Searcharxiv⌕ Search

arXiv subjects

Andrea Vandin

Publications and source records attributed to Andrea Vandin.

At least 19 recordsLinked to original sources
arXiv2026

Large Language Models, Encoder Architectures and Hybrid Approaches for Patent Classification

Automated patent classification is essential for organizing technological knowledge and constructing indicators of technological change, specialization, and leadership. To identify the relative strengths and weaknesses of popular state- of-the-art approaches to this problem, we perform a controlled comparison of patent-specific encoders and open-weight local LLMs for hierarchical multi-label Cooperative Patent Classification (CPC). We find that the best-performing encoder (task-adapted BERT-for-Patents) outperforms the best-performing LLM (fine-tuned Qwen3.5-9B), while requiring one to two orders of magnitude less energy for inference. The two model families show complementary capabilities, which we leverage through a hybrid pipeline that routes patents with the highest encoder uncertainty to the LLM, yielding significant gains on this subset. We also find that across models, classification errors are especially pronounced in CPC categories that are cross-cutting or semantically broad - such as Section Y - and that they have substantial consequences for technology mapping and country and assignee rankings. The analysis covers predictive and hierarchical performance, computational cost and energy consumption, external validation on EPO patents, and the propagation of classification errors into downstream technological indicators, with implications for automated patent classification procedures used by patent offices, technology analysts, and scientometric researchers.

cs.CE↗
arXiv2026

The hidden structure of innovation networks

Innovation emerges from complex collaboration patterns - among inventors, firms, or institutions. However, not much is known about the overall mesoscopic structure around which inventive activity self-organizes. Here, we tackle this problem by employing patent data to analyze both individual (\textit{co-inventorship}) and organization (\textit{co-ownership}) networks in three strategic domains (\textit{artificial intelligence}, \textit{biotechnology} and \textit{semiconductors}). We characterize the mesoscale structure (in terms of clusters) of each domain by comparing two alternative methods: a standard baseline - modularity maximization - and one based on the minimization of the Bayesian Information Criterion, within the Stochastic Block Model and its degree-corrected variant. We find that, across sectors, inventor networks are denser and more clustered than organization ones - consistently with the presence of small recurrent teams embedded into broader institutional hierarchies - whereas organization networks have a neater role-based structures, with few bridging firms coordinating the most peripheral ones; still, both are characterized by the presence of local core-periphery structures. We also find that the discovered meso-structures are connected to innovation output. In particular, Lorenz curves of forward citations show a pervasive inequality in technological influence: across sectors and methods, both inventor (especially) and organization networks consistently show high levels of concentration of citations in a few of the discovered clusters. Our results demonstrate that the baseline modularity-based method may not be capable of fully capturing the way collaborations drive the spreading of inventive impact across technological domains. This is due to the presence of local hierarchies that call for the more refined tools of Bayesian inference.

econ.GN↗
arXiv2026

Towards Agentic Agent-based Models: Feasibility, Performance, and Statistical Model Checking

Agent-based models (ABMs) rely on simple, explicit and reproducible rules for individual decision making, while complex collective behavior emerges from interactions among agents. Recent advances in large language models (LLMs) make it tempting to replace, enrich, or perturb these rules with LLM-based agentic capabilities. However, this raises a methodological question: how does introducing LLM-driven decisions affect the reliability, computational cost, and behavior of ABM simulations? We investigate this for Mesa ABM models, a popular Python library for ABMs, analyzed by statistical model checking. Building on Mesa's integration with the statistical model checker MultiVeStA, we extend the classical Schelling segregation model with a hybrid population: ordinary agents classify neighbors using the standard symbolic rule, while one agent delegates this task to an LLM through tool calls. The LLM-enabled agent receives natural-language descriptions of neighboring agents and invokes tools that increment counters of similar/different neighbors; these counters determine its happiness according to the original Schelling dynamics. This provides a minimal but controlled setting where the semantic, operational, and computational behavior of LLM-based decisions can be studied inside an otherwise standard ABM. We report preliminary experiments with locally served LLMs of different sizes, showing that smaller models may fail simple semantic classification experiments or become operationally unusable during repeated tool-call generation, while larger tested models pass these preliminary checks. We discuss how statistical model checking can estimate classical ABM observables and quantify the impact of introducing agentic LLM components into simulation models.

