SEBD 2025
Symposium on Advanced Database Systems 2025

Table of Contents

• Preface
  Summary: There were 58 peer-reviewed papers. Additionally, 8 papers were accepted to be presented at the Doctoral Consortium and 7 papers were presented as a poster presentation.

Keynotes

• A Theory of Regular Queries - Abstract 1–1
  Moshe Y. Vardi
• Local Consistency vs. Global Consistency on Annotated Data - Abstract 2–2
  Phokion G. Kolaitis
• SQL and Large Language Models: A Marriage Made in Heaven? - Abstract 3–3
  Paolo Papotti

Session 1: Privacy and Security

• Privacy of Textual Data: The pyPANTERA Package 4–14
  Francesco Luigi De Faveri, Guglielmo Faggioli, Nicola Ferro
• QuIPU: Evaluating Actual Privacy of Obfuscated Queries 15–26
  Francesco Luigi De Faveri, Guglielmo Faggioli, Nicola Ferro
• Password Strength Analysis Through Social Network Data Exposure: A Combined Approach Relying on Data Reconstruction and Generative Models 27–35
  Maurizio Atzori, Eleonora Calò, Loredana Caruccio, Stefano Cirillo, Giuseppe Polese, Giandomenico Solimando
• Privacy-Preserving Identity Management in Cloud Environments via SOLID 36–46
  Alfredo Cuzzocrea, Islam Belmerabet, Ismail Benlaredj

Session 2: Knowledge Representation

• On Equality Constraints in Datalog+/- Knowledge Bases 47–55
  Andrea Calì, Marco Console, Riccardo Frosini
• Data Augmentation for Data-Centric AI Through the Lens of Semantic Technologies: A Position Paper 56–66
  Daniele Bertillo, Luca Cabibbo, Gianluca Cima, Valter Crescenzi, Marco Console, Roberto Maria Delfino, Stefano Iannucci, Domenico Lembo, Maurizio Lenzerini, Lorenzo Marconi, Paolo Merialdo, Marco Napoleone, Laura Papi, Antonella Poggi, Federico Maria Scafoglieri, Riccardo Torlone
• Semantic Containment in MLMs: A Prompt-Based Approach 67–79
  Vito Walter Anelli, Alessandro De Bellis, Tommaso Di Noia, Eugenio Di Sciascio
• Enhancing Data Management and Value Creation through a Knowledge-centric Data Stack 80–94
  Enrico Franconi, Théo Abgrall
• Towards Leveraging Link Prediction for Geospatial Data Integration 95–104
  Albulen Pano, Mattia Fumagalli, Davide Lanti, Diego Calvanese
• MARTIALIS: An Open Framework for Knowledge Graphs-based Retrieval Augmented Generation 105–114
  Edoardo Bianchini, Filippo Bianchini, Marco Calamo, Francesca De luzi, Mattia Macrì, Massimo Mecella,
• The Vadalog Parallel System: Distributed Reasoning with Datalog+/- (extended abstract) 115–128
  Luigi Bellomarini, Davide Benedetto, Matteo Brandetti, Emanuel Sallinger, Adriano Vlad

Session 3: Social Networks, Data Mining and Information Retrieval

• Relevant, yet Hard to Find: Directional Queries to the Rescue 129–138
  Paolo Ciaccia, Davide Martinenghi
• Benchmarking Active Learning Techniques: Insights from Multi-Domain Fake News Detection 139–154
  Sergio Flesca, Marco Gagliardi, Danilo Maurmo, Francesco Scala, Eugenio Vocaturo
• Analyzing the dynamics of user influence in Threads 155–164
  Gianluca Bonifazi, Christopher Buratti, Enrico Corradini, Michele Marchetti, Federica Parlapiano, Davide Traini, Domenico Ursino, Luca Virgili
• Joint Information Retrieval and Recommendation: a Reproducibility Study 165–175
  Simone Merlo, Guglielmo Faggioli, Nicola Ferro
• Integrating Semantic, Social, and Spatial Dimensions for Inductive Malicious User Detection in Social Networks 176–184
  Francesco Benedetti, Antonio Pellicani, Gianvito Pio, Michelangelo Ceci
• A Dimension Importance Estimation-based Framework for Query Performance Prediction 185–195
  Guglielmo Faggioli, Nicola Ferro, Raffaele Perego, Nicola Tonellotto
• Concept Drift Detection in Machine Learning Systems by Exploiting Relaxed Functional Dependencies 196–205
  Loredana Caruccio, Stefano Cirillo, Giuseppe Polese, Roberto Stanzione
• Discovering Balance-Aware Polarized Communities in Signed Networks with Graph Neural Networks 206–216
  Francesco Gullo, Domenico Mandaglio, Andrea Tagarelli

