{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:FCQZZ675SU4IF2BVMIS2ILD6WR","short_pith_number":"pith:FCQZZ675","schema_version":"1.0","canonical_sha256":"28a19cfbfd953882e8356225a42c7eb465a14b0008aac2754856831c89b18bcd","source":{"kind":"arxiv","id":"1902.00715","version":2},"attestation_state":"computed","paper":{"title":"When Collaborative Filtering Meets Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Wenjie Li, Yu Lei","submitted_at":"2019-02-02T13:22:35Z","abstract_excerpt":"In this paper, we study a multi-step interactive recommendation problem, where the item recommended at current step may affect the quality of future recommendations. To address the problem, we develop a novel and effective approach, named CFRL, which seamlessly integrates the ideas of both collaborative filtering (CF) and reinforcement learning (RL). More specifically, we first model the recommender-user interactive recommendation problem as an agent-environment RL task, which is mathematically described by a Markov decision process (MDP). Further, to achieve collaborative recommendations 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":"1902.00715","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-02T13:22:35Z","cross_cats_sorted":["cs.IR","stat.ML"],"title_canon_sha256":"bf92fa1bbe32d8d6e8823a84e83db20b93f9fa9d7dd5432252df2374e7721419","abstract_canon_sha256":"1631577d85d9a54bb23c6d910f61fb1fff697a412967b1033c573e1ec0ecfe61"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:39.385341Z","signature_b64":"aGWsD8U0Fil27gEng6EZvCSNzCUQiJetzPDhh09lSoFzctsvYE8zOr/Ti22mcCwsFMVx+Kr3YVdsd1PMPMk0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28a19cfbfd953882e8356225a42c7eb465a14b0008aac2754856831c89b18bcd","last_reissued_at":"2026-05-17T23:49:39.384815Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:39.384815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Collaborative Filtering Meets Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Wenjie Li, Yu Lei","submitted_at":"2019-02-02T13:22:35Z","abstract_excerpt":"In this paper, we study a multi-step interactive recommendation problem, where the item recommended at current step may affect the quality of future recommendations. To address the problem, we develop a novel and effective approach, named CFRL, which seamlessly integrates the ideas of both collaborative filtering (CF) and reinforcement learning (RL). More specifically, we first model the recommender-user interactive recommendation problem as an agent-environment RL task, which is mathematically described by a Markov decision process (MDP). Further, to achieve collaborative recommendations for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.00715","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":"1902.00715","created_at":"2026-05-17T23:49:39.384905+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.00715v2","created_at":"2026-05-17T23:49:39.384905+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00715","created_at":"2026-05-17T23:49:39.384905+00:00"},{"alias_kind":"pith_short_12","alias_value":"FCQZZ675SU4I","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"FCQZZ675SU4IF2BV","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"FCQZZ675","created_at":"2026-05-18T12:33:15.570797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FCQZZ675SU4IF2BVMIS2ILD6WR","json":"https://pith.science/pith/FCQZZ675SU4IF2BVMIS2ILD6WR.json","graph_json":"https://pith.science/api/pith-number/FCQZZ675SU4IF2BVMIS2ILD6WR/graph.json","events_json":"https://pith.science/api/pith-number/FCQZZ675SU4IF2BVMIS2ILD6WR/events.json","paper":"https://pith.science/paper/FCQZZ675"},"agent_actions":{"view_html":"https://pith.science/pith/FCQZZ675SU4IF2BVMIS2ILD6WR","download_json":"https://pith.science/pith/FCQZZ675SU4IF2BVMIS2ILD6WR.json","view_paper":"https://pith.science/paper/FCQZZ675","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.00715&json=true","fetch_graph":"https://pith.science/api/pith-number/FCQZZ675SU4IF2BVMIS2ILD6WR/graph.json","fetch_events":"https://pith.science/api/pith-number/FCQZZ675SU4IF2BVMIS2ILD6WR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FCQZZ675SU4IF2BVMIS2ILD6WR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FCQZZ675SU4IF2BVMIS2ILD6WR/action/storage_attestation","attest_author":"https://pith.science/pith/FCQZZ675SU4IF2BVMIS2ILD6WR/action/author_attestation","sign_citation":"https://pith.science/pith/FCQZZ675SU4IF2BVMIS2ILD6WR/action/citation_signature","submit_replication":"https://pith.science/pith/FCQZZ675SU4IF2BVMIS2ILD6WR/action/replication_record"}},"created_at":"2026-05-17T23:49:39.384905+00:00","updated_at":"2026-05-17T23:49:39.384905+00:00"}