cs.AI↗
arXiv2026

Statistical Model Checking of the Keynes+Schumpeter Model: A Transient Sensitivity Analysis of a Macroeconomic ABM

Agent-based models (ABMs) are increasingly used in macroeconomics, but their analysis still often relies on ad hoc Monte Carlo campaigns with heterogeneous statistical effort across parameter settings. We show how statistical model checking (SMC), implemented through MultiVeStA, can provide a principled analysis layer for a realistic macroeconomic ABM without rewriting the simulator in a dedicated formalism. Our case study is the heuristic-switching Keynes+Schumpeter(K+S) model, analysed hrough a transient sensitivity campaign over one-parameter sweeps, two macro observables (unemployment and GDP growth), and one auxiliary micro-level probe (market share) on the post-warmup phase of a 600-step horizon. The analysis is driven by reusable temporal queries, observable-specific precision targets, and confidence-based stopping rules that automatically determine the simulation effort required by each configuration. Results show a clear contrast across parameter families: macro-financial and structural sweeps produce the strongest transient effects, whereas several heuristic-rule sweeps remain much weaker under the same precision policy. More broadly, the paper shows that SMC can support reproducible and informative quantitative analysis of substantively rich economic ABMs, while making uncertainty estimates and simulation cost explicit parts of the reported results.

cs.MA↗
arXiv2026

GravityGraphSAGE: Link Prediction in Directed Attributed Graphs

Link prediction (inferring missing or future connections between nodes in a graph) is a fundamental problem in network science with widespread applications in, e.g., biological systems, recommender systems, finance and cybersecurity. The ability to accurately predict links has significant real-world applications, such as detecting fraudulent financial transactions or identifying drug-target interactions in biomedicine. Despite a rich literature, link prediction is still challenging, especially for graphs enriched with information on edges (direction) and nodes (attributes). In fact, research on link prediction, especially the one based on Graph Deep Learning (GDL), has mostly focused on undirected graphs, without fully leveraging node attributes. Here, we fill this gap by proposing Gravity-GraphSAGE (GG-SAGE), a modified version of GraphSAGE, a GDL model for node embeddings, composed of a gravity-inspired decoder. This implementation is the first example in the literature of a GraphSAGE backbone adopted for directed link prediction. Using the benchmark datasets Cora, Citeseer, PubMed and 16 real-world graphs from the online Netzschleuder repository, we show that our proposed model outperforms state-of-the-art GDL link prediction techniques. Using further experimental evidence, we relate the quality of the output of our model with various characteristics of the graph, suggesting that our framework scales well when applied to data of increasing complexity.

cs.LG↗
arXiv2026

RAwR: Role-Aware Rewiring via Approximate Equitable Partition

While Graph Neural Networks (GNNs) have demonstrated significant efficacy in node classification tasks, where predictions rely on local neighborhood information, the performance of GNNs often drops when prediction tasks depend on long-range interactions. These limitations are attributed to phenomena such as oversquashing, where structural bottlenecks restrict signal propagation across the network topology. To address this challenge, we introduce RAwR, a computationally efficient rewiring framework that augments the input graph with a quotient graph derived from equitable partitions. This approach facilitates accelerated communication between nodes that share identical structural roles, as identified by the Weisfeiler-Leman graph coloring, and thereby reduces the total effective resistance of the system. Furthermore, by employing an approximate definition of the equitable partition, RAwR enables a controllable reduction of the quotient graph, which, in its most condensed state, recovers the conventional Master Node rewiring technique. Empirical evaluations across a diverse suite of benchmarks -- including homophilic, heterophilic, and synthetic long-range datasets -- demonstrate that RAwR achieves state-of-the-art results. Our contribution is further supported by an analytical investigation using a teacher-student model of linear GNNs, which elucidates the theoretical foundations of role-based rewiring. This analysis leads to the formulation of Spectral Role Lift (SRL), a metric designed to identify the optimal approximate equitable partition for maximizing predictive performance.

