{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PTWHMVSEWAOH7GMLCYJYF3X7Q4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"aaac0e59ba7191a88bbeeb7b1580a97b136b644d100dd349d100e16a15ceb3c8","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-09T04:45:18Z","title_canon_sha256":"26897e4890f7ce14254614ff2c260c7a9365da47a1a9fc61be7627ab8520d156"},"schema_version":"1.0","source":{"id":"2404.06013","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.06013","created_at":"2026-07-05T08:06:02Z"},{"alias_kind":"arxiv_version","alias_value":"2404.06013v1","created_at":"2026-07-05T08:06:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06013","created_at":"2026-07-05T08:06:02Z"},{"alias_kind":"pith_short_12","alias_value":"PTWHMVSEWAOH","created_at":"2026-07-05T08:06:02Z"},{"alias_kind":"pith_short_16","alias_value":"PTWHMVSEWAOH7GML","created_at":"2026-07-05T08:06:02Z"},{"alias_kind":"pith_short_8","alias_value":"PTWHMVSE","created_at":"2026-07-05T08:06:02Z"}],"graph_snapshots":[{"event_id":"sha256:dd3c0a673abe129d9c9e80aad42a9995e2d1d756cf5b907b5155f8be832897b7","target":"graph","created_at":"2026-07-05T08:06:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.06013/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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.","authors_text":"Heyang Zhao, Quanquan Gu, Xuheng Li","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-09T04:45:18Z","title":"Feel-Good Thompson Sampling for Contextual Dueling Bandits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06013","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f6562f8b876b0bec0148e802d167c938747a5c1d36a2294697d863be2fe2635c","target":"record","created_at":"2026-07-05T08:06:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"aaac0e59ba7191a88bbeeb7b1580a97b136b644d100dd349d100e16a15ceb3c8","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-09T04:45:18Z","title_canon_sha256":"26897e4890f7ce14254614ff2c260c7a9365da47a1a9fc61be7627ab8520d156"},"schema_version":"1.0","source":{"id":"2404.06013","kind":"arxiv","version":1}},"canonical_sha256":"7cec765644b01c7f998b161382eeff870704dadd34f7e28d1470db938f921690","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7cec765644b01c7f998b161382eeff870704dadd34f7e28d1470db938f921690","first_computed_at":"2026-07-05T08:06:02.348109Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:06:02.348109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"801Le6SEp1dDpU72zMcyego1eSDdunEzgTgUBvwMs6OKWkWdWWe0HWreHiBExV30wtVPBkJYyH7FNECO05y4CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:06:02.348582Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.06013","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6562f8b876b0bec0148e802d167c938747a5c1d36a2294697d863be2fe2635c","sha256:dd3c0a673abe129d9c9e80aad42a9995e2d1d756cf5b907b5155f8be832897b7"],"state_sha256":"806b5fe531e16637fd22054a65f813fe5e5df75823ffb8cad5a13e46ad1496e7"}