{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VCTVDCR2HMRWWDBTHO75Y6VSPX","short_pith_number":"pith:VCTVDCR2","schema_version":"1.0","canonical_sha256":"a8a7518a3a3b236b0c333bbfdc7ab27de75961e349e392a56526059ada3b8af2","source":{"kind":"arxiv","id":"2407.18488","version":1},"attestation_state":"computed","paper":{"title":"Conversational Dueling Bandits in Generalized Linear Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hong Zhang, Huazheng Wang, Hui Yuan, Mengdi Wang, Shuhua Yang, Xiaoying Zhang","submitted_at":"2024-07-26T03:43:10Z","abstract_excerpt":"Conversational recommendation systems elicit user preferences by interacting with users to obtain their feedback on recommended commodities. Such systems utilize a multi-armed bandit framework to learn user preferences in an online manner and have received great success in recent years. However, existing conversational bandit methods have several limitations. First, they only enable users to provide explicit binary feedback on the recommended items or categories, leading to ambiguity in interpretation. In practice, users are usually faced with more than one choice. Relative feedback, known for"},"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":"2407.18488","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-26T03:43:10Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"687bf86025f5e239ceeed111f21d7311e3678bdd5fc65b70c85b6459757a9ebe","abstract_canon_sha256":"1dfef7db5e77032315d4f9b2795dd66d16990bb509019b82e500c4c19b6cc928"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:50.391582Z","signature_b64":"dbuMy6N7TXaLCAYoEVVx7vB+6A8zG1royWvxVfrH99FxlFGLCFaNxTeoZVU8wa2y2+wzfyntTHM5WpvLkmrhBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8a7518a3a3b236b0c333bbfdc7ab27de75961e349e392a56526059ada3b8af2","last_reissued_at":"2026-07-05T08:48:50.391129Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:50.391129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conversational Dueling Bandits in Generalized Linear Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hong Zhang, Huazheng Wang, Hui Yuan, Mengdi Wang, Shuhua Yang, Xiaoying Zhang","submitted_at":"2024-07-26T03:43:10Z","abstract_excerpt":"Conversational recommendation systems elicit user preferences by interacting with users to obtain their feedback on recommended commodities. Such systems utilize a multi-armed bandit framework to learn user preferences in an online manner and have received great success in recent years. However, existing conversational bandit methods have several limitations. First, they only enable users to provide explicit binary feedback on the recommended items or categories, leading to ambiguity in interpretation. In practice, users are usually faced with more than one choice. Relative feedback, known for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18488","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/2407.18488/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":"2407.18488","created_at":"2026-07-05T08:48:50.391193+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.18488v1","created_at":"2026-07-05T08:48:50.391193+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18488","created_at":"2026-07-05T08:48:50.391193+00:00"},{"alias_kind":"pith_short_12","alias_value":"VCTVDCR2HMRW","created_at":"2026-07-05T08:48:50.391193+00:00"},{"alias_kind":"pith_short_16","alias_value":"VCTVDCR2HMRWWDBT","created_at":"2026-07-05T08:48:50.391193+00:00"},{"alias_kind":"pith_short_8","alias_value":"VCTVDCR2","created_at":"2026-07-05T08:48:50.391193+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.21393","citing_title":"Leveraging the Power of Conversations: Optimal Key Term Selection in Conversational Contextual Bandits","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VCTVDCR2HMRWWDBTHO75Y6VSPX","json":"https://pith.science/pith/VCTVDCR2HMRWWDBTHO75Y6VSPX.json","graph_json":"https://pith.science/api/pith-number/VCTVDCR2HMRWWDBTHO75Y6VSPX/graph.json","events_json":"https://pith.science/api/pith-number/VCTVDCR2HMRWWDBTHO75Y6VSPX/events.json","paper":"https://pith.science/paper/VCTVDCR2"},"agent_actions":{"view_html":"https://pith.science/pith/VCTVDCR2HMRWWDBTHO75Y6VSPX","download_json":"https://pith.science/pith/VCTVDCR2HMRWWDBTHO75Y6VSPX.json","view_paper":"https://pith.science/paper/VCTVDCR2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.18488&json=true","fetch_graph":"https://pith.science/api/pith-number/VCTVDCR2HMRWWDBTHO75Y6VSPX/graph.json","fetch_events":"https://pith.science/api/pith-number/VCTVDCR2HMRWWDBTHO75Y6VSPX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VCTVDCR2HMRWWDBTHO75Y6VSPX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VCTVDCR2HMRWWDBTHO75Y6VSPX/action/storage_attestation","attest_author":"https://pith.science/pith/VCTVDCR2HMRWWDBTHO75Y6VSPX/action/author_attestation","sign_citation":"https://pith.science/pith/VCTVDCR2HMRWWDBTHO75Y6VSPX/action/citation_signature","submit_replication":"https://pith.science/pith/VCTVDCR2HMRWWDBTHO75Y6VSPX/action/replication_record"}},"created_at":"2026-07-05T08:48:50.391193+00:00","updated_at":"2026-07-05T08:48:50.391193+00:00"}