{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MYNRJCWHMBI5K3ZM34OGJU7UBZ","short_pith_number":"pith:MYNRJCWH","schema_version":"1.0","canonical_sha256":"661b148ac76051d56f2cdf1c64d3f40e508314b3bfd14e3e3ea76db767a2e6e2","source":{"kind":"arxiv","id":"2408.06512","version":1},"attestation_state":"computed","paper":{"title":"Learned Ranking Function: From Short-term Behavior Predictions to Long-term User Satisfaction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.LG","authors_text":"Daryl Chang, Jennifer She, Li Wei, Lukasz Heldt, Yi Wu, Zhe Zhao","submitted_at":"2024-08-12T22:02:39Z","abstract_excerpt":"We present the Learned Ranking Function (LRF), a system that takes short-term user-item behavior predictions as input and outputs a slate of recommendations that directly optimizes for long-term user satisfaction. Most previous work is based on optimizing the hyperparameters of a heuristic function. We propose to model the problem directly as a slate optimization problem with the objective of maximizing long-term user satisfaction. We also develop a novel constraint optimization algorithm that stabilizes objective trade-offs for multi-objective optimization. We evaluate our approach with live "},"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":"2408.06512","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-12T22:02:39Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"d48d03ab2f142e2af7feb3fb26cffea5d4645b04d3b6f18c25cc69376fda7602","abstract_canon_sha256":"21bf715433c707f279f9ab70b5830d7aa40040f77762143736d408974c6526dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:58.093495Z","signature_b64":"JHBicXSTZAX0JyNURLTmx4jt7IaDK0o+ZYz/Lw+nXB6dsW3tM2q89lY/13xlqf23vNf8Dhc2gDeTq83Z5gQrBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"661b148ac76051d56f2cdf1c64d3f40e508314b3bfd14e3e3ea76db767a2e6e2","last_reissued_at":"2026-07-05T08:54:58.093077Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:58.093077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learned Ranking Function: From Short-term Behavior Predictions to Long-term User Satisfaction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.LG","authors_text":"Daryl Chang, Jennifer She, Li Wei, Lukasz Heldt, Yi Wu, Zhe Zhao","submitted_at":"2024-08-12T22:02:39Z","abstract_excerpt":"We present the Learned Ranking Function (LRF), a system that takes short-term user-item behavior predictions as input and outputs a slate of recommendations that directly optimizes for long-term user satisfaction. Most previous work is based on optimizing the hyperparameters of a heuristic function. We propose to model the problem directly as a slate optimization problem with the objective of maximizing long-term user satisfaction. We also develop a novel constraint optimization algorithm that stabilizes objective trade-offs for multi-objective optimization. We evaluate our approach with live "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06512","kind":"arxiv","version":1},"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/2408.06512/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":"2408.06512","created_at":"2026-07-05T08:54:58.093133+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.06512v1","created_at":"2026-07-05T08:54:58.093133+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06512","created_at":"2026-07-05T08:54:58.093133+00:00"},{"alias_kind":"pith_short_12","alias_value":"MYNRJCWHMBI5","created_at":"2026-07-05T08:54:58.093133+00:00"},{"alias_kind":"pith_short_16","alias_value":"MYNRJCWHMBI5K3ZM","created_at":"2026-07-05T08:54:58.093133+00:00"},{"alias_kind":"pith_short_8","alias_value":"MYNRJCWH","created_at":"2026-07-05T08:54:58.093133+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.03661","citing_title":"ACT: Automated Constraint Targeting for Multi-Objective Recommender Systems","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MYNRJCWHMBI5K3ZM34OGJU7UBZ","json":"https://pith.science/pith/MYNRJCWHMBI5K3ZM34OGJU7UBZ.json","graph_json":"https://pith.science/api/pith-number/MYNRJCWHMBI5K3ZM34OGJU7UBZ/graph.json","events_json":"https://pith.science/api/pith-number/MYNRJCWHMBI5K3ZM34OGJU7UBZ/events.json","paper":"https://pith.science/paper/MYNRJCWH"},"agent_actions":{"view_html":"https://pith.science/pith/MYNRJCWHMBI5K3ZM34OGJU7UBZ","download_json":"https://pith.science/pith/MYNRJCWHMBI5K3ZM34OGJU7UBZ.json","view_paper":"https://pith.science/paper/MYNRJCWH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.06512&json=true","fetch_graph":"https://pith.science/api/pith-number/MYNRJCWHMBI5K3ZM34OGJU7UBZ/graph.json","fetch_events":"https://pith.science/api/pith-number/MYNRJCWHMBI5K3ZM34OGJU7UBZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MYNRJCWHMBI5K3ZM34OGJU7UBZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MYNRJCWHMBI5K3ZM34OGJU7UBZ/action/storage_attestation","attest_author":"https://pith.science/pith/MYNRJCWHMBI5K3ZM34OGJU7UBZ/action/author_attestation","sign_citation":"https://pith.science/pith/MYNRJCWHMBI5K3ZM34OGJU7UBZ/action/citation_signature","submit_replication":"https://pith.science/pith/MYNRJCWHMBI5K3ZM34OGJU7UBZ/action/replication_record"}},"created_at":"2026-07-05T08:54:58.093133+00:00","updated_at":"2026-07-05T08:54:58.093133+00:00"}