{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:5KXCXOCMZA4E6NGYCYCCRFYAT7","short_pith_number":"pith:5KXCXOCM","schema_version":"1.0","canonical_sha256":"eaae2bb84cc8384f34d816042897009fd2e282c1439e0705f4bc87f5c987cbfe","source":{"kind":"arxiv","id":"2110.07923","version":2},"attestation_state":"computed","paper":{"title":"Value Penalized Q-Learning for Recommender Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo Yuan, Chengqian Gao, Ke Xu, Kuangqi Zhou, Lanqing Li, Peilin Zhao, Xueqian Wang","submitted_at":"2021-10-15T08:08:28Z","abstract_excerpt":"Scaling reinforcement learning (RL) to recommender systems (RS) is promising since maximizing the expected cumulative rewards for RL agents meets the objective of RS, i.e., improving customers' long-term satisfaction. A key approach to this goal is offline RL, which aims to learn policies from logged data. However, the high-dimensional action space and the non-stationary dynamics in commercial RS intensify distributional shift issues, making it challenging to apply offline RL methods to RS. To alleviate the action distribution shift problem in extracting RL policy from static trajectories, we "},"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":"2110.07923","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-15T08:08:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a87194b5a8a3865264c42859edc83ab18a02ddd6b063013f1fc4408ba1827214","abstract_canon_sha256":"42f9c1e8824e6ad391a30ad71b4e1890a671ea7e7d6349f33a7692fcf632ea5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:00:38.770786Z","signature_b64":"b1Dv+EHEftOxeODqrWBh0zAB8LGCwo76GU+S7uSWS3MekFCWIl9AbKySmvuLBn7YTPVQDQFC4dNXVTkqnzZUAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eaae2bb84cc8384f34d816042897009fd2e282c1439e0705f4bc87f5c987cbfe","last_reissued_at":"2026-07-05T05:00:38.770296Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:00:38.770296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Value Penalized Q-Learning for Recommender Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo Yuan, Chengqian Gao, Ke Xu, Kuangqi Zhou, Lanqing Li, Peilin Zhao, Xueqian Wang","submitted_at":"2021-10-15T08:08:28Z","abstract_excerpt":"Scaling reinforcement learning (RL) to recommender systems (RS) is promising since maximizing the expected cumulative rewards for RL agents meets the objective of RS, i.e., improving customers' long-term satisfaction. A key approach to this goal is offline RL, which aims to learn policies from logged data. However, the high-dimensional action space and the non-stationary dynamics in commercial RS intensify distributional shift issues, making it challenging to apply offline RL methods to RS. To alleviate the action distribution shift problem in extracting RL policy from static trajectories, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07923","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2110.07923/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":"2110.07923","created_at":"2026-07-05T05:00:38.770368+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.07923v2","created_at":"2026-07-05T05:00:38.770368+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07923","created_at":"2026-07-05T05:00:38.770368+00:00"},{"alias_kind":"pith_short_12","alias_value":"5KXCXOCMZA4E","created_at":"2026-07-05T05:00:38.770368+00:00"},{"alias_kind":"pith_short_16","alias_value":"5KXCXOCMZA4E6NGY","created_at":"2026-07-05T05:00:38.770368+00:00"},{"alias_kind":"pith_short_8","alias_value":"5KXCXOCM","created_at":"2026-07-05T05:00:38.770368+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/5KXCXOCMZA4E6NGYCYCCRFYAT7","json":"https://pith.science/pith/5KXCXOCMZA4E6NGYCYCCRFYAT7.json","graph_json":"https://pith.science/api/pith-number/5KXCXOCMZA4E6NGYCYCCRFYAT7/graph.json","events_json":"https://pith.science/api/pith-number/5KXCXOCMZA4E6NGYCYCCRFYAT7/events.json","paper":"https://pith.science/paper/5KXCXOCM"},"agent_actions":{"view_html":"https://pith.science/pith/5KXCXOCMZA4E6NGYCYCCRFYAT7","download_json":"https://pith.science/pith/5KXCXOCMZA4E6NGYCYCCRFYAT7.json","view_paper":"https://pith.science/paper/5KXCXOCM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.07923&json=true","fetch_graph":"https://pith.science/api/pith-number/5KXCXOCMZA4E6NGYCYCCRFYAT7/graph.json","fetch_events":"https://pith.science/api/pith-number/5KXCXOCMZA4E6NGYCYCCRFYAT7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5KXCXOCMZA4E6NGYCYCCRFYAT7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5KXCXOCMZA4E6NGYCYCCRFYAT7/action/storage_attestation","attest_author":"https://pith.science/pith/5KXCXOCMZA4E6NGYCYCCRFYAT7/action/author_attestation","sign_citation":"https://pith.science/pith/5KXCXOCMZA4E6NGYCYCCRFYAT7/action/citation_signature","submit_replication":"https://pith.science/pith/5KXCXOCMZA4E6NGYCYCCRFYAT7/action/replication_record"}},"created_at":"2026-07-05T05:00:38.770368+00:00","updated_at":"2026-07-05T05:00:38.770368+00:00"}