab8520d156","abstract_canon_sha256":"aaac0e59ba7191a88bbeeb7b1580a97b136b644d100dd349d100e16a15ceb3c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:02.348582Z","signature_b64":"801Le6SEp1dDpU72zMcyego1eSDdunEzgTgUBvwMs6OKWkWdWWe0HWreHiBExV30wtVPBkJYyH7FNECO05y4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cec765644b01c7f998b161382eeff870704dadd34f7e28d1470db938f921690","last_reissued_at":"2026-07-05T08:06:02.348109Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:02.348109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feel-Good Thompson Sampling for Contextual Dueling Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Heyang Zhao, Quanquan Gu, Xuheng Li","submitted_at":"2024-04-09T04:45:18Z","abstract_excerpt":"Contextual dueling bandits, where a learner compares two options based on context and receives feedback indicating which was preferred, extends classic dueling bandits by incorporating contextual information for decision-making and preference learning. Several algorithms based on the upper confidence bound (UCB) have been proposed for linear contextual dueling bandits. However, no algorithm based on posterior sampling has been developed in this setting, despite the empirical success observed in traditional contextual bandits. In this paper, we propose a Thompson sampling algorithm, named FGTS."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06013","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/2404.06013/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":"2404.06013","created_at":"2026-07-05T08:06:02.348164+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.06013v1","created_at":"2026-07-05T08:06:02.348164+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06013","created_at":"2026-07-05T08:06:02.348164+00:00"},{"alias_kind":"pith_short_12","alias_value":"PTWHMVSEWAOH","created_at":"2026-07-05T08:06:02.348164+00:00"},{"alias_kind":"pith_short_16","alias_value":"PTWHMVSEWAOH7GML","created_at":"2026-07-05T08:06:02.348164+00:00"},{"alias_kind":"pith_short_8","alias_value":"PTWHMVSE","created_at":"2026-07-05T08:06:02.348164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26554","citing_title":"Linear and Neural Dueling Bandits with Delayed Feedback","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2505.19241","citing_title":"ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01752","citing_title":"Robust Linear Dueling Bandits with Post-serving Context under Unknown Delays and Adversarial Corruptions","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2506.01250","citing_title":"Neural Variance-aware Dueling Bandits with Deep Representation and Shallow Exploration","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01752","citing_title":"Robust Linear Dueling Bandits with Post-serving Context under Unknown Delays and Adversarial Corruptions","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PTWHMVSEWAOH7GMLCYJYF3X7Q4","json":"https://pith.science/pith/PTWHMVSEWAOH7GMLCYJYF3X7Q4.json","graph_json":"https://pith.science/api/pith-number/PTWHMVSEWAOH7GMLCYJYF3X7Q4/graph.json","events_json":"https://pith.science/api/pith-number/PTWHMVSEWAOH7GMLCYJYF3X7Q4/events.json","paper":"https://pith.science/paper/PTWHMVSE"},"agent_actions":{"view_html":"https://pith.science/pith/PTWHMVSEWAOH7GMLCYJYF3X7Q4","download_json":"https://pith.science/pith/PTWHMVSEWAOH7GMLCYJYF3X7Q4.json","view_paper":"https://pith.science/paper/PTWHMVSE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.06013&json=true","fetch_graph":"https://pith.science/api/pith-number/PTWHMVSEWAOH7GMLCYJYF3X7Q4/graph.json","fetch_events":"https://pith.science/api/pith-number/PTWHMVSEWAOH7GMLCYJYF3X7Q4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PTWHMVSEWAOH7GMLCYJYF3X7Q4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PTWHMVSEWAOH7GMLCYJYF3X7Q4/action/storage_attestation","attest_author":"https://pith.science/pith/PTWHMVSEWAOH7GMLCYJYF3X7Q4/action/author_attestation","sign_citation":"https://pith.science/pith/PTWHMVSEWAOH7GMLCYJYF3X7Q4/action/citation_signature","submit_replication":"https://pith.science/pith/PTWHMVSEWAOH7GMLCYJYF3X7Q4/action/replication_record"}},"created_at":"2026-07-05T08:06:02.348164+00:00","updated_at":"2026-07-05T08:06:02.348164+00:00"}