{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:HT2HZ5BXFIMH7P3YG65RUAFPEW","short_pith_number":"pith:HT2HZ5BX","schema_version":"1.0","canonical_sha256":"3cf47cf4372a187fbf7837bb1a00af2589ab06a4148d292dbad8df57ad44e977","source":{"kind":"arxiv","id":"1705.00253","version":1},"attestation_state":"computed","paper":{"title":"Multi-dueling Bandits with Dependent Arms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Joel W. Burdick, Vincent Zhuang, Yanan Sui, Yisong Yue","submitted_at":"2017-04-29T23:47:52Z","abstract_excerpt":"The dueling bandits problem is an online learning framework for learning from pairwise preference feedback, and is particularly well-suited for modeling settings that elicit subjective or implicit human feedback. In this paper, we study the problem of multi-dueling bandits with dependent arms, which extends the original dueling bandits setting by simultaneously dueling multiple arms as well as modeling dependencies between arms. These extensions capture key characteristics found in many real-world applications, and allow for the opportunity to develop significantly more efficient algorithms th"},"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":"1705.00253","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-29T23:47:52Z","cross_cats_sorted":[],"title_canon_sha256":"79872f5ea799cd6b1e6670845976f66f80b7e6c2323fb3849679aea945852216","abstract_canon_sha256":"21e2bb3b44c5e45323dbdd0f0a39f3561a51e40f1570cfb01d8246aa566a78e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:21.026361Z","signature_b64":"bMkWijLjJovHB9EbHHCLiHBcwKGCGZeh6wKr+RfTPWSl2u3SVwbUQ271qQYxnAUmmuLxrEmjPpHYXmapFZzBCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3cf47cf4372a187fbf7837bb1a00af2589ab06a4148d292dbad8df57ad44e977","last_reissued_at":"2026-05-18T00:45:21.025661Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:21.025661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-dueling Bandits with Dependent Arms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Joel W. Burdick, Vincent Zhuang, Yanan Sui, Yisong Yue","submitted_at":"2017-04-29T23:47:52Z","abstract_excerpt":"The dueling bandits problem is an online learning framework for learning from pairwise preference feedback, and is particularly well-suited for modeling settings that elicit subjective or implicit human feedback. In this paper, we study the problem of multi-dueling bandits with dependent arms, which extends the original dueling bandits setting by simultaneously dueling multiple arms as well as modeling dependencies between arms. These extensions capture key characteristics found in many real-world applications, and allow for the opportunity to develop significantly more efficient algorithms th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.00253","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":"1705.00253","created_at":"2026-05-18T00:45:21.025768+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.00253v1","created_at":"2026-05-18T00:45:21.025768+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.00253","created_at":"2026-05-18T00:45:21.025768+00:00"},{"alias_kind":"pith_short_12","alias_value":"HT2HZ5BXFIMH","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"HT2HZ5BXFIMH7P3Y","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"HT2HZ5BX","created_at":"2026-05-18T12:31:18.294218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2510.17671","citing_title":"LILO: Bayesian Optimization with Natural Language Feedback","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HT2HZ5BXFIMH7P3YG65RUAFPEW","json":"https://pith.science/pith/HT2HZ5BXFIMH7P3YG65RUAFPEW.json","graph_json":"https://pith.science/api/pith-number/HT2HZ5BXFIMH7P3YG65RUAFPEW/graph.json","events_json":"https://pith.science/api/pith-number/HT2HZ5BXFIMH7P3YG65RUAFPEW/events.json","paper":"https://pith.science/paper/HT2HZ5BX"},"agent_actions":{"view_html":"https://pith.science/pith/HT2HZ5BXFIMH7P3YG65RUAFPEW","download_json":"https://pith.science/pith/HT2HZ5BXFIMH7P3YG65RUAFPEW.json","view_paper":"https://pith.science/paper/HT2HZ5BX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.00253&json=true","fetch_graph":"https://pith.science/api/pith-number/HT2HZ5BXFIMH7P3YG65RUAFPEW/graph.json","fetch_events":"https://pith.science/api/pith-number/HT2HZ5BXFIMH7P3YG65RUAFPEW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HT2HZ5BXFIMH7P3YG65RUAFPEW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HT2HZ5BXFIMH7P3YG65RUAFPEW/action/storage_attestation","attest_author":"https://pith.science/pith/HT2HZ5BXFIMH7P3YG65RUAFPEW/action/author_attestation","sign_citation":"https://pith.science/pith/HT2HZ5BXFIMH7P3YG65RUAFPEW/action/citation_signature","submit_replication":"https://pith.science/pith/HT2HZ5BXFIMH7P3YG65RUAFPEW/action/replication_record"}},"created_at":"2026-05-18T00:45:21.025768+00:00","updated_at":"2026-05-18T00:45:21.025768+00:00"}