{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HHCGSQ27PKF4HUPWTQ6JBGJ6TZ","short_pith_number":"pith:HHCGSQ27","schema_version":"1.0","canonical_sha256":"39c469435f7a8bc3d1f69c3c90993e9e54fa25e67a2a7a8d28bd33ebbdcb670e","source":{"kind":"arxiv","id":"2104.02981","version":2},"attestation_state":"computed","paper":{"title":"Reinforcement Learning with a Disentangled Universal Value Function for Item Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Changjie Fan, Jianrong Tao, Kai Wang, Liang Chen, Peng Cui, Qilin Deng, Runze Wu, Zhene Zou","submitted_at":"2021-04-07T08:13:32Z","abstract_excerpt":"In recent years, there are great interests as well as challenges in applying reinforcement learning (RL) to recommendation systems (RS). In this paper, we summarize three key practical challenges of large-scale RL-based recommender systems: massive state and action spaces, high-variance environment, and the unspecific reward setting in recommendation. All these problems remain largely unexplored in the existing literature and make the application of RL challenging. We develop a model-based reinforcement learning framework, called GoalRec. Inspired by the ideas of world model (model-based), val"},"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":"2104.02981","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-04-07T08:13:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e8b5d1bcfc4303f96982ba3b0f3ab171c62f1c7e01f778bc1bcdb3588a7f6721","abstract_canon_sha256":"dcebfa25ba1cb69b5e2d19a2442469f01a4ff949a7c2ed46f9df73430315889d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:31:05.612647Z","signature_b64":"Bka7rAZbMDEXbzJNLR8jVpyKfvwdq+xxGGvHxntvNRdn8O/jTZNkgma7cA19zN+ZVXDn8fZGj3wKRZeuuyl+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39c469435f7a8bc3d1f69c3c90993e9e54fa25e67a2a7a8d28bd33ebbdcb670e","last_reissued_at":"2026-07-05T02:31:05.612087Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:31:05.612087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning with a Disentangled Universal Value Function for Item Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Changjie Fan, Jianrong Tao, Kai Wang, Liang Chen, Peng Cui, Qilin Deng, Runze Wu, Zhene Zou","submitted_at":"2021-04-07T08:13:32Z","abstract_excerpt":"In recent years, there are great interests as well as challenges in applying reinforcement learning (RL) to recommendation systems (RS). In this paper, we summarize three key practical challenges of large-scale RL-based recommender systems: massive state and action spaces, high-variance environment, and the unspecific reward setting in recommendation. All these problems remain largely unexplored in the existing literature and make the application of RL challenging. We develop a model-based reinforcement learning framework, called GoalRec. Inspired by the ideas of world model (model-based), val"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.02981","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/2104.02981/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":"2104.02981","created_at":"2026-07-05T02:31:05.612147+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.02981v2","created_at":"2026-07-05T02:31:05.612147+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.02981","created_at":"2026-07-05T02:31:05.612147+00:00"},{"alias_kind":"pith_short_12","alias_value":"HHCGSQ27PKF4","created_at":"2026-07-05T02:31:05.612147+00:00"},{"alias_kind":"pith_short_16","alias_value":"HHCGSQ27PKF4HUPW","created_at":"2026-07-05T02:31:05.612147+00:00"},{"alias_kind":"pith_short_8","alias_value":"HHCGSQ27","created_at":"2026-07-05T02:31:05.612147+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/HHCGSQ27PKF4HUPWTQ6JBGJ6TZ","json":"https://pith.science/pith/HHCGSQ27PKF4HUPWTQ6JBGJ6TZ.json","graph_json":"https://pith.science/api/pith-number/HHCGSQ27PKF4HUPWTQ6JBGJ6TZ/graph.json","events_json":"https://pith.science/api/pith-number/HHCGSQ27PKF4HUPWTQ6JBGJ6TZ/events.json","paper":"https://pith.science/paper/HHCGSQ27"},"agent_actions":{"view_html":"https://pith.science/pith/HHCGSQ27PKF4HUPWTQ6JBGJ6TZ","download_json":"https://pith.science/pith/HHCGSQ27PKF4HUPWTQ6JBGJ6TZ.json","view_paper":"https://pith.science/paper/HHCGSQ27","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.02981&json=true","fetch_graph":"https://pith.science/api/pith-number/HHCGSQ27PKF4HUPWTQ6JBGJ6TZ/graph.json","fetch_events":"https://pith.science/api/pith-number/HHCGSQ27PKF4HUPWTQ6JBGJ6TZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HHCGSQ27PKF4HUPWTQ6JBGJ6TZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HHCGSQ27PKF4HUPWTQ6JBGJ6TZ/action/storage_attestation","attest_author":"https://pith.science/pith/HHCGSQ27PKF4HUPWTQ6JBGJ6TZ/action/author_attestation","sign_citation":"https://pith.science/pith/HHCGSQ27PKF4HUPWTQ6JBGJ6TZ/action/citation_signature","submit_replication":"https://pith.science/pith/HHCGSQ27PKF4HUPWTQ6JBGJ6TZ/action/replication_record"}},"created_at":"2026-07-05T02:31:05.612147+00:00","updated_at":"2026-07-05T02:31:05.612147+00:00"}