{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZDYSF36I3NNVK2KMF3ZHSH7RQM","short_pith_number":"pith:ZDYSF36I","schema_version":"1.0","canonical_sha256":"c8f122efc8db5b55694c2ef2791ff1832d8f1f6fd8b5f7ccf224aa806b8f83b0","source":{"kind":"arxiv","id":"2305.17428","version":2},"attestation_state":"computed","paper":{"title":"Choosing the Right Weights: Balancing Value, Strategy, and Noise in Recommender Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Emma Pierson, Nikhil Garg, Smitha Milli","submitted_at":"2023-05-27T09:37:58Z","abstract_excerpt":"Many recommender systems optimize a linear weighting of different user behaviors, such as clicks, likes, and shares. We analyze the optimal choice of weights from the perspectives of both users and content producers who strategically respond to the weights. We consider three aspects of each potential behavior: value-faithfulness (how well a behavior indicates whether the user values the content), strategy-robustness (how hard it is for producers to manipulate the behavior), and noisiness (how much estimation error there is in predicting the behavior). Our theoretical results show that for user"},"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":"2305.17428","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-27T09:37:58Z","cross_cats_sorted":[],"title_canon_sha256":"1bec949747ffa4aab188592f0ab041dfc4f401f3ffb954b6cedbf56d25a683b8","abstract_canon_sha256":"b8a23ec542edf7ab57861016c4639e35dd63a22d79759736a2c4b7c95f928a47"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:38.677254Z","signature_b64":"FXJmsBz+5eXvkBg2UpFpbZclx9DskXPPgaYXuRl3uSvUMqwX5DTBUOVtTh5eyuyBOyiO1avwdL5MV3SYwtasBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8f122efc8db5b55694c2ef2791ff1832d8f1f6fd8b5f7ccf224aa806b8f83b0","last_reissued_at":"2026-07-05T09:45:38.676812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:38.676812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Choosing the Right Weights: Balancing Value, Strategy, and Noise in Recommender Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Emma Pierson, Nikhil Garg, Smitha Milli","submitted_at":"2023-05-27T09:37:58Z","abstract_excerpt":"Many recommender systems optimize a linear weighting of different user behaviors, such as clicks, likes, and shares. We analyze the optimal choice of weights from the perspectives of both users and content producers who strategically respond to the weights. We consider three aspects of each potential behavior: value-faithfulness (how well a behavior indicates whether the user values the content), strategy-robustness (how hard it is for producers to manipulate the behavior), and noisiness (how much estimation error there is in predicting the behavior). Our theoretical results show that for user"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17428","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/2305.17428/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":"2305.17428","created_at":"2026-07-05T09:45:38.676870+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.17428v2","created_at":"2026-07-05T09:45:38.676870+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17428","created_at":"2026-07-05T09:45:38.676870+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZDYSF36I3NNV","created_at":"2026-07-05T09:45:38.676870+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZDYSF36I3NNVK2KM","created_at":"2026-07-05T09:45:38.676870+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZDYSF36I","created_at":"2026-07-05T09:45:38.676870+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16344","citing_title":"A Production-Ready RL Framework for Personalized Utility Tuning with Pareto Sweeping in Pinterest Recommender Systems","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZDYSF36I3NNVK2KMF3ZHSH7RQM","json":"https://pith.science/pith/ZDYSF36I3NNVK2KMF3ZHSH7RQM.json","graph_json":"https://pith.science/api/pith-number/ZDYSF36I3NNVK2KMF3ZHSH7RQM/graph.json","events_json":"https://pith.science/api/pith-number/ZDYSF36I3NNVK2KMF3ZHSH7RQM/events.json","paper":"https://pith.science/paper/ZDYSF36I"},"agent_actions":{"view_html":"https://pith.science/pith/ZDYSF36I3NNVK2KMF3ZHSH7RQM","download_json":"https://pith.science/pith/ZDYSF36I3NNVK2KMF3ZHSH7RQM.json","view_paper":"https://pith.science/paper/ZDYSF36I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.17428&json=true","fetch_graph":"https://pith.science/api/pith-number/ZDYSF36I3NNVK2KMF3ZHSH7RQM/graph.json","fetch_events":"https://pith.science/api/pith-number/ZDYSF36I3NNVK2KMF3ZHSH7RQM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZDYSF36I3NNVK2KMF3ZHSH7RQM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZDYSF36I3NNVK2KMF3ZHSH7RQM/action/storage_attestation","attest_author":"https://pith.science/pith/ZDYSF36I3NNVK2KMF3ZHSH7RQM/action/author_attestation","sign_citation":"https://pith.science/pith/ZDYSF36I3NNVK2KMF3ZHSH7RQM/action/citation_signature","submit_replication":"https://pith.science/pith/ZDYSF36I3NNVK2KMF3ZHSH7RQM/action/replication_record"}},"created_at":"2026-07-05T09:45:38.676870+00:00","updated_at":"2026-07-05T09:45:38.676870+00:00"}