cs.LG↗
arXiv2026

Constrained Quantum Optimization meets Model Reduction

Quantum optimization algorithms promise advantages for difficult problems but are costly to simulate and analyze on classical machines. Recently, constrained quantum optimization has been investigated through the lens of Quantum Zeno dynamics, an approach which constrains the search to a subspace by means of quantum measurements. Exploiting that quantum measurements are projections, we propose a model reduction approach and show that simulations can be conducted in a lower-dimensional space. As possible applications, we demonstrate exponential state-space reduction of constrained quantum optimization in case of random 3-SAT and agent coordination problems over graphs.

quant-ph↗
arXiv2026

Statistical Model Checking of the Island Model: An Established Economic Agent-Based Model of Endogenous Growth

Agent-based models (ABMs) are increasingly used to study complex economic phenomena such as endogenous growth, but their analysis typically relies on ad-hoc Monte Carlo exercises without formal statistical guarantees. We show how statistical model checking (SMC), and in particular Multi-VeStA, can automate and enrich the analysis of a seminal ABM: the Island Model of Fagiolo and Dosi, which captures the exploration-exploitation trade-off in technological search. We reproduce key stylized facts from the original model with formal confidence intervals, confirm the optimality of moderate exploration rates, and perform a counterfactual sensitivity analysis across returns to scale, skill transfer, and knowledge locality. Using MultiVeStA's built-in Welch's t-test, 6 out of 7 pairwise parameter comparisons yield statistically different growth trajectories, while the exception reveals a saturation effect in knowledge locality. Our results demonstrate that SMC offers a principled, reproducible methodology for the quantitative analysis of agent-based economic models.

cs.MA↗
arXiv2025

Statistical Model Checking of NetLogo Models

Agent-based models (ABMs) are gaining increasing traction in several domains, due to their ability to represent complex systems that are not easily expressible with classical mathematical models. This expressivity and richness come at a cost: ABMs can typically be analyzed only through simulation, making their analysis challenging. Specifically, when studying the output of ABMs, the analyst is often confronted with practical questions such as: (i) how many independent replications should be run? (ii) how many initial time steps should be discarded as a warm-up? (iii) after the warm-up, how long should the model run? (iv) what are the right parameter values? Analysts usually resort to rules of thumb and experimentation, which lack statistical rigor. This is mainly because addressing these points takes time, and analysts prefer to spend their limited time improving the model. In this paper, we propose a methodology, drawing on the field of Statistical Model Checking, to automate the process and provide guarantees of statistical rigor for ABMs written in NetLogo, one of the most popular ABM platforms. We discuss MultiVeStA, a tool that dramatically reduces the time and human intervention needed to run statistically rigorous checks on ABM outputs, and introduce its integration with NetLogo. Using two ABMs from the NetLogo library, we showcase MultiVeStA's analysis capabilities for NetLogo ABMs, as well as a novel application to statistically rigorous calibration. Our tool-chain makes it immediate to perform statistical checks with NetLogo models, promoting more rigorous and reliable analyses of ABM outputs.

cs.MA↗
arXiv2025

The anatomy of Green AI technologies: structure, evolution, and impact

Artificial intelligence (AI) is a key enabler of innovation against climate change. In this study, we investigate the intersection of AI and climate adaptation and mitigation technologies through patent analyses of a novel dataset of approximately 63 000 Green AI patents. We analyze patenting trends, corporate ownership of the technology, the geographical distributions of patents, their impact on follow-on inventions and their market value. We use topic modeling (BERTopic) to identify 16 major technological domains, track their evolution over time, and identify their relative impact. We uncover a clear shift from legacy domains such as combustion engines technology to emerging areas like data processing, microgrids, and agricultural water management. We find evidence of growing concentration in corporate patenting against a rapidly increasing number of patenting firms. Looking at the technological and economic impact of patents, while some Green AI domains combine technological impact and market value, others reflect weaker private incentives for innovation, despite their relevance for climate adaptation and mitigation strategies. This is where policy intervention might be required to foster the generation and use of new Green AI applications.

