{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YU3YSHEMAM5ZYHNIAV6RPJUIPL","short_pith_number":"pith:YU3YSHEM","schema_version":"1.0","canonical_sha256":"c537891c8c033b9c1da8057d17a6887ae470f41bd3a0b4d16789f4ee404001d8","source":{"kind":"arxiv","id":"2402.02680","version":2},"attestation_state":"computed","paper":{"title":"Large Language Models are Geographically Biased","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.LG"],"primary_cat":"cs.CL","authors_text":"David Lobell, Marshall Burke, Rohin Manvi, Samar Khanna, Stefano Ermon","submitted_at":"2024-02-05T02:32:09Z","abstract_excerpt":"Large Language Models (LLMs) inherently carry the biases contained in their training corpora, which can lead to the perpetuation of societal harm. As the impact of these foundation models grows, understanding and evaluating their biases becomes crucial to achieving fairness and accuracy. We propose to study what LLMs know about the world we live in through the lens of geography. This approach is particularly powerful as there is ground truth for the numerous aspects of human life that are meaningfully projected onto geographic space such as culture, race, language, politics, and religion. We s"},"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":"2402.02680","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-05T02:32:09Z","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"title_canon_sha256":"88584b80f4835ee95447dcfc346adfa4e110f82636537cef5a1cc02b0e0f610b","abstract_canon_sha256":"42c726d28b7a86d9cd319a15f264e48cffa185aca005a333c2285f71fa33e4d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:12.317586Z","signature_b64":"kUpPB3VzRvEVPbHfORLpvYRIxRy2m703y0VY9IUUGjfXo8LEzB7Sii/5ktMzdNsf8fX1ry81wS4FDvqtWaiICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c537891c8c033b9c1da8057d17a6887ae470f41bd3a0b4d16789f4ee404001d8","last_reissued_at":"2026-07-05T09:16:12.317102Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:12.317102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models are Geographically Biased","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.LG"],"primary_cat":"cs.CL","authors_text":"David Lobell, Marshall Burke, Rohin Manvi, Samar Khanna, Stefano Ermon","submitted_at":"2024-02-05T02:32:09Z","abstract_excerpt":"Large Language Models (LLMs) inherently carry the biases contained in their training corpora, which can lead to the perpetuation of societal harm. As the impact of these foundation models grows, understanding and evaluating their biases becomes crucial to achieving fairness and accuracy. We propose to study what LLMs know about the world we live in through the lens of geography. This approach is particularly powerful as there is ground truth for the numerous aspects of human life that are meaningfully projected onto geographic space such as culture, race, language, politics, and religion. We s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02680","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/2402.02680/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":"2402.02680","created_at":"2026-07-05T09:16:12.317167+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.02680v2","created_at":"2026-07-05T09:16:12.317167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02680","created_at":"2026-07-05T09:16:12.317167+00:00"},{"alias_kind":"pith_short_12","alias_value":"YU3YSHEMAM5Z","created_at":"2026-07-05T09:16:12.317167+00:00"},{"alias_kind":"pith_short_16","alias_value":"YU3YSHEMAM5ZYHNI","created_at":"2026-07-05T09:16:12.317167+00:00"},{"alias_kind":"pith_short_8","alias_value":"YU3YSHEM","created_at":"2026-07-05T09:16:12.317167+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20048","citing_title":"Culturally uneven urban perception in large language models","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28369","citing_title":"Multimodal and Multiscale Spatial-Temporal Semantic Search and Recommendation with AI Foundation Models","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01745","citing_title":"Enhancing the Socioeconomic Understanding of Foundation Models with Urban Mobility","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28369","citing_title":"Multimodal and Multiscale Spatial-Temporal Semantic Search and Recommendation with AI Foundation Models","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06694","citing_title":"The Geography of Algorithmic Judgment: LLM Intermediaries, Place Identity, and Racial Steering in Housing Search","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2401.15284","citing_title":"Beyond principlism: Practical strategies for ethical AI use in research practices","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2406.04952","citing_title":"Quantifying Geospatial in the Common Crawl Corpus","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21919","citing_title":"SDGBiasBench: Benchmarking and Mitigating Vision--Language Models' Biases in Sustainable Development Goals","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13069","citing_title":"Geographic Blind Spots in AI Control Monitors: A Cross-National Audit of Claude Opus 4.6","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00315","citing_title":"Unbox Responsible GeoAI: Navigating Climate Extreme and Disaster Mapping","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20048","citing_title":"Culturally uneven urban perception in large language models","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14672","citing_title":"SPAGBias: Uncovering and Tracing Structured Spatial Gender Bias in Large Language Models","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YU3YSHEMAM5ZYHNIAV6RPJUIPL","json":"https://pith.science/pith/YU3YSHEMAM5ZYHNIAV6RPJUIPL.json","graph_json":"https://pith.science/api/pith-number/YU3YSHEMAM5ZYHNIAV6RPJUIPL/graph.json","events_json":"https://pith.science/api/pith-number/YU3YSHEMAM5ZYHNIAV6RPJUIPL/events.json","paper":"https://pith.science/paper/YU3YSHEM"},"agent_actions":{"view_html":"https://pith.science/pith/YU3YSHEMAM5ZYHNIAV6RPJUIPL","download_json":"https://pith.science/pith/YU3YSHEMAM5ZYHNIAV6RPJUIPL.json","view_paper":"https://pith.science/paper/YU3YSHEM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.02680&json=true","fetch_graph":"https://pith.science/api/pith-number/YU3YSHEMAM5ZYHNIAV6RPJUIPL/graph.json","fetch_events":"https://pith.science/api/pith-number/YU3YSHEMAM5ZYHNIAV6RPJUIPL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YU3YSHEMAM5ZYHNIAV6RPJUIPL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YU3YSHEMAM5ZYHNIAV6RPJUIPL/action/storage_attestation","attest_author":"https://pith.science/pith/YU3YSHEMAM5ZYHNIAV6RPJUIPL/action/author_attestation","sign_citation":"https://pith.science/pith/YU3YSHEMAM5ZYHNIAV6RPJUIPL/action/citation_signature","submit_replication":"https://pith.science/pith/YU3YSHEMAM5ZYHNIAV6RPJUIPL/action/replication_record"}},"created_at":"2026-07-05T09:16:12.317167+00:00","updated_at":"2026-07-05T09:16:12.317167+00:00"}