Louis-Felix Nothias | Searcharxiv

arXiv2026

kgsteward: a tool for building, reproducing and maintaining distributed knowledge graphs

Collaborative research projects in life sciences increasingly need to integrate private, embargoed consortium data with public reference databases in order to reach statistically meaningful interpretations. The Resource Description Framework (RDF) is well suited to this task: it facilitates the integration of heterogeneous data sources, and allows researchers to keep data and their documentation as metadata in the same place, provided the knowledge graph itself remains private during the time course of the project. Nevertheless, the development and long-term maintenance of a scientific knowledge graph remains a challenging, labour-intensive endeavour owing to the state of constant flux of most public resources. To tackle this challenge, we present kgsteward, a Python command-line tool that builds and maintains knowledge graphs inside RDF stores from a single, version-controlled configuration file. kgsteward supports multiple triplestores, keeps the local graph up-to-date with its external sources possibly already in RDF, or transformed into it on the fly, and uses SPARQL 1.1 UPDATE commands to amend further imported RDF on the fly. It can also validate the resulting graph with SPARQL queries that double as usage examples for both human users and AI agents. kgsteward has already been used in several collaborative projects at the SIB Swiss Institute of Bioinformatics, and we demonstrate its applicability in two real-world international research projects: one that builds a library of plant extracts with chemical analyses and associated bio-activities, and a second that reconciles public reference resources for human metabolic-network reconstruction.

cs.DB↗

arXiv2026

T2S-Metrics: Unified Library for Evaluating SPARQL Queries Generated From Natural Language

The evaluation of Question Answering (QA) systems over Knowledge Graphs has historically suffered from fragmentation, inconsistency, and limited reproducibility. While significant progress has been made in semantic parsing and SPARQL query generation, evaluation methodologies remain diverse, ad hoc, and often incomparable across studies. Existing benchmarks typically focus on a small subset of metrics, such as query exact match or answer-level F1, neglecting syntactic validity, semantic faithfulness, execution correctness, results ranking quality, and computational efficiency. In this paper, we present t2s-metrics, an open-source, extensible, and unified evaluation library designed specifically for SPARQL query comparison and execution-based assessment. t2s-metrics provides a broad and extensible set of over 20 evaluation metrics, collected from the literature and practical evaluation needs, spanning lexical, syntactic, semantic, structural, execution-based and ranking-based dimensions. These include query-based metrics such as token-level Precision, Recall, and F1; BLEU, ROUGE, METEOR, and CodeBLEU variants; variable-normalized metrics (SP-BLEU, SP-F1); graph-and URI-based exact match metrics; as well as answer set-based metrics such as F1-QALD and Jaccard similarity; ranking metrics including MRR, NDCG, P@k, and Hit@k; and LLM-as-a-Judge metrics. Taking inspiration from the ir-metrics library for Information Retrieval, t2s-metrics provides a modular abstraction layer that decouples metric specification from implementation, enabling consistent, transparent, and reproducible evaluation of SPARQLbased QA systems. We argue that t2s-metrics constitutes a necessary step toward systematic, standardized evaluation in question answering over knowledge graphs and facilitates deeper diagnostic insights into system behavior beyond answer correctness.

cs.IR↗