{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4UBUCTUFGP7D663RFTK3YWCOZ7","short_pith_number":"pith:4UBUCTUF","schema_version":"1.0","canonical_sha256":"e503414e8533fe3f7b712cd5bc584ecff3bb174dcc0fef2d8ddc7199cd0bb450","source":{"kind":"arxiv","id":"2505.12900","version":1},"attestation_state":"computed","paper":{"title":"AutoGEEval: A Multimodal and Automated Framework for Geospatial Code Generation on GEE with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CG","cs.CL","cs.DB"],"primary_cat":"cs.SE","authors_text":"Haoyue Jiao, Huayi Wu, Jianyuan Liang, Longgang Xiang, Shuyang Hou, Xiaopu Zhang, Xuefeng Guan, Xu Li, Yaxian Qing, Zhangxiao Shen, Zhipeng Gui","submitted_at":"2025-05-19T09:35:58Z","abstract_excerpt":"Geospatial code generation is emerging as a key direction in the integration of artificial intelligence and geoscientific analysis. However, there remains a lack of standardized tools for automatic evaluation in this domain. To address this gap, we propose AutoGEEval, the first multimodal, unit-level automated evaluation framework for geospatial code generation tasks on the Google Earth Engine (GEE) platform powered by large language models (LLMs). Built upon the GEE Python API, AutoGEEval establishes a benchmark suite (AutoGEEval-Bench) comprising 1325 test cases that span 26 GEE data types. "},"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":"2505.12900","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-05-19T09:35:58Z","cross_cats_sorted":["cs.AI","cs.CG","cs.CL","cs.DB"],"title_canon_sha256":"fa2612790a088e82197002f0ad3789015a27db6e983024baaef83eb1972fc822","abstract_canon_sha256":"cb09f4671c1beeb141ec429e9ebc42088115d8b2dffe1e9abfa0bc8bb6ffcef8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:11.435763Z","signature_b64":"fe/0Lz8nrVaq7O5lw+Hrr6YiyHeRZx3om23XJuwVjxv8JPBB+8m9++Ie+eGQkM31sGDuCe4rcfHrV2Q+KYxlBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e503414e8533fe3f7b712cd5bc584ecff3bb174dcc0fef2d8ddc7199cd0bb450","last_reissued_at":"2026-07-05T11:05:11.435278Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:11.435278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoGEEval: A Multimodal and Automated Framework for Geospatial Code Generation on GEE with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CG","cs.CL","cs.DB"],"primary_cat":"cs.SE","authors_text":"Haoyue Jiao, Huayi Wu, Jianyuan Liang, Longgang Xiang, Shuyang Hou, Xiaopu Zhang, Xuefeng Guan, Xu Li, Yaxian Qing, Zhangxiao Shen, Zhipeng Gui","submitted_at":"2025-05-19T09:35:58Z","abstract_excerpt":"Geospatial code generation is emerging as a key direction in the integration of artificial intelligence and geoscientific analysis. However, there remains a lack of standardized tools for automatic evaluation in this domain. To address this gap, we propose AutoGEEval, the first multimodal, unit-level automated evaluation framework for geospatial code generation tasks on the Google Earth Engine (GEE) platform powered by large language models (LLMs). Built upon the GEE Python API, AutoGEEval establishes a benchmark suite (AutoGEEval-Bench) comprising 1325 test cases that span 26 GEE data types. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12900","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/2505.12900/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":"2505.12900","created_at":"2026-07-05T11:05:11.435343+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12900v1","created_at":"2026-07-05T11:05:11.435343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12900","created_at":"2026-07-05T11:05:11.435343+00:00"},{"alias_kind":"pith_short_12","alias_value":"4UBUCTUFGP7D","created_at":"2026-07-05T11:05:11.435343+00:00"},{"alias_kind":"pith_short_16","alias_value":"4UBUCTUFGP7D663R","created_at":"2026-07-05T11:05:11.435343+00:00"},{"alias_kind":"pith_short_8","alias_value":"4UBUCTUF","created_at":"2026-07-05T11:05:11.435343+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4UBUCTUFGP7D663RFTK3YWCOZ7","json":"https://pith.science/pith/4UBUCTUFGP7D663RFTK3YWCOZ7.json","graph_json":"https://pith.science/api/pith-number/4UBUCTUFGP7D663RFTK3YWCOZ7/graph.json","events_json":"https://pith.science/api/pith-number/4UBUCTUFGP7D663RFTK3YWCOZ7/events.json","paper":"https://pith.science/paper/4UBUCTUF"},"agent_actions":{"view_html":"https://pith.science/pith/4UBUCTUFGP7D663RFTK3YWCOZ7","download_json":"https://pith.science/pith/4UBUCTUFGP7D663RFTK3YWCOZ7.json","view_paper":"https://pith.science/paper/4UBUCTUF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12900&json=true","fetch_graph":"https://pith.science/api/pith-number/4UBUCTUFGP7D663RFTK3YWCOZ7/graph.json","fetch_events":"https://pith.science/api/pith-number/4UBUCTUFGP7D663RFTK3YWCOZ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4UBUCTUFGP7D663RFTK3YWCOZ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4UBUCTUFGP7D663RFTK3YWCOZ7/action/storage_attestation","attest_author":"https://pith.science/pith/4UBUCTUFGP7D663RFTK3YWCOZ7/action/author_attestation","sign_citation":"https://pith.science/pith/4UBUCTUFGP7D663RFTK3YWCOZ7/action/citation_signature","submit_replication":"https://pith.science/pith/4UBUCTUFGP7D663RFTK3YWCOZ7/action/replication_record"}},"created_at":"2026-07-05T11:05:11.435343+00:00","updated_at":"2026-07-05T11:05:11.435343+00:00"}