{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:P5R43HPPJFHSIQN4XPHHTTZWZJ","short_pith_number":"pith:P5R43HPP","schema_version":"1.0","canonical_sha256":"7f63cd9def494f2441bcbbce79cf36ca65863a96057389a24ccdda63ac567759","source":{"kind":"arxiv","id":"2409.19804","version":2},"attestation_state":"computed","paper":{"title":"Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hsin-Tai Wu, Shuowei Li, Xuyang Wu, Yi Fang, Zhiqiang Tao","submitted_at":"2024-09-29T22:04:26Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has recently gained significant attention for its enhanced ability to integrate external knowledge sources into open-domain question answering (QA) tasks. However, it remains unclear how these models address fairness concerns, particularly with respect to sensitive attributes such as gender, geographic location, and other demographic factors. First, as language models evolve to prioritize utility, like improving exact match accuracy, fairness considerations may have been largely overlooked. Second, the complex, multi-component architecture of RAG methods po"},"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":"2409.19804","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-29T22:04:26Z","cross_cats_sorted":[],"title_canon_sha256":"4cd8735d8ee7347254b7b867a823fb5d95f07e4b8739c071403915f5244d512a","abstract_canon_sha256":"3e3a8337e7107c2bb1429e5df899806013fa8df28b1498c634dd9aec450486f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:13.101740Z","signature_b64":"fFs9KCVw2mtshZ84LgPjj/ZN+1j8rBof+3gZNYVAbOFwHhu/7BarAI8GLl1ScaRiS9WvQ2bR+B5eN6a+xZ3ACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f63cd9def494f2441bcbbce79cf36ca65863a96057389a24ccdda63ac567759","last_reissued_at":"2026-07-05T10:40:13.101204Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:13.101204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hsin-Tai Wu, Shuowei Li, Xuyang Wu, Yi Fang, Zhiqiang Tao","submitted_at":"2024-09-29T22:04:26Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has recently gained significant attention for its enhanced ability to integrate external knowledge sources into open-domain question answering (QA) tasks. However, it remains unclear how these models address fairness concerns, particularly with respect to sensitive attributes such as gender, geographic location, and other demographic factors. First, as language models evolve to prioritize utility, like improving exact match accuracy, fairness considerations may have been largely overlooked. Second, the complex, multi-component architecture of RAG methods po"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19804","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/2409.19804/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":"2409.19804","created_at":"2026-07-05T10:40:13.101263+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.19804v2","created_at":"2026-07-05T10:40:13.101263+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19804","created_at":"2026-07-05T10:40:13.101263+00:00"},{"alias_kind":"pith_short_12","alias_value":"P5R43HPPJFHS","created_at":"2026-07-05T10:40:13.101263+00:00"},{"alias_kind":"pith_short_16","alias_value":"P5R43HPPJFHSIQN4","created_at":"2026-07-05T10:40:13.101263+00:00"},{"alias_kind":"pith_short_8","alias_value":"P5R43HPP","created_at":"2026-07-05T10:40:13.101263+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.05929","citing_title":"LLM Harms: A Taxonomy and Discussion","ref_index":82,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P5R43HPPJFHSIQN4XPHHTTZWZJ","json":"https://pith.science/pith/P5R43HPPJFHSIQN4XPHHTTZWZJ.json","graph_json":"https://pith.science/api/pith-number/P5R43HPPJFHSIQN4XPHHTTZWZJ/graph.json","events_json":"https://pith.science/api/pith-number/P5R43HPPJFHSIQN4XPHHTTZWZJ/events.json","paper":"https://pith.science/paper/P5R43HPP"},"agent_actions":{"view_html":"https://pith.science/pith/P5R43HPPJFHSIQN4XPHHTTZWZJ","download_json":"https://pith.science/pith/P5R43HPPJFHSIQN4XPHHTTZWZJ.json","view_paper":"https://pith.science/paper/P5R43HPP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.19804&json=true","fetch_graph":"https://pith.science/api/pith-number/P5R43HPPJFHSIQN4XPHHTTZWZJ/graph.json","fetch_events":"https://pith.science/api/pith-number/P5R43HPPJFHSIQN4XPHHTTZWZJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P5R43HPPJFHSIQN4XPHHTTZWZJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P5R43HPPJFHSIQN4XPHHTTZWZJ/action/storage_attestation","attest_author":"https://pith.science/pith/P5R43HPPJFHSIQN4XPHHTTZWZJ/action/author_attestation","sign_citation":"https://pith.science/pith/P5R43HPPJFHSIQN4XPHHTTZWZJ/action/citation_signature","submit_replication":"https://pith.science/pith/P5R43HPPJFHSIQN4XPHHTTZWZJ/action/replication_record"}},"created_at":"2026-07-05T10:40:13.101263+00:00","updated_at":"2026-07-05T10:40:13.101263+00:00"}