{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VY2PX333QUAHI3HDZRAYI62JAF","short_pith_number":"pith:VY2PX333","schema_version":"1.0","canonical_sha256":"ae34fbef7b8500746ce3cc41847b49017c037ae34b67835aeb6a40f1e78cfc5d","source":{"kind":"arxiv","id":"2409.11598","version":4},"attestation_state":"computed","paper":{"title":"Towards Fair RAG: On the Impact of Fair Ranking in Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Fernando Diaz, To Eun Kim","submitted_at":"2024-09-17T23:10:04Z","abstract_excerpt":"Despite the central role of retrieval in retrieval-augmented generation (RAG) systems, much of the existing research on RAG overlooks the well-established field of fair ranking and fails to account for the interests of all stakeholders involved. In this paper, we conduct the first systematic evaluation of RAG systems that integrate fairness-aware rankings, addressing both ranking fairness and attribution fairness, which ensures equitable exposure of the sources cited in the generated content. Our evaluation focuses on measuring item-side fairness, specifically the fair exposure of relevant ite"},"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":"2409.11598","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-09-17T23:10:04Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"82ebdc33cd3ae96479652bd051c2b51ecc8f4fa3b2c2b59c7a7ec0df4244eb93","abstract_canon_sha256":"3ac793275d21748cebb12fc551ea3979a44237c4b6d69545b18eadbc2801fe51"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:17.854336Z","signature_b64":"R9SeZsbBK0VBiMyGfXBHtuudgwbTPHjo37KAsob4IJmDW34NBWtLAIBYX7h/vIAywl2h0zvTFgWZikzl9rCpBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae34fbef7b8500746ce3cc41847b49017c037ae34b67835aeb6a40f1e78cfc5d","last_reissued_at":"2026-07-05T11:32:17.853770Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:17.853770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Fair RAG: On the Impact of Fair Ranking in Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Fernando Diaz, To Eun Kim","submitted_at":"2024-09-17T23:10:04Z","abstract_excerpt":"Despite the central role of retrieval in retrieval-augmented generation (RAG) systems, much of the existing research on RAG overlooks the well-established field of fair ranking and fails to account for the interests of all stakeholders involved. In this paper, we conduct the first systematic evaluation of RAG systems that integrate fairness-aware rankings, addressing both ranking fairness and attribution fairness, which ensures equitable exposure of the sources cited in the generated content. Our evaluation focuses on measuring item-side fairness, specifically the fair exposure of relevant ite"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11598","kind":"arxiv","version":4},"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/2409.11598/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":"2409.11598","created_at":"2026-07-05T11:32:17.853844+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.11598v4","created_at":"2026-07-05T11:32:17.853844+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11598","created_at":"2026-07-05T11:32:17.853844+00:00"},{"alias_kind":"pith_short_12","alias_value":"VY2PX333QUAH","created_at":"2026-07-05T11:32:17.853844+00:00"},{"alias_kind":"pith_short_16","alias_value":"VY2PX333QUAHI3HD","created_at":"2026-07-05T11:32:17.853844+00:00"},{"alias_kind":"pith_short_8","alias_value":"VY2PX333","created_at":"2026-07-05T11:32:17.853844+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18806","citing_title":"Towards FairRAG: Preventing Representational Harm in Retrieval-Augmented Generation by Enforcing Fair Exposure at Retrieval Time","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2506.13743","citing_title":"LTRR: Learning To Rank Retrievers for LLMs","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2410.07283","citing_title":"Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2410.07283","citing_title":"Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VY2PX333QUAHI3HDZRAYI62JAF","json":"https://pith.science/pith/VY2PX333QUAHI3HDZRAYI62JAF.json","graph_json":"https://pith.science/api/pith-number/VY2PX333QUAHI3HDZRAYI62JAF/graph.json","events_json":"https://pith.science/api/pith-number/VY2PX333QUAHI3HDZRAYI62JAF/events.json","paper":"https://pith.science/paper/VY2PX333"},"agent_actions":{"view_html":"https://pith.science/pith/VY2PX333QUAHI3HDZRAYI62JAF","download_json":"https://pith.science/pith/VY2PX333QUAHI3HDZRAYI62JAF.json","view_paper":"https://pith.science/paper/VY2PX333","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.11598&json=true","fetch_graph":"https://pith.science/api/pith-number/VY2PX333QUAHI3HDZRAYI62JAF/graph.json","fetch_events":"https://pith.science/api/pith-number/VY2PX333QUAHI3HDZRAYI62JAF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VY2PX333QUAHI3HDZRAYI62JAF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VY2PX333QUAHI3HDZRAYI62JAF/action/storage_attestation","attest_author":"https://pith.science/pith/VY2PX333QUAHI3HDZRAYI62JAF/action/author_attestation","sign_citation":"https://pith.science/pith/VY2PX333QUAHI3HDZRAYI62JAF/action/citation_signature","submit_replication":"https://pith.science/pith/VY2PX333QUAHI3HDZRAYI62JAF/action/replication_record"}},"created_at":"2026-07-05T11:32:17.853844+00:00","updated_at":"2026-07-05T11:32:17.853844+00:00"}