econ.GN↗
arXiv2025

The ProLiFIC dataset: Leveraging LLMs to Unveil the Italian Lawmaking Process

Process Mining (PM), initially developed for industrial and business contexts, has recently been applied to social systems, including legal ones. However, PM's efficacy in the legal domain is limited by the accessibility and quality of datasets. We introduce ProLiFIC (Procedural Lawmaking Flow in Italian Chambers), a comprehensive event log of the Italian lawmaking process from 1987 to 2022. Created from unstructured data from the Normattiva portal and structured using large language models (LLMs), ProLiFIC aligns with recent efforts in integrating PM with LLMs. We exemplify preliminary analyses and propose ProLiFIC as a benchmark for legal PM, fostering new developments.

cs.CL↗
arXiv2024

Efficient Network Embedding by Approximate Equitable Partitions

Structural network embedding is a crucial step in enabling effective downstream tasks for complex systems that aims to project a network into a lower-dimensional space while preserving similarities among nodes. We introduce a simple and efficient embedding technique based on approximate variants of equitable partitions. The approximation consists in introducing a user-tunable tolerance parameter relaxing the otherwise strict condition for exact equitable partitions that can be hardly found in real-world networks. We exploit a relationship between equitable partitions and equivalence relations for Markov chains and ordinary differential equations to develop a partition refinement algorithm for computing an approximate equitable partition in polynomial time. We compare our method against state-of-the-art embedding techniques on benchmark networks. We report comparable -- when not superior -- performance for visualization, classification, and regression tasks at a cost between one and three orders of magnitude smaller using a prototype implementation, enabling the embedding of large-scale networks which could not be efficiently handled by most of the competing techniques.

cs.SI↗
arXiv2024

Approximate Constrained Lumping of Chemical Reaction Networks

Gaining insights from realistic dynamical models of biochemical systems can be challenging given their large number of state variables. Model reduction techniques can mitigate this by decreasing complexity by mapping the model onto a lower-dimensional state space. Exact constrained lumping identifies reductions as linear combinations of the original state variables in systems of nonlinear ordinary differential equations, preserving specific user-defined output variables without error. However, exact reductions can be too stringent in practice, as model parameters are often uncertain or imprecise -- a particularly relevant problem for biochemical systems. We propose approximate constrained lumping. It allows for a relaxation of exactness within a given tolerance parameter $\varepsilon$, while still working in polynomial time. We prove that the accuracy, i.e., the difference between the output variables in the original and reduced model, is in the order of $\varepsilon$. Furthermore, we provide a heuristic algorithm to find the smallest $\varepsilon$ for a given maximum allowable size of the lumped system. Our method is applied to several models from the literature, resulting in coarser aggregations than exact lumping while still capturing the dynamics of the original system accurately.

cs.CE↗
arXiv2024

Accurate and fast anomaly detection in industrial processes and IoT environments

We present a novel, simple and widely applicable semi-supervised procedure for anomaly detection in industrial and IoT environments, SAnD (Simple Anomaly Detection). SAnD comprises 5 steps, each leveraging well-known statistical tools, namely; smoothing filters, variance inflation factors, the Mahalanobis distance, threshold selection algorithms and feature importance techniques. To our knowledge, SAnD is the first procedure that integrates these tools to identify anomalies and help decipher their putative causes. We show how each step contributes to tackling technical challenges that practitioners face when detecting anomalies in industrial contexts, where signals can be highly multicollinear, have unknown distributions, and intertwine short-lived noise with the long(er)-lived actual anomalies. The development of SAnD was motivated by a concrete case study from our industrial partner, which we use here to show its effectiveness. We also evaluate the performance of SAnD by comparing it with a selection of semi-supervised methods on public datasets from the literature on anomaly detection. We conclude that SAnD is effective, broadly applicable, and outperforms existing approaches in both anomaly detection and runtime.

cs.LG↗
arXiv2024

White-box validation of quantitative product lines by statistical model checking and process mining

