{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:24B5PI63RWUDPAUPL6APWD345F","short_pith_number":"pith:24B5PI63","schema_version":"1.0","canonical_sha256":"d703d7a3db8da837828f5f80fb0f7ce96a488ed103da511ce24cac1d2f71f71c","source":{"kind":"arxiv","id":"2502.18470","version":5},"attestation_state":"computed","paper":{"title":"Spatial-RAG: Spatial Retrieval Augmented Generation for Real-World Geospatial Reasoning Questions","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.ET","cs.LG"],"primary_cat":"cs.IR","authors_text":"Dazhou Yu, Gengchen Mai, Jinghong Peng, Liang Zhao, Riyang Bao, Ruiyu Ning","submitted_at":"2025-02-04T01:30:06Z","abstract_excerpt":"Answering real-world geospatial questions--such as finding restaurants along a travel route or amenities near a landmark--requires reasoning over both geographic relationships and semantic user intent. However, existing large language models (LLMs) lack spatial computing capabilities and access to up-to-date, ubiquitous real-world geospatial data, while traditional geospatial systems fall short in interpreting natural language. To bridge this gap, we introduce Spatial-RAG, a Retrieval-Augmented Generation (RAG) framework designed for geospatial question answering. Spatial-RAG integrates struct"},"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":"2502.18470","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2025-02-04T01:30:06Z","cross_cats_sorted":["cs.ET","cs.LG"],"title_canon_sha256":"06bd35944ed765f022088236c5e067876c9a7614d627fc99fec9261a6b178e87","abstract_canon_sha256":"d8af2d4f1c88afa908cfe232c5aac62e87e30d6ca005937b21623f5043222802"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:24.980887Z","signature_b64":"nMZSpC6ZHaYJ06Z8imGlYi+am9bBOn/f3a84Hl6YwrI9c7/dncLHkMoU3hTcyCS9TfGC3M2kozw8v1h+f0K7CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d703d7a3db8da837828f5f80fb0f7ce96a488ed103da511ce24cac1d2f71f71c","last_reissued_at":"2026-07-05T11:19:24.980402Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:24.980402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spatial-RAG: Spatial Retrieval Augmented Generation for Real-World Geospatial Reasoning Questions","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.ET","cs.LG"],"primary_cat":"cs.IR","authors_text":"Dazhou Yu, Gengchen Mai, Jinghong Peng, Liang Zhao, Riyang Bao, Ruiyu Ning","submitted_at":"2025-02-04T01:30:06Z","abstract_excerpt":"Answering real-world geospatial questions--such as finding restaurants along a travel route or amenities near a landmark--requires reasoning over both geographic relationships and semantic user intent. However, existing large language models (LLMs) lack spatial computing capabilities and access to up-to-date, ubiquitous real-world geospatial data, while traditional geospatial systems fall short in interpreting natural language. To bridge this gap, we introduce Spatial-RAG, a Retrieval-Augmented Generation (RAG) framework designed for geospatial question answering. Spatial-RAG integrates struct"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18470","kind":"arxiv","version":5},"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/2502.18470/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":"2502.18470","created_at":"2026-07-05T11:19:24.980463+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.18470v5","created_at":"2026-07-05T11:19:24.980463+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18470","created_at":"2026-07-05T11:19:24.980463+00:00"},{"alias_kind":"pith_short_12","alias_value":"24B5PI63RWUD","created_at":"2026-07-05T11:19:24.980463+00:00"},{"alias_kind":"pith_short_16","alias_value":"24B5PI63RWUDPAUP","created_at":"2026-07-05T11:19:24.980463+00:00"},{"alias_kind":"pith_short_8","alias_value":"24B5PI63","created_at":"2026-07-05T11:19:24.980463+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22219","citing_title":"Lost in Aggregation: A Multi-Scale Diagnostic Benchmark for LLM Spatial Navigation","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19667","citing_title":"CacheWeaver: Cache-Aware Evidence Ordering for Efficient Grounded RAG Inference","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2503.16683","citing_title":"GAIR: Location-Aware Self-Supervised Contrastive Pre-Training with Geo-Aligned Implicit Representations","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22811","citing_title":"GS-QA: A Benchmark for Geospatial Question Answering","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13956","citing_title":"AOI: Context-Aware Multi-Agent Operations via Dynamic Scheduling and Hierarchical Memory Compression","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2602.04712","citing_title":"SAR-RAG: ATR Visual Question Answering by Semantic Search, Retrieval, and MLLM Generation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2603.23375","citing_title":"Natural Language Interfaces for Spatial and Temporal Databases: A Comprehensive Overview of Methods, Taxonomy, and Future Directions","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05459","citing_title":"Privacy Without Losing Place: A Paradigm for Private Retrieval in Spatial RAGs","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07677","citing_title":"TRACE: Tourism Recommendation with Accountable Citation Evidence","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/24B5PI63RWUDPAUPL6APWD345F","json":"https://pith.science/pith/24B5PI63RWUDPAUPL6APWD345F.json","graph_json":"https://pith.science/api/pith-number/24B5PI63RWUDPAUPL6APWD345F/graph.json","events_json":"https://pith.science/api/pith-number/24B5PI63RWUDPAUPL6APWD345F/events.json","paper":"https://pith.science/paper/24B5PI63"},"agent_actions":{"view_html":"https://pith.science/pith/24B5PI63RWUDPAUPL6APWD345F","download_json":"https://pith.science/pith/24B5PI63RWUDPAUPL6APWD345F.json","view_paper":"https://pith.science/paper/24B5PI63","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.18470&json=true","fetch_graph":"https://pith.science/api/pith-number/24B5PI63RWUDPAUPL6APWD345F/graph.json","fetch_events":"https://pith.science/api/pith-number/24B5PI63RWUDPAUPL6APWD345F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/24B5PI63RWUDPAUPL6APWD345F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/24B5PI63RWUDPAUPL6APWD345F/action/storage_attestation","attest_author":"https://pith.science/pith/24B5PI63RWUDPAUPL6APWD345F/action/author_attestation","sign_citation":"https://pith.science/pith/24B5PI63RWUDPAUPL6APWD345F/action/citation_signature","submit_replication":"https://pith.science/pith/24B5PI63RWUDPAUPL6APWD345F/action/replication_record"}},"created_at":"2026-07-05T11:19:24.980463+00:00","updated_at":"2026-07-05T11:19:24.980463+00:00"}