{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:OC64QK3GYFQFAN6BELG3YNTWFS","short_pith_number":"pith:OC64QK3G","schema_version":"1.0","canonical_sha256":"70bdc82b66c1605037c122cdbc36762c90bef508bdb2ee9ba80521ee7ed665fd","source":{"kind":"arxiv","id":"1905.12767","version":2},"attestation_state":"computed","paper":{"title":"Reinforcement Learning for Slate-based Recommender Systems: A Tractable Decomposition and Practical Methodology","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Craig Boutilier, Eugene Ie, Heng-Tze Cheng, Jim McFadden, Jing Wang, Morgane Lustman, Paul Covington, Ritesh Agarwal, Rui Wu, Sanmit Narvekar, Tushar Chandra, Vihan Jain, Vince Gatto","submitted_at":"2019-05-29T22:55:28Z","abstract_excerpt":"Most practical recommender systems focus on estimating immediate user engagement without considering the long-term effects of recommendations on user behavior. Reinforcement learning (RL) methods offer the potential to optimize recommendations for long-term user engagement. However, since users are often presented with slates of multiple items - which may have interacting effects on user choice - methods are required to deal with the combinatorics of the RL action space. In this work, we address the challenge of making slate-based recommendations to optimize long-term value using RL. Our contr"},"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":"1905.12767","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-29T22:55:28Z","cross_cats_sorted":["cs.AI","cs.IR","stat.ML"],"title_canon_sha256":"85b52c4472ee8cdceb175af5b0095b9a7eba1c11aaabd0a29153b34582d2c6c7","abstract_canon_sha256":"abeb1d01cb9b74b89a36b6b9496ed5e4900cb27923981895f559fd22fe1d6f5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:37.336080Z","signature_b64":"n4jpPw7/s7TEu3VZaHG1OcAY0gF2eQ1KSRWvD0OmFHFIq0IyBoNReiVHHY1vR+6ebdvfPc6h3vSvbYE1RgQvBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70bdc82b66c1605037c122cdbc36762c90bef508bdb2ee9ba80521ee7ed665fd","last_reissued_at":"2026-05-17T23:44:37.335623Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:37.335623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning for Slate-based Recommender Systems: A Tractable Decomposition and Practical Methodology","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Craig Boutilier, Eugene Ie, Heng-Tze Cheng, Jim McFadden, Jing Wang, Morgane Lustman, Paul Covington, Ritesh Agarwal, Rui Wu, Sanmit Narvekar, Tushar Chandra, Vihan Jain, Vince Gatto","submitted_at":"2019-05-29T22:55:28Z","abstract_excerpt":"Most practical recommender systems focus on estimating immediate user engagement without considering the long-term effects of recommendations on user behavior. Reinforcement learning (RL) methods offer the potential to optimize recommendations for long-term user engagement. However, since users are often presented with slates of multiple items - which may have interacting effects on user choice - methods are required to deal with the combinatorics of the RL action space. In this work, we address the challenge of making slate-based recommendations to optimize long-term value using RL. Our contr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12767","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":"1905.12767","created_at":"2026-05-17T23:44:37.335690+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.12767v2","created_at":"2026-05-17T23:44:37.335690+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12767","created_at":"2026-05-17T23:44:37.335690+00:00"},{"alias_kind":"pith_short_12","alias_value":"OC64QK3GYFQF","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"OC64QK3GYFQFAN6B","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"OC64QK3G","created_at":"2026-05-18T12:33:24.271573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2512.13726","citing_title":"Time-Constrained Recommendations: Reinforcement Learning Strategies for E-Commerce","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08268","citing_title":"Insider Attacks in Multi-Agent LLM Consensus Systems","ref_index":149,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OC64QK3GYFQFAN6BELG3YNTWFS","json":"https://pith.science/pith/OC64QK3GYFQFAN6BELG3YNTWFS.json","graph_json":"https://pith.science/api/pith-number/OC64QK3GYFQFAN6BELG3YNTWFS/graph.json","events_json":"https://pith.science/api/pith-number/OC64QK3GYFQFAN6BELG3YNTWFS/events.json","paper":"https://pith.science/paper/OC64QK3G"},"agent_actions":{"view_html":"https://pith.science/pith/OC64QK3GYFQFAN6BELG3YNTWFS","download_json":"https://pith.science/pith/OC64QK3GYFQFAN6BELG3YNTWFS.json","view_paper":"https://pith.science/paper/OC64QK3G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.12767&json=true","fetch_graph":"https://pith.science/api/pith-number/OC64QK3GYFQFAN6BELG3YNTWFS/graph.json","fetch_events":"https://pith.science/api/pith-number/OC64QK3GYFQFAN6BELG3YNTWFS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OC64QK3GYFQFAN6BELG3YNTWFS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OC64QK3GYFQFAN6BELG3YNTWFS/action/storage_attestation","attest_author":"https://pith.science/pith/OC64QK3GYFQFAN6BELG3YNTWFS/action/author_attestation","sign_citation":"https://pith.science/pith/OC64QK3GYFQFAN6BELG3YNTWFS/action/citation_signature","submit_replication":"https://pith.science/pith/OC64QK3GYFQFAN6BELG3YNTWFS/action/replication_record"}},"created_at":"2026-05-17T23:44:37.335690+00:00","updated_at":"2026-05-17T23:44:37.335690+00:00"}