{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7EQ733KVA6A7QD422ZM3CFUREB","short_pith_number":"pith:7EQ733KV","schema_version":"1.0","canonical_sha256":"f921fded550781f80f9ad659b11691205298ed3aaa2dd86dcecd78f61a208b7b","source":{"kind":"arxiv","id":"2212.02779","version":2},"attestation_state":"computed","paper":{"title":"PrefRec: Recommender Systems with Human Preferences for Reinforcing Long-term User Engagement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.IR","authors_text":"Bo An, Dong Zheng, Kun Gai, Peng Jiang, Qingpeng Cai, Shuchang Liu, Shuo Sun, Wanqi Xue, Zhenghai Xue","submitted_at":"2022-12-06T06:21:17Z","abstract_excerpt":"Current advances in recommender systems have been remarkably successful in optimizing immediate engagement. However, long-term user engagement, a more desirable performance metric, remains difficult to improve. Meanwhile, recent reinforcement learning (RL) algorithms have shown their effectiveness in a variety of long-term goal optimization tasks. For this reason, RL is widely considered as a promising framework for optimizing long-term user engagement in recommendation. Though promising, the application of RL heavily relies on well-designed rewards, but designing rewards related to long-term "},"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":"2212.02779","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-12-06T06:21:17Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5be5e7dd667066381c25426c893b15bb62fd19ac344e8f45d919125440ed7d7b","abstract_canon_sha256":"503a5fd3ebb98c6f5520681949682d9dea0b1f21eacce658759142e37e27defd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:48.322079Z","signature_b64":"guJeQ0QEcMEOpckc1iIP/EiP+qHE28xdEIPAzR/DrRXk025gn9bcjPPybTCR6+fNmzsBJNqGq7AMH3moxmKFDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f921fded550781f80f9ad659b11691205298ed3aaa2dd86dcecd78f61a208b7b","last_reissued_at":"2026-07-05T06:16:48.321486Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:48.321486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PrefRec: Recommender Systems with Human Preferences for Reinforcing Long-term User Engagement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.IR","authors_text":"Bo An, Dong Zheng, Kun Gai, Peng Jiang, Qingpeng Cai, Shuchang Liu, Shuo Sun, Wanqi Xue, Zhenghai Xue","submitted_at":"2022-12-06T06:21:17Z","abstract_excerpt":"Current advances in recommender systems have been remarkably successful in optimizing immediate engagement. However, long-term user engagement, a more desirable performance metric, remains difficult to improve. Meanwhile, recent reinforcement learning (RL) algorithms have shown their effectiveness in a variety of long-term goal optimization tasks. For this reason, RL is widely considered as a promising framework for optimizing long-term user engagement in recommendation. Though promising, the application of RL heavily relies on well-designed rewards, but designing rewards related to long-term "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.02779","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/2212.02779/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":"2212.02779","created_at":"2026-07-05T06:16:48.321560+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.02779v2","created_at":"2026-07-05T06:16:48.321560+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.02779","created_at":"2026-07-05T06:16:48.321560+00:00"},{"alias_kind":"pith_short_12","alias_value":"7EQ733KVA6A7","created_at":"2026-07-05T06:16:48.321560+00:00"},{"alias_kind":"pith_short_16","alias_value":"7EQ733KVA6A7QD42","created_at":"2026-07-05T06:16:48.321560+00:00"},{"alias_kind":"pith_short_8","alias_value":"7EQ733KV","created_at":"2026-07-05T06:16:48.321560+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22376","citing_title":"Target-Aligned Bellman Backup for Cross-domain Offline Reinforcement Learning","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7EQ733KVA6A7QD422ZM3CFUREB","json":"https://pith.science/pith/7EQ733KVA6A7QD422ZM3CFUREB.json","graph_json":"https://pith.science/api/pith-number/7EQ733KVA6A7QD422ZM3CFUREB/graph.json","events_json":"https://pith.science/api/pith-number/7EQ733KVA6A7QD422ZM3CFUREB/events.json","paper":"https://pith.science/paper/7EQ733KV"},"agent_actions":{"view_html":"https://pith.science/pith/7EQ733KVA6A7QD422ZM3CFUREB","download_json":"https://pith.science/pith/7EQ733KVA6A7QD422ZM3CFUREB.json","view_paper":"https://pith.science/paper/7EQ733KV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.02779&json=true","fetch_graph":"https://pith.science/api/pith-number/7EQ733KVA6A7QD422ZM3CFUREB/graph.json","fetch_events":"https://pith.science/api/pith-number/7EQ733KVA6A7QD422ZM3CFUREB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7EQ733KVA6A7QD422ZM3CFUREB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7EQ733KVA6A7QD422ZM3CFUREB/action/storage_attestation","attest_author":"https://pith.science/pith/7EQ733KVA6A7QD422ZM3CFUREB/action/author_attestation","sign_citation":"https://pith.science/pith/7EQ733KVA6A7QD422ZM3CFUREB/action/citation_signature","submit_replication":"https://pith.science/pith/7EQ733KVA6A7QD422ZM3CFUREB/action/replication_record"}},"created_at":"2026-07-05T06:16:48.321560+00:00","updated_at":"2026-07-05T06:16:48.321560+00:00"}