{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:3SEQHHR3L44GTPFEN7HY56WV4F","short_pith_number":"pith:3SEQHHR3","schema_version":"1.0","canonical_sha256":"dc89039e3b5f3869bca46fcf8efad5e178545c1be5a06e6d83bb776101cd8c75","source":{"kind":"arxiv","id":"1602.03146","version":2},"attestation_state":"computed","paper":{"title":"DCM Bandits: Learning to Rank with Multiple Clicks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Branislav Kveton, Csaba Szepesv\\'ari, Sumeet Katariya, Zheng Wen","submitted_at":"2016-02-09T20:03:30Z","abstract_excerpt":"A search engine recommends to the user a list of web pages. The user examines this list, from the first page to the last, and clicks on all attractive pages until the user is satisfied. This behavior of the user can be described by the dependent click model (DCM). We propose DCM bandits, an online learning variant of the DCM where the goal is to maximize the probability of recommending satisfactory items, such as web pages. The main challenge of our learning problem is that we do not observe which attractive item is satisfactory. We propose a computationally-efficient learning algorithm for so"},"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":"1602.03146","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-09T20:03:30Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ac6f54504a4e8f2cabc5f4c156be1e8e5821d68f4e4f3bb91e5f4bc81f9bd950","abstract_canon_sha256":"7dc1298e77bd567581ec37e6f4ac6eee1d426203e53d4e5b17072d84424c6388"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:13:09.432929Z","signature_b64":"ER1nqzBT59Q6iexe+a0koHW8PBkLA8EPgvj30Th85osNmitsJZdts5MYlKMsN9f1YKPBJI26QUlLvMRxxiriBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc89039e3b5f3869bca46fcf8efad5e178545c1be5a06e6d83bb776101cd8c75","last_reissued_at":"2026-05-18T01:13:09.432593Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:13:09.432593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DCM Bandits: Learning to Rank with Multiple Clicks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Branislav Kveton, Csaba Szepesv\\'ari, Sumeet Katariya, Zheng Wen","submitted_at":"2016-02-09T20:03:30Z","abstract_excerpt":"A search engine recommends to the user a list of web pages. The user examines this list, from the first page to the last, and clicks on all attractive pages until the user is satisfied. This behavior of the user can be described by the dependent click model (DCM). We propose DCM bandits, an online learning variant of the DCM where the goal is to maximize the probability of recommending satisfactory items, such as web pages. The main challenge of our learning problem is that we do not observe which attractive item is satisfactory. We propose a computationally-efficient learning algorithm for so"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.03146","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":""},"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":"1602.03146","created_at":"2026-05-18T01:13:09.432648+00:00"},{"alias_kind":"arxiv_version","alias_value":"1602.03146v2","created_at":"2026-05-18T01:13:09.432648+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.03146","created_at":"2026-05-18T01:13:09.432648+00:00"},{"alias_kind":"pith_short_12","alias_value":"3SEQHHR3L44G","created_at":"2026-05-18T12:29:58.707656+00:00"},{"alias_kind":"pith_short_16","alias_value":"3SEQHHR3L44GTPFE","created_at":"2026-05-18T12:29:58.707656+00:00"},{"alias_kind":"pith_short_8","alias_value":"3SEQHHR3","created_at":"2026-05-18T12:29:58.707656+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.07260","citing_title":"Unbiased Learning to Rank: Counterfactual and Online Approaches","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3SEQHHR3L44GTPFEN7HY56WV4F","json":"https://pith.science/pith/3SEQHHR3L44GTPFEN7HY56WV4F.json","graph_json":"https://pith.science/api/pith-number/3SEQHHR3L44GTPFEN7HY56WV4F/graph.json","events_json":"https://pith.science/api/pith-number/3SEQHHR3L44GTPFEN7HY56WV4F/events.json","paper":"https://pith.science/paper/3SEQHHR3"},"agent_actions":{"view_html":"https://pith.science/pith/3SEQHHR3L44GTPFEN7HY56WV4F","download_json":"https://pith.science/pith/3SEQHHR3L44GTPFEN7HY56WV4F.json","view_paper":"https://pith.science/paper/3SEQHHR3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1602.03146&json=true","fetch_graph":"https://pith.science/api/pith-number/3SEQHHR3L44GTPFEN7HY56WV4F/graph.json","fetch_events":"https://pith.science/api/pith-number/3SEQHHR3L44GTPFEN7HY56WV4F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3SEQHHR3L44GTPFEN7HY56WV4F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3SEQHHR3L44GTPFEN7HY56WV4F/action/storage_attestation","attest_author":"https://pith.science/pith/3SEQHHR3L44GTPFEN7HY56WV4F/action/author_attestation","sign_citation":"https://pith.science/pith/3SEQHHR3L44GTPFEN7HY56WV4F/action/citation_signature","submit_replication":"https://pith.science/pith/3SEQHHR3L44GTPFEN7HY56WV4F/action/replication_record"}},"created_at":"2026-05-18T01:13:09.432648+00:00","updated_at":"2026-05-18T01:13:09.432648+00:00"}