{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KWWJKTQPI4ANKSPV5QDEEFFHQB","short_pith_number":"pith:KWWJKTQP","schema_version":"1.0","canonical_sha256":"55ac954e0f4700d549f5ec064214a7805b0c6394fed87f9df1094bfa7946285f","source":{"kind":"arxiv","id":"2504.07801","version":1},"attestation_state":"computed","paper":{"title":"FairEval: Evaluating Fairness in LLM-Based Recommendations with Personality Awareness","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.IR","authors_text":"Chandan Kumar Sah, Li Zhang, Tony Xu, Xiaoli Lian","submitted_at":"2025-04-10T14:38:15Z","abstract_excerpt":"Recent advances in Large Language Models (LLMs) have enabled their application to recommender systems (RecLLMs), yet concerns remain regarding fairness across demographic and psychological user dimensions. We introduce FairEval, a novel evaluation framework to systematically assess fairness in LLM-based recommendations. FairEval integrates personality traits with eight sensitive demographic attributes,including gender, race, and age, enabling a comprehensive assessment of user-level bias. We evaluate models, including ChatGPT 4o and Gemini 1.5 Flash, on music and movie recommendations. FairEva"},"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":"2504.07801","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-04-10T14:38:15Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"3e638fca2a2dc50388fd2d01d7cf1e0e1b322033c2eeee86dac2b79a209c1387","abstract_canon_sha256":"2ec9dee41ad0284a202570c958350328b8772415b71189b3b674e33294a66133"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:14.994347Z","signature_b64":"jYj+lL6VbHAvAI8RfjFDAC7YRz+41Dmy8cI5s/qNyGwYMMyGkJTStnlpkok0E36dAasdPcJkeZm9HeFhaD9RDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55ac954e0f4700d549f5ec064214a7805b0c6394fed87f9df1094bfa7946285f","last_reissued_at":"2026-07-05T10:47:14.993851Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:14.993851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FairEval: Evaluating Fairness in LLM-Based Recommendations with Personality Awareness","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.IR","authors_text":"Chandan Kumar Sah, Li Zhang, Tony Xu, Xiaoli Lian","submitted_at":"2025-04-10T14:38:15Z","abstract_excerpt":"Recent advances in Large Language Models (LLMs) have enabled their application to recommender systems (RecLLMs), yet concerns remain regarding fairness across demographic and psychological user dimensions. We introduce FairEval, a novel evaluation framework to systematically assess fairness in LLM-based recommendations. FairEval integrates personality traits with eight sensitive demographic attributes,including gender, race, and age, enabling a comprehensive assessment of user-level bias. We evaluate models, including ChatGPT 4o and Gemini 1.5 Flash, on music and movie recommendations. FairEva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07801","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/2504.07801/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":"2504.07801","created_at":"2026-07-05T10:47:14.993908+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.07801v1","created_at":"2026-07-05T10:47:14.993908+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07801","created_at":"2026-07-05T10:47:14.993908+00:00"},{"alias_kind":"pith_short_12","alias_value":"KWWJKTQPI4AN","created_at":"2026-07-05T10:47:14.993908+00:00"},{"alias_kind":"pith_short_16","alias_value":"KWWJKTQPI4ANKSPV","created_at":"2026-07-05T10:47:14.993908+00:00"},{"alias_kind":"pith_short_8","alias_value":"KWWJKTQP","created_at":"2026-07-05T10:47:14.993908+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00540","citing_title":"Trustworthy Recommendation in the Era of Large Language Models: Opportunities and Challenges","ref_index":199,"is_internal_anchor":false},{"citing_arxiv_id":"2602.16990","citing_title":"Conv-FinRe: A Conversational and Longitudinal Benchmark for Utility-Grounded Financial Recommendation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08525","citing_title":"Ads in AI Chatbots? An Analysis of How Large Language Models Navigate Conflicts of Interest","ref_index":84,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KWWJKTQPI4ANKSPV5QDEEFFHQB","json":"https://pith.science/pith/KWWJKTQPI4ANKSPV5QDEEFFHQB.json","graph_json":"https://pith.science/api/pith-number/KWWJKTQPI4ANKSPV5QDEEFFHQB/graph.json","events_json":"https://pith.science/api/pith-number/KWWJKTQPI4ANKSPV5QDEEFFHQB/events.json","paper":"https://pith.science/paper/KWWJKTQP"},"agent_actions":{"view_html":"https://pith.science/pith/KWWJKTQPI4ANKSPV5QDEEFFHQB","download_json":"https://pith.science/pith/KWWJKTQPI4ANKSPV5QDEEFFHQB.json","view_paper":"https://pith.science/paper/KWWJKTQP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.07801&json=true","fetch_graph":"https://pith.science/api/pith-number/KWWJKTQPI4ANKSPV5QDEEFFHQB/graph.json","fetch_events":"https://pith.science/api/pith-number/KWWJKTQPI4ANKSPV5QDEEFFHQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KWWJKTQPI4ANKSPV5QDEEFFHQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KWWJKTQPI4ANKSPV5QDEEFFHQB/action/storage_attestation","attest_author":"https://pith.science/pith/KWWJKTQPI4ANKSPV5QDEEFFHQB/action/author_attestation","sign_citation":"https://pith.science/pith/KWWJKTQPI4ANKSPV5QDEEFFHQB/action/citation_signature","submit_replication":"https://pith.science/pith/KWWJKTQPI4ANKSPV5QDEEFFHQB/action/replication_record"}},"created_at":"2026-07-05T10:47:14.993908+00:00","updated_at":"2026-07-05T10:47:14.993908+00:00"}