{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:BSTLFRJYSVSFHGADXEIVRI56PN","short_pith_number":"pith:BSTLFRJY","schema_version":"1.0","canonical_sha256":"0ca6b2c5389564539803b91158a3be7b7a0e8fae4857109400d408535ca0978b","source":{"kind":"arxiv","id":"1801.00209","version":3},"attestation_state":"computed","paper":{"title":"Deep Reinforcement Learning for List-wise Recommendations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dawei Yin, Jiliang Tang, Liang Zhang, Long Xia, Xiangyu Zhao, Zhuoye Ding","submitted_at":"2017-12-30T23:30:36Z","abstract_excerpt":"Recommender systems play a crucial role in mitigating the problem of information overload by suggesting users' personalized items or services. The vast majority of traditional recommender systems consider the recommendation procedure as a static process and make recommendations following a fixed strategy. In this paper, we propose a novel recommender system with the capability of continuously improving its strategies during the interactions with users. We model the sequential interactions between users and a recommender system as a Markov Decision Process (MDP) and leverage Reinforcement Learn"},"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":"1801.00209","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-30T23:30:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"94e96c6b8263023065437dfcbdc8f0d23d87d09b5075f37634c368bbb0de4fcf","abstract_canon_sha256":"6fc3f4b96b6a3fc1fbc2aace4d02febc85b909047b2260972893c4b1d1c758e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:08.849976Z","signature_b64":"uyUV+ZTdRRiN3OTxzj7Y4M1evVN/0zdMmppo7vLN2TajkeThWDnmJej2JhTz05lGTjUUrVVB/4pBSjId5cskCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ca6b2c5389564539803b91158a3be7b7a0e8fae4857109400d408535ca0978b","last_reissued_at":"2026-05-17T23:42:08.849357Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:08.849357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning for List-wise Recommendations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dawei Yin, Jiliang Tang, Liang Zhang, Long Xia, Xiangyu Zhao, Zhuoye Ding","submitted_at":"2017-12-30T23:30:36Z","abstract_excerpt":"Recommender systems play a crucial role in mitigating the problem of information overload by suggesting users' personalized items or services. The vast majority of traditional recommender systems consider the recommendation procedure as a static process and make recommendations following a fixed strategy. In this paper, we propose a novel recommender system with the capability of continuously improving its strategies during the interactions with users. We model the sequential interactions between users and a recommender system as a Markov Decision Process (MDP) and leverage Reinforcement Learn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.00209","kind":"arxiv","version":3},"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":"1801.00209","created_at":"2026-05-17T23:42:08.849455+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.00209v3","created_at":"2026-05-17T23:42:08.849455+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.00209","created_at":"2026-05-17T23:42:08.849455+00:00"},{"alias_kind":"pith_short_12","alias_value":"BSTLFRJYSVSF","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"BSTLFRJYSVSFHGAD","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"BSTLFRJY","created_at":"2026-05-18T12:31:08.081275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1907.08686","citing_title":"Combinatorial Keyword Recommendations for Sponsored Search with Deep Reinforcement Learning","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2512.13726","citing_title":"Time-Constrained Recommendations: Reinforcement Learning Strategies for E-Commerce","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04559","citing_title":"Beyond Static Best-of-N: Bayesian List-wise Alignment for LLM-based Recommendation","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BSTLFRJYSVSFHGADXEIVRI56PN","json":"https://pith.science/pith/BSTLFRJYSVSFHGADXEIVRI56PN.json","graph_json":"https://pith.science/api/pith-number/BSTLFRJYSVSFHGADXEIVRI56PN/graph.json","events_json":"https://pith.science/api/pith-number/BSTLFRJYSVSFHGADXEIVRI56PN/events.json","paper":"https://pith.science/paper/BSTLFRJY"},"agent_actions":{"view_html":"https://pith.science/pith/BSTLFRJYSVSFHGADXEIVRI56PN","download_json":"https://pith.science/pith/BSTLFRJYSVSFHGADXEIVRI56PN.json","view_paper":"https://pith.science/paper/BSTLFRJY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.00209&json=true","fetch_graph":"https://pith.science/api/pith-number/BSTLFRJYSVSFHGADXEIVRI56PN/graph.json","fetch_events":"https://pith.science/api/pith-number/BSTLFRJYSVSFHGADXEIVRI56PN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BSTLFRJYSVSFHGADXEIVRI56PN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BSTLFRJYSVSFHGADXEIVRI56PN/action/storage_attestation","attest_author":"https://pith.science/pith/BSTLFRJYSVSFHGADXEIVRI56PN/action/author_attestation","sign_citation":"https://pith.science/pith/BSTLFRJYSVSFHGADXEIVRI56PN/action/citation_signature","submit_replication":"https://pith.science/pith/BSTLFRJYSVSFHGADXEIVRI56PN/action/replication_record"}},"created_at":"2026-05-17T23:42:08.849455+00:00","updated_at":"2026-05-17T23:42:08.849455+00:00"}