Livio Pompianu

Salvatore Carta, Alessandro Giuliani, Leonardo Piano et al.

In the current digitalization era, capturing and effectively representing knowledge is crucial in most real-world scenarios. In this context, knowledge graphs represent a potent tool for retrieving and organizing a vast amount of information in a properly interconnected and interpretable structure. However, their generation is still challenging and often requires considerable human effort and domain expertise, hampering the scalability and flexibility across different application fields. This paper proposes an innovative knowledge graph generation approach that leverages the potential of the latest generative large language models, such as GPT-3.5, that can address all the main critical issues in knowledge graph building. The approach is conveyed in a pipeline that comprises novel iterative zero-shot and external knowledge-agnostic strategies in the main stages of the generation process. Our unique manifold approach may encompass significant benefits to the scientific community. In particular, the main contribution can be summarized by: (i) an innovative strategy for iteratively prompting large language models to extract relevant components of the final graph; (ii) a zero-shot strategy for each prompt, meaning that there is no need for providing examples for "guiding" the prompt result; (iii) a scalable solution, as the adoption of LLMs avoids the need for any external resources or human expertise. To assess the effectiveness of our proposed model, we performed experiments on a dataset that covered a specific domain. We claim that our proposal is a suitable solution for scalable and versatile knowledge graph construction and may be applied to different and novel contexts.

Massimo Bartoletti, Andrea Bracciali, Stefano Lande et al.

Modern cryptocurrencies exploit decentralised blockchains to record a public and unalterable history of transactions. Besides transactions, further information is stored for different, and often undisclosed, purposes, making the blockchains a rich and increasingly growing source of valuable information, in part of difficult interpretation. Many data analytics have been developed, mostly based on specifically designed and ad-hoc engineered approaches. We propose a general-purpose framework, seamlessly supporting data analytics on both Bitcoin and Ethereum - currently the two most prominent cryptocurrencies. Such a framework allows us to integrate relevant blockchain data with data from other sources, and to organise them in a database, either SQL or NoSQL. Our framework is released as an open-source Scala library. We illustrate the distinguishing features of our approach on a set of significant use cases, which allow us to empirically compare ours to other competing proposals, and evaluate the impact of the database choice on scalability.

Salvatore Mario Carta, Stefano Chessa, Giulia Contu et al.

Minority languages are vital to preserving cultural heritage, yet they face growing risks of extinction due to limited digital resources and the dominance of artificial intelligence models trained on high-resource languages. This white paper proposes a framework to generate linguistic tools for low-resource languages, focusing on data creation to support the development of language models that can aid in preservation efforts. Sardinian, an endangered language, serves as the case study to demonstrate the framework's effectiveness. By addressing the data scarcity that hinders intelligent applications for such languages, we contribute to promoting linguistic diversity and support ongoing efforts in language standardization and revitalization through modern technologies.

Massimo Bartoletti, Enrico Lipparini, Livio Pompianu

Ensuring the correctness of smart contracts is critical, as even subtle flaws can lead to severe financial losses. While bug detection tools able to spot common vulnerability patterns can serve as a first line of defense, most real-world exploits and losses stem from errors in the contract business logic. Formal verification tools such as SolCMC and the Certora Prover address this challenge, but their impact remains limited by steep learning curves and restricted specification languages. Recent works have begun to explore the use of large language models (LLMs) for security-related tasks such as vulnerability detection and test generation. Yet, a fundamental question remains open: can LLMs serve as verification oracles, capable of reasoning about arbitrary contract-specific properties? In this paper, we provide the first systematic evaluation of GPT-5, a state-of-the-art reasoning LLM, in this role. We benchmark its performance on a large dataset of verification tasks, compare its outputs against those of established formal verification tools, and assess its practical effectiveness in real-world auditing scenarios. Our study combines quantitative metrics with qualitative analysis, and shows that recent reasoning-oriented LLMs can be surprisingly effective as verification oracles, suggesting a new frontier in the convergence of AI and formal methods for secure smart contract development and auditing.

Alessia Pisu, Livio Pompianu, Francesco Osborne et al.

Taxonomies and ontologies of research topics (e.g., MeSH, UMLS, CSO, NLM) play a central role in providing the primary framework through which intelligent systems can explore and interpret the literature. However, these resources have traditionally been manually curated, a process that is time-consuming, prone to obsolescence, and limited in granularity. This paper presents Sci-OG, a semi-auto\-mated methodology for generating research topic ontologies, employing a multi-step approach: 1) Topic Discovery, extracting potential topics from research papers; 2) Relationship Classification, determining semantic relationships between topic pairs; and 3) Ontology Construction, refining and organizing topics into a structured ontology. The relationship classification component, which constitutes the core of the system, integrates an encoder-based language model with features describing topic occurrence in the scientific literature. We evaluate this approach against a range of alternative solutions using a dataset of 21,649 manually annotated semantic triples. Our method achieves the highest F1 score (0.951), surpassing various competing approaches, including a fine-tuned SciBERT model and several LLM baselines, such as the fine-tuned GPT4-mini. Our work is corroborated by a use case which illustrates the practical application of our system to extend the CSO ontology in the area of cybersecurity. The presented solution is designed to improve the accessibility, organization, and analysis of scientific knowledge, thereby supporting advancements in AI-enabled literature management and research exploration.

Lodovica Marchesi, Michele Marchesi, Livio Pompianu et al.

In recent years Smart Contracts and DApps are becoming increasingly important and widespread thanks to the properties of blockchain technology. In most cases DApps are business critical, and very strict security requirements should be assured. Developing safe and reliable Smart Contracts, however, is not a trivial task. Several researchers have studied the security issues, however none of these provide a simple and intuitive tool to overcome these problems. In this paper we collected a list of security patterns for DApps. Moreover, based on these patterns, we provide the reader with security assessment checklists that can be easily used for the development of SCs. We cover the phases of design, coding, and testing and deployment of the software lifecycle. In this way, we allow developers to easily verify if they applied all the relevant security patterns to their smart contracts. We focus all the analysis on the most popular Ethereum blockchain, and on the Solidity language.

Massimo Bartoletti, Livio Pompianu

Smart contracts are computer programs that can be consistently executed by a network of mutually distrusting nodes, without the arbitration of a trusted authority. Because of their resilience to tampering, smart contracts are appealing in many scenarios, especially in those which require transfers of money to respect certain agreed rules (like in financial services and in games). Over the last few years many platforms for smart contracts have been proposed, and some of them have been actually implemented and used. We study how the notion of smart contract is interpreted in some of these platforms. Focussing on the two most widespread ones, Bitcoin and Ethereum, we quantify the usage of smart contracts in relation to their application domain. We also analyse the most common programming patterns in Ethereum, where the source code of smart contracts is available.

Massimo Bartoletti, Livio Pompianu

The Bitcoin protocol allows to save arbitrary data on the blockchain through a special instruction of the scripting language, called OP_RETURN. A growing number of protocols exploit this feature to extend the range of applications of the Bitcoin blockchain beyond transfer of currency. A point of debate in the Bitcoin community is whether loading data through OP_RETURN can negatively affect the performance of the Bitcoin network with respect to its primary goal. This paper is an empirical study of the usage of OP_RETURN over the years. We identify several protocols based on OP_RETURN, which we classify by their application domain. We measure the evolution in time of the usage of each protocol, the distribution of OP_RETURN transactions by application domain, and their space consumption.