Session 4: Cloud and IoT

• Design of Cloud Data Platforms 217–228
  Alex Baiardi, Matteo Francia, Enrico Gallinucci, Matteo Golfarelli, Manuele Pasini
• A Unified Framework for Human Activity Recognition Data Preprocessing 229–237
  Sara Comai, Davide Mangano, Kévin Bouchard, Fabio Salice
• {A Process-Aware Model for Industrial IoT Integration and Analytics based on Knowledge Graphs 238–246
  Claudia Diamantini, Alex Mircoli, Domenico Potena, Emanuele Storti
• Towards Bringing Human-Like Intelligence in the Computing Continuum: the INTEND Project 247–255
  Lorenzo Balzotti, Donatella Firmani, Francesco Leotta, Jerin George Mathew, Jacopo Rossi
• Leveraging LLMs and RAG for Data Service Discovery in the Internet of Production 256–263
  Devis Bianchini, Valeria De Antonellis, Massimiliano Garda, Michele Melchiori, Anisa Rula
• LLM-Based Composition of Smart Data Services in Shop Floors 264–273
  Adriano Izzi, Jerin George Mathew, Flavia Monti, Donatella Firmani, Francesco Leotta, Federica Mandreoli, Massimo Mecella
• A Framework for Enhanced Decision-Making Support in Production Planning through Event Data Analysis 274–283
  Simone Agostinelli, Dario Benvenuti, Angelo Casciani, Francesca De Luzi, Matteo Marinacci, Andrea Marrella, Jacopo Rossi
• Supporting Multidimensional Risk Analysis and Mining over Big Digital Twins: An Effective and Efficient Framework 284–299
  Alfredo Cuzzocrea, Ismail Benlaredj

Session 5: Data-Driven Decision Making

• AI–Driven Clinical Reporting: A Case Study on IQLINIQ 300–316
  Seyedeh Leili Mirtaheri, Reza Shahbazian, Narges Movahedkor, Irina Trubitsyna, Sergio Greco
• Comparative Conflict Analysis between Autonomous and Human-Operated Vehicles with Pedestrians at Unsignalized Crosswalks 317–326
  Andrea Avignone, Marco Bassani, Beatrice Borgogno, Brunella Caroleo, Silvia Chiusano, Federico Princiotto
• Processing and Representation of Linguistic Properties in Large Language Models 327–336
  Elisabetta Rocchetti, Alfio Ferrara
• Analyzing Common Student Errors in SQL Query Formulation to Enhance Learning Support 337–345
  Davide Ponzini, Abdolhamid Livani, Giovanna Guerrini, Barbara Catania, Mauro Coccoli
• Legal Document Query Language: Conceptualizing Linguistic Commands for AI Assistants in Civil Appeal Proceedings 346–359
  Ruben Agazzi, Carlo Batini, Matteo Palmonari, Monica Vitali

Session 6: Data Quality, Curation and Fairness

• Binomial Confidence Intervals for Knowledge Graph Accuracy Estimation (Extended Abstract) 360–369
  Stefano Marchesin, Gianmaria Silvello
• BUNNI: Discover Repair Actions for Data Cleaning 370–381
  Giansalvatore Mecca, Paolo Papotti, Donatello Santoro, Enzo Veltri
• PuckTrick: A Library for Making Synthetic Data More Realistic 382–398
  Alessandra Agostini, Andrea Maurino, Blerina Spahiu
• On Measuring Inconsistency in Graph Databases 399–410
  John Grant, Francesco Parisi
• Analysing the Impact of Data Distribution Shifts on Model Fairness in Machine Learning 411–422
  Federico Motta, Yijie Li, Huiping Chen, Federica Mandreoli, Paolo Missier
• S-PIC4CHU: Semantics-based Provenance, Integrity, and Curation for Consistent, High-quality, and Unbiased Data Science 423–433
  Gianvincenzo Alfano, Ