🤖 AI Summary
This study addresses the lack of a unified knowledge representation framework in current urban digital twins, which hinders multi-source data fusion, provenance tracking, spatial reasoning, and machine learning. The authors propose, for the first time, a provenance-aware urban knowledge graph that integrates CityGML and OpenStreetMap data, incorporates roof material prediction and LoD3 geometric reconstruction, and employs confidence-weighted edges to align cross-source entities while preserving a complete evidence chain. The resulting 180 GiB knowledge graph comprises 180 million nodes and 220 million edges. The work also introduces novel benchmark tasks to evaluate capabilities in 3D spatial reasoning, cross-source consistency judgment, and detection of unsatisfiable queries. Experiments reveal that commercial large language models achieve only 54–69% accuracy, while open-source 7B models perform as low as 6–19% and fail entirely to recognize unsolvable queries.
📝 Abstract
Urban digital twins increasingly combine authoritative, crowd-sourced, machine-learned, and reconstructed data with differing reliability, coverage, and semantics. Yet few urban datasets provide a unified representation supporting multi-source integration, provenance tracking, spatial reasoning, and machine learning. We present AuthentiCity, a multi-source, provenance-aware 3D city knowledge graph spanning five cities across three continents (Hamburg, Helsinki, Zurich, New York, and Tokyo) and comprising 180 GiB, 180M nodes, 220M edges, 1.2B properties, and 3.6M buildings. The labeled property graphs integrate authoritative CityGML and OpenStreetMap data for all cities, adding roof-material predictions and reconstructed LoD3 geometry for Hamburg, under a provenance model in which derived information never replaces authoritative data. Confidence-weighted edges resolve cross-source correspondences, constructing canonical urban entities while preserving traceable links to contributing evidence. AuthentiCity is primarily a data contribution. We introduce two benchmark families that demonstrate the tasks enabled by the representation. The first evaluates natural-language-to-query translation beyond conventional text-to-SQL and text-to-Cypher benchmarks, including 3D spatial reasoning, provenance-aware filtering, cross-source agreement and disagreement, coverage-aware aggregation, and infeasible-query detection. The second evaluates graph representation learning through multi-source attribute prediction, node classification, and cross-source matching prediction, enabling comparison of provenance-agnostic and provenance-aware embeddings. Even a strong commercial LLM reaches only 54-69 % execution accuracy and a 7B open-weight model 6-19 %, while the open-weight model never abstains on unanswerable questions.