arXiv subjects

Mauro Dalle Lucca Tosi

Publications and source records attributed to Mauro Dalle Lucca Tosi.

4 recordsLinked to original sources

arXiv2026

A Two-Dimensional Study of the Model Context Protocol: Publication and Adoption

The Model Context Protocol (MCP), released by Anthropic in November 2024, standardizes how large language model applications connect to external tools and data sources. Despite MCP's rapid growth, no study has jointly characterized its emergence in the research literature, its adoption on GitHub and the relationship between them. We address this gap with a longitudinal, two-dimensional study of 802 MCP-related publications and 33,319 GitHub repositories. We characterize their growth and identify their application domains via BERTopic and usage contexts via a human-validated GPT-5.6-Luna classifier. We find that publications and repositories began rapid growth within a month of each other in 2025, and peaked together in March 2026. Notably, a second growth wave alone accounts for 49.5% of the GitHub repositories. Most publications (57.8%) and nearly all repositories (93.7%) use MCP as an enabling technology rather than for analyzing, evaluating, extending, or securing it directly. Among repositories, the latter category concentrates almost entirely in one general-purpose topic, while applied usage spreads into product-specific niches. Finally, we provide an overview of the MCP landscape and recommendations to researchers and practitioners in this field.

cs.SE↗

arXiv2026

Ask Safely: Privacy-Aware LLM Query Generation for Knowledge Graphs

Large Language Models (LLMs) are increasingly used to query knowledge graphs (KGs) due to their strong semantic understanding and extrapolation capabilities compared to traditional approaches. However, when KGs contain sensitive information and users lack local access to generative models, privacy becomes a critical concern. To address this issue, we propose a privacy-aware query generation approach for KGs. Our method identifies sensitive information in the graph based on its structure and omits such values before requesting the LLM to translate natural language questions into Cypher queries. Experimental results show that our approach effectively prevents sensitive data from being transmitted to third-party services, while maintaining a high level of query accuracy.

cs.IR↗

arXiv2025

A Metascience Study of the Low-Code Scientific Field

In the last years, model-related publications have been exploring the application of modeling techniques across various domains. Initially focused on UML and the Model-Driven Architecture approach, the literature has been evolving towards the usage of more general concepts such as Model-Driven Development or Model-Driven Engineering. More recently, however, the term "low-code" has taken the modeling field by storm, largely due to its association with several highly popular development platforms. The research community is still discussing the differences and commonalities between this emerging term and previous modeling-related concepts, as well as the broader implications of low-code on the modeling field. In this paper, we present a metascience study of Low-Code. Our study follows a two-fold approach: (1) to analyze the composition and growth (e.g., size, diversity, venues, and topics) of the emerging Low-Code community; and (2) to explore how these aspects differ from those of the "classical" model-driven community. Ultimately, we hope to trigger a discussion on the current state and potential future trajectory of the low-code community, as well as the opportunities for collaboration and synergies between the low-code and modeling communities.

cs.SE↗

arXiv2023

OPTWIN: Drift identification with optimal sub-windows

Online Learning (OL) is a field of research that is increasingly gaining attention both in academia and industry. One of the main challenges of OL is the inherent presence of concept drifts, which are commonly defined as unforeseeable changes in the statistical properties of an incoming data stream over time. The detection of concept drifts typically involves analyzing the error rates produced by an underlying OL algorithm in order to identify if a concept drift occurred or not, such that the OL algorithm can adapt accordingly. Current concept-drift detectors perform very well, i.e., with low false negative rates, but they still tend to exhibit high false positive rates in the concept-drift detection. This may impact the performance of the learner and result in an undue amount of computational resources spent on retraining a model that actually still performs within its expected range. In this paper, we propose OPTWIN, our "OPTimal WINdow" concept drift detector. OPTWIN uses a sliding window of events over an incoming data stream to track the errors of an OL algorithm. The novelty of OPTWIN is to consider both the means and the variances of the error rates produced by a learner in order to split the sliding window into two provably optimal sub-windows, such that the split occurs at the earliest event at which a statistically significant difference according to either the $t$- or the $f$-tests occurred. We assessed OPTWIN over the MOA framework, using ADWIN, DDM, EDDM, STEPD and ECDD as baselines over 7 synthetic and real-world datasets, and in the presence of both sudden and gradual concept drifts. In our experiments, we show that OPTWIN surpasses the F1-score of the baselines in a statistically significant manner while maintaining a lower detection delay and saving up to 21% of time spent on retraining the models.

cs.LG↗