{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JP2Q5GWMDBZN3FZKHPWIDN7XZ4","short_pith_number":"pith:JP2Q5GWM","schema_version":"1.0","canonical_sha256":"4bf50e9acc1872dd972a3bec81b7f7cf26b4a15ab856565c823f849f18d11991","source":{"kind":"arxiv","id":"2509.06195","version":1},"attestation_state":"computed","paper":{"title":"Language Bias in Information Retrieval: The Nature of the Beast and Mitigation Methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Fan Jiang, Jinrui Yang, Timothy Baldwin","submitted_at":"2025-09-07T20:10:49Z","abstract_excerpt":"Language fairness in multilingual information retrieval (MLIR) systems is crucial for ensuring equitable access to information across diverse languages. This paper sheds light on the issue, based on the assumption that queries in different languages, but with identical semantics, should yield equivalent ranking lists when retrieving on the same multilingual documents. We evaluate the degree of fairness using both traditional retrieval methods, and a DPR neural ranker based on mBERT and XLM-R. Additionally, we introduce `LaKDA', a novel loss designed to mitigate language biases in neural MLIR a"},"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":"2509.06195","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-09-07T20:10:49Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"633b8c2762bf4ffb9899ad064a8eed4be1444f2ada704db170b55fb054706ef9","abstract_canon_sha256":"3757c41ab1be5b426ee4f80bd4585417e0bd487ae9de72169cbd542cd3a5d4af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:31.428851Z","signature_b64":"DZ56RV2yf01/y6JWSWD4F15ZAGxbiOx6RbDjpI0cty7mpcc2UyZJNE+Bo49PnP11wxAfPZKVus3IV9/WeHUABw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bf50e9acc1872dd972a3bec81b7f7cf26b4a15ab856565c823f849f18d11991","last_reissued_at":"2026-07-05T12:06:31.428355Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:31.428355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Bias in Information Retrieval: The Nature of the Beast and Mitigation Methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Fan Jiang, Jinrui Yang, Timothy Baldwin","submitted_at":"2025-09-07T20:10:49Z","abstract_excerpt":"Language fairness in multilingual information retrieval (MLIR) systems is crucial for ensuring equitable access to information across diverse languages. This paper sheds light on the issue, based on the assumption that queries in different languages, but with identical semantics, should yield equivalent ranking lists when retrieving on the same multilingual documents. We evaluate the degree of fairness using both traditional retrieval methods, and a DPR neural ranker based on mBERT and XLM-R. Additionally, we introduce `LaKDA', a novel loss designed to mitigate language biases in neural MLIR a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06195","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/2509.06195/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":"2509.06195","created_at":"2026-07-05T12:06:31.428424+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.06195v1","created_at":"2026-07-05T12:06:31.428424+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06195","created_at":"2026-07-05T12:06:31.428424+00:00"},{"alias_kind":"pith_short_12","alias_value":"JP2Q5GWMDBZN","created_at":"2026-07-05T12:06:31.428424+00:00"},{"alias_kind":"pith_short_16","alias_value":"JP2Q5GWMDBZN3FZK","created_at":"2026-07-05T12:06:31.428424+00:00"},{"alias_kind":"pith_short_8","alias_value":"JP2Q5GWM","created_at":"2026-07-05T12:06:31.428424+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07249","citing_title":"MLAIRE: Multilingual Language-Aware Information Retrieval Evaluation Protocal","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JP2Q5GWMDBZN3FZKHPWIDN7XZ4","json":"https://pith.science/pith/JP2Q5GWMDBZN3FZKHPWIDN7XZ4.json","graph_json":"https://pith.science/api/pith-number/JP2Q5GWMDBZN3FZKHPWIDN7XZ4/graph.json","events_json":"https://pith.science/api/pith-number/JP2Q5GWMDBZN3FZKHPWIDN7XZ4/events.json","paper":"https://pith.science/paper/JP2Q5GWM"},"agent_actions":{"view_html":"https://pith.science/pith/JP2Q5GWMDBZN3FZKHPWIDN7XZ4","download_json":"https://pith.science/pith/JP2Q5GWMDBZN3FZKHPWIDN7XZ4.json","view_paper":"https://pith.science/paper/JP2Q5GWM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.06195&json=true","fetch_graph":"https://pith.science/api/pith-number/JP2Q5GWMDBZN3FZKHPWIDN7XZ4/graph.json","fetch_events":"https://pith.science/api/pith-number/JP2Q5GWMDBZN3FZKHPWIDN7XZ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JP2Q5GWMDBZN3FZKHPWIDN7XZ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JP2Q5GWMDBZN3FZKHPWIDN7XZ4/action/storage_attestation","attest_author":"https://pith.science/pith/JP2Q5GWMDBZN3FZKHPWIDN7XZ4/action/author_attestation","sign_citation":"https://pith.science/pith/JP2Q5GWMDBZN3FZKHPWIDN7XZ4/action/citation_signature","submit_replication":"https://pith.science/pith/JP2Q5GWMDBZN3FZKHPWIDN7XZ4/action/replication_record"}},"created_at":"2026-07-05T12:06:31.428424+00:00","updated_at":"2026-07-05T12:06:31.428424+00:00"}