{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:W223U2YULNLUW55CEBUH5EVEDG","short_pith_number":"pith:W223U2YU","schema_version":"1.0","canonical_sha256":"b6b5ba6b145b574b77a220687e92a419ab49fe842a280e61fbbd0f0aa41d367f","source":{"kind":"arxiv","id":"2410.18792","version":2},"attestation_state":"computed","paper":{"title":"An LLM Agent for Automatic Geospatial Data Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CY","authors_text":"Camille Kurtz, Sylvain Lobry, Weijie Wang, Yuxing Chen","submitted_at":"2024-10-24T14:47:25Z","abstract_excerpt":"Large language models (LLMs) are being used in data science code generation tasks, but they often struggle with complex sequential tasks, leading to logical errors. Their application to geospatial data processing is particularly challenging due to difficulties in incorporating complex data structures and spatial constraints, effectively utilizing diverse function calls, and the tendency to hallucinate less-used geospatial libraries. To tackle these problems, we introduce GeoAgent, a new interactive framework designed to help LLMs handle geospatial data processing more effectively. GeoAgent pio"},"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":"2410.18792","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2024-10-24T14:47:25Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ee812a0ec0eea0a4eb90de4c067847c0d10759c246ba438e7255019c4d7d7937","abstract_canon_sha256":"dab9f9e525c15216bbb4a18e3425c632f960fe56d806d84baaaaf5618d32a6c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:49.456135Z","signature_b64":"nrvsbVdAY++SovV7UiFDfraeZdNljVl70eZY60fmTzAGgs64/etzuCecVG33elhIp7EJYhW5/BcwgQfWacUlBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6b5ba6b145b574b77a220687e92a419ab49fe842a280e61fbbd0f0aa41d367f","last_reissued_at":"2026-07-05T09:25:49.455673Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:49.455673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An LLM Agent for Automatic Geospatial Data Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CY","authors_text":"Camille Kurtz, Sylvain Lobry, Weijie Wang, Yuxing Chen","submitted_at":"2024-10-24T14:47:25Z","abstract_excerpt":"Large language models (LLMs) are being used in data science code generation tasks, but they often struggle with complex sequential tasks, leading to logical errors. Their application to geospatial data processing is particularly challenging due to difficulties in incorporating complex data structures and spatial constraints, effectively utilizing diverse function calls, and the tendency to hallucinate less-used geospatial libraries. To tackle these problems, we introduce GeoAgent, a new interactive framework designed to help LLMs handle geospatial data processing more effectively. GeoAgent pio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18792","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/2410.18792/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":"2410.18792","created_at":"2026-07-05T09:25:49.455734+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.18792v2","created_at":"2026-07-05T09:25:49.455734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18792","created_at":"2026-07-05T09:25:49.455734+00:00"},{"alias_kind":"pith_short_12","alias_value":"W223U2YULNLU","created_at":"2026-07-05T09:25:49.455734+00:00"},{"alias_kind":"pith_short_16","alias_value":"W223U2YULNLUW55C","created_at":"2026-07-05T09:25:49.455734+00:00"},{"alias_kind":"pith_short_8","alias_value":"W223U2YU","created_at":"2026-07-05T09:25:49.455734+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17076","citing_title":"CMIP-Forge: An Agentic System that Retrieves, Computes, and Self-Reviews Climate Science","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11740","citing_title":"UniReason-Med: A Shared Grounded Reasoning Interface for 2D-to-3D Transfer in Medical VQA","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28896","citing_title":"A Task-Driven and Quality-Assured Agent Framework for SAR Data Generation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2601.01891","citing_title":"Agentic AI in Remote Sensing: Foundations, Taxonomy, and Emerging Systems","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25544","citing_title":"Medoid Prototype Alignment for Cross-Plant Unknown Attack Detection in Industrial Control Systems","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W223U2YULNLUW55CEBUH5EVEDG","json":"https://pith.science/pith/W223U2YULNLUW55CEBUH5EVEDG.json","graph_json":"https://pith.science/api/pith-number/W223U2YULNLUW55CEBUH5EVEDG/graph.json","events_json":"https://pith.science/api/pith-number/W223U2YULNLUW55CEBUH5EVEDG/events.json","paper":"https://pith.science/paper/W223U2YU"},"agent_actions":{"view_html":"https://pith.science/pith/W223U2YULNLUW55CEBUH5EVEDG","download_json":"https://pith.science/pith/W223U2YULNLUW55CEBUH5EVEDG.json","view_paper":"https://pith.science/paper/W223U2YU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.18792&json=true","fetch_graph":"https://pith.science/api/pith-number/W223U2YULNLUW55CEBUH5EVEDG/graph.json","fetch_events":"https://pith.science/api/pith-number/W223U2YULNLUW55CEBUH5EVEDG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W223U2YULNLUW55CEBUH5EVEDG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W223U2YULNLUW55CEBUH5EVEDG/action/storage_attestation","attest_author":"https://pith.science/pith/W223U2YULNLUW55CEBUH5EVEDG/action/author_attestation","sign_citation":"https://pith.science/pith/W223U2YULNLUW55CEBUH5EVEDG/action/citation_signature","submit_replication":"https://pith.science/pith/W223U2YULNLUW55CEBUH5EVEDG/action/replication_record"}},"created_at":"2026-07-05T09:25:49.455734+00:00","updated_at":"2026-07-05T09:25:49.455734+00:00"}