{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7U2RPTY76RAG4XUJTLMMRR4UPL","short_pith_number":"pith:7U2RPTY7","schema_version":"1.0","canonical_sha256":"fd3517cf1ff4406e5e899ad8c8c7947ac932e493d3e26acefc8242c30edad6c8","source":{"kind":"arxiv","id":"2505.19473","version":1},"attestation_state":"computed","paper":{"title":"Improving Recommendation Fairness without Sensitive Attributes Using Multi-Persona LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chao Wang, Haoran Xin, Hui Xiong, Weijia Zhang, Yanke Yu, Ying Sun","submitted_at":"2025-05-26T03:52:41Z","abstract_excerpt":"Despite the success of recommender systems in alleviating information overload, fairness issues have raised concerns in recent years, potentially leading to unequal treatment for certain user groups. While efforts have been made to improve recommendation fairness, they often assume that users' sensitive attributes are available during model training. However, collecting sensitive information can be difficult, especially on platforms that involve no personal information disclosure. Therefore, we aim to improve recommendation fairness without any access to sensitive attributes. However, this is "},"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":"2505.19473","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-26T03:52:41Z","cross_cats_sorted":[],"title_canon_sha256":"d246a7f97eca32e62c4cd26804ee826e61bc342a045085b976bbb1a86d0c873e","abstract_canon_sha256":"4ab1437f07eca46f2833516df73577963e94fdbc74c518aa41d8e97288d34349"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:30.831720Z","signature_b64":"8OsdonYo4BroCJMREgrBfYtf71i0WYv+w+/1O55DtydrgNLn3Q03AFv0d09MO9PBqtExfweC4DB+zihBhMTmCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd3517cf1ff4406e5e899ad8c8c7947ac932e493d3e26acefc8242c30edad6c8","last_reissued_at":"2026-07-05T11:09:30.831228Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:30.831228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Recommendation Fairness without Sensitive Attributes Using Multi-Persona LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chao Wang, Haoran Xin, Hui Xiong, Weijia Zhang, Yanke Yu, Ying Sun","submitted_at":"2025-05-26T03:52:41Z","abstract_excerpt":"Despite the success of recommender systems in alleviating information overload, fairness issues have raised concerns in recent years, potentially leading to unequal treatment for certain user groups. While efforts have been made to improve recommendation fairness, they often assume that users' sensitive attributes are available during model training. However, collecting sensitive information can be difficult, especially on platforms that involve no personal information disclosure. Therefore, we aim to improve recommendation fairness without any access to sensitive attributes. However, this is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19473","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/2505.19473/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":"2505.19473","created_at":"2026-07-05T11:09:30.831281+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19473v1","created_at":"2026-07-05T11:09:30.831281+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19473","created_at":"2026-07-05T11:09:30.831281+00:00"},{"alias_kind":"pith_short_12","alias_value":"7U2RPTY76RAG","created_at":"2026-07-05T11:09:30.831281+00:00"},{"alias_kind":"pith_short_16","alias_value":"7U2RPTY76RAG4XUJ","created_at":"2026-07-05T11:09:30.831281+00:00"},{"alias_kind":"pith_short_8","alias_value":"7U2RPTY7","created_at":"2026-07-05T11:09:30.831281+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.27157","citing_title":"A Survey on Generative Recommendation: Data, Model, and Tasks","ref_index":200,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7U2RPTY76RAG4XUJTLMMRR4UPL","json":"https://pith.science/pith/7U2RPTY76RAG4XUJTLMMRR4UPL.json","graph_json":"https://pith.science/api/pith-number/7U2RPTY76RAG4XUJTLMMRR4UPL/graph.json","events_json":"https://pith.science/api/pith-number/7U2RPTY76RAG4XUJTLMMRR4UPL/events.json","paper":"https://pith.science/paper/7U2RPTY7"},"agent_actions":{"view_html":"https://pith.science/pith/7U2RPTY76RAG4XUJTLMMRR4UPL","download_json":"https://pith.science/pith/7U2RPTY76RAG4XUJTLMMRR4UPL.json","view_paper":"https://pith.science/paper/7U2RPTY7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19473&json=true","fetch_graph":"https://pith.science/api/pith-number/7U2RPTY76RAG4XUJTLMMRR4UPL/graph.json","fetch_events":"https://pith.science/api/pith-number/7U2RPTY76RAG4XUJTLMMRR4UPL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7U2RPTY76RAG4XUJTLMMRR4UPL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7U2RPTY76RAG4XUJTLMMRR4UPL/action/storage_attestation","attest_author":"https://pith.science/pith/7U2RPTY76RAG4XUJTLMMRR4UPL/action/author_attestation","sign_citation":"https://pith.science/pith/7U2RPTY76RAG4XUJTLMMRR4UPL/action/citation_signature","submit_replication":"https://pith.science/pith/7U2RPTY76RAG4XUJTLMMRR4UPL/action/replication_record"}},"created_at":"2026-07-05T11:09:30.831281+00:00","updated_at":"2026-07-05T11:09:30.831281+00:00"}