We propose a novel methodology for validating software product line (PL) models by integrating Statistical Model Checking (SMC) with Process Mining (PM). Our approach focuses on the feature-oriented language QFLan in the PL engineering domain, allowing modeling of PLs with rich cross-tree and quantitative constraints, as well as aspects of dynamic PLs like staged configurations. This richness leads to models with infinite state-space, requiring simulation-based analysis techniques like SMC. For instance, we illustrate with a running example involving infinite state space. SMC involves generating samples of system dynamics to estimate properties such as event probabilities or expected values. On the other hand, PM uses data-driven techniques on execution logs to identify and reason about the underlying execution process. In this paper, we propose, for the first time, applying PM techniques to SMC simulations' byproducts to enhance the utility of SMC analyses. Typically, when SMC results are unexpected, modelers must determine whether they stem from actual system characteristics or model bugs in a black-box manner. We improve on this by using PM to provide a white-box perspective on the observed system dynamics. Samples from SMC are fed into PM tools, producing a compact graphical representation of observed dynamics. The mined PM model is then transformed into a QFLan model, accessible to PL engineers. Using two well-known PL models, we demonstrate the effectiveness and scalability of our methodology in pinpointing issues and suggesting fixes. Additionally, we show its generality by applying it to the security domain.

cs.SE↗
arXiv2023

Proper Lumping for Positive Bilinear Control Systems

Positive systems naturally arise in situations where the model tracks physical quantities. Although the linear case is well understood, analysis and controller design for nonlinear positive systems remain challenging. Model reduction methods can help tame this problem. Here we propose a notion of model reduction for a class of positive bilinear systems with (bounded) matrix and exogenous controls. Our reduction, called proper positive lumping, aggregates the original system such that states of the corresponding reduced model represent non-negative linear combinations of original state variables. We prove a characterization result showing that the reductions by proper positive lumping are exactly those preserving the optimality of a suitable class of value functions. Moreover, we provide an efficient polynomial-time algorithm for the computation of the minimal lumping. We numerically evaluate our approach by applying it to a number of benchmark case studies.

math.OC↗
arXiv2023

Coarse-graining Complex Networks for Control Equivalence

The ability to control complex networks is of crucial importance across a wide range of applications in natural and engineering sciences. However, issues of both theoretical and numerical nature introduce fundamental limitations to controlling large-scale networks. In this paper, we cope with this problem by introducing a coarse-graining algorithm. It leads to an aggregated network which satisfies control equivalence, i.e., such that the optimal control values for the original network can be exactly recovered from those of the aggregated one. The algorithm is based on a partition refinement method originally devised for systems of ordinary differential equations, here extended and applied to linear dynamics on complex networks. Using a number of benchmarks from the literature we show considerable reductions across a variety of networks from biology, ecology, engineering, and social sciences.

eess.SY↗
arXiv2023

Automated and Distributed Statistical Analysis of Economic Agent-Based Models

We propose a novel approach to the statistical analysis of stochastic simulation models and, especially, agent-based models (ABMs). Our main goal is to provide fully automated, model-independent and tool-supported techniques and algorithms to inspect simulations and perform counterfactual analysis. Our approach: (i) is easy-to-use by the modeller, (ii) improves reproducibility of results, (iii) optimizes running time given the modeller's machine, (iv) automatically chooses the number of required simulations and simulation steps to reach user-specified statistical confidence, and (v) automates a variety of statistical tests. In particular, our techniques are designed to distinguish the transient dynamics of the model from its steady-state behaviour (if any), estimate properties in both 'phases', and provide indications on the (non-)ergodic nature of the simulated processes - which, in turn, allows one to gauge the reliability of a steady-state analysis. Estimates are equipped with statistical guarantees, allowing for robust comparisons across computational experiments. To demonstrate the effectiveness of our approach, we apply it to two models from the literature: a large-scale macro-financial ABM and a small scale prediction market model. Compared to prior analyses of these models, we obtain new insights and we are able to identify and fix some erroneous conclusions.

econ.GN↗