{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:32RVIDFBYK4D52AMIPYQ6MBEM3","short_pith_number":"pith:32RVIDFB","schema_version":"1.0","canonical_sha256":"dea3540ca1c2b83ee80c43f10f302466f17cf1111da796bc4f650668ca47ab20","source":{"kind":"arxiv","id":"2310.06213","version":2},"attestation_state":"computed","paper":{"title":"GeoLLM: Extracting Geospatial Knowledge from Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"David Lobell, Gengchen Mai, Marshall Burke, Rohin Manvi, Samar Khanna, Stefano Ermon","submitted_at":"2023-10-10T00:03:23Z","abstract_excerpt":"The application of machine learning (ML) in a range of geospatial tasks is increasingly common but often relies on globally available covariates such as satellite imagery that can either be expensive or lack predictive power. Here we explore the question of whether the vast amounts of knowledge found in Internet language corpora, now compressed within large language models (LLMs), can be leveraged for geospatial prediction tasks. We first demonstrate that LLMs embed remarkable spatial information about locations, but naively querying LLMs using geographic coordinates alone is ineffective in pr"},"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":"2310.06213","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-10T00:03:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"769ed237bc3552c161dc14876ba717db113a194c75629322708d5d545f910f5f","abstract_canon_sha256":"1ddf85d33e699d7ae29df46281e0f6e70e6078bed0587236272cb6610d5d0b30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:48.997164Z","signature_b64":"t5dppzBrZcBXM21O82hk17tzXp7mmYKEwj9Q0CJTelfleKqj0X/zZT7vPe4NLSxtBEgj2h/QzYZ3a7djRV60DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dea3540ca1c2b83ee80c43f10f302466f17cf1111da796bc4f650668ca47ab20","last_reissued_at":"2026-07-05T07:48:48.996711Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:48.996711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GeoLLM: Extracting Geospatial Knowledge from Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"David Lobell, Gengchen Mai, Marshall Burke, Rohin Manvi, Samar Khanna, Stefano Ermon","submitted_at":"2023-10-10T00:03:23Z","abstract_excerpt":"The application of machine learning (ML) in a range of geospatial tasks is increasingly common but often relies on globally available covariates such as satellite imagery that can either be expensive or lack predictive power. Here we explore the question of whether the vast amounts of knowledge found in Internet language corpora, now compressed within large language models (LLMs), can be leveraged for geospatial prediction tasks. We first demonstrate that LLMs embed remarkable spatial information about locations, but naively querying LLMs using geographic coordinates alone is ineffective in pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.06213","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/2310.06213/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":"2310.06213","created_at":"2026-07-05T07:48:48.996770+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.06213v2","created_at":"2026-07-05T07:48:48.996770+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06213","created_at":"2026-07-05T07:48:48.996770+00:00"},{"alias_kind":"pith_short_12","alias_value":"32RVIDFBYK4D","created_at":"2026-07-05T07:48:48.996770+00:00"},{"alias_kind":"pith_short_16","alias_value":"32RVIDFBYK4D52AM","created_at":"2026-07-05T07:48:48.996770+00:00"},{"alias_kind":"pith_short_8","alias_value":"32RVIDFB","created_at":"2026-07-05T07:48:48.996770+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08036","citing_title":"GIScholarBench: Benchmarking LLM Overconfidence in GIS Research","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04381","citing_title":"From Symbolic to Geometric: Enabling Spatial Reasoning in Large Language Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01745","citing_title":"Enhancing the Socioeconomic Understanding of Foundation Models with Urban Mobility","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2411.07207","citing_title":"General Geospatial Inference with a Population Dynamics Foundation Model","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19172","citing_title":"Bridge: Retrieval-Augmented Spatiotemporal Modeling for Urban Delivery Demand","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14705","citing_title":"SynHAT: A Two-stage Coarse-to-Fine Diffusion Framework for Synthesizing Human Activity Traces","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/32RVIDFBYK4D52AMIPYQ6MBEM3","json":"https://pith.science/pith/32RVIDFBYK4D52AMIPYQ6MBEM3.json","graph_json":"https://pith.science/api/pith-number/32RVIDFBYK4D52AMIPYQ6MBEM3/graph.json","events_json":"https://pith.science/api/pith-number/32RVIDFBYK4D52AMIPYQ6MBEM3/events.json","paper":"https://pith.science/paper/32RVIDFB"},"agent_actions":{"view_html":"https://pith.science/pith/32RVIDFBYK4D52AMIPYQ6MBEM3","download_json":"https://pith.science/pith/32RVIDFBYK4D52AMIPYQ6MBEM3.json","view_paper":"https://pith.science/paper/32RVIDFB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.06213&json=true","fetch_graph":"https://pith.science/api/pith-number/32RVIDFBYK4D52AMIPYQ6MBEM3/graph.json","fetch_events":"https://pith.science/api/pith-number/32RVIDFBYK4D52AMIPYQ6MBEM3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/32RVIDFBYK4D52AMIPYQ6MBEM3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/32RVIDFBYK4D52AMIPYQ6MBEM3/action/storage_attestation","attest_author":"https://pith.science/pith/32RVIDFBYK4D52AMIPYQ6MBEM3/action/author_attestation","sign_citation":"https://pith.science/pith/32RVIDFBYK4D52AMIPYQ6MBEM3/action/citation_signature","submit_replication":"https://pith.science/pith/32RVIDFBYK4D52AMIPYQ6MBEM3/action/replication_record"}},"created_at":"2026-07-05T07:48:48.996770+00:00","updated_at":"2026-07-05T07:48:48.996770+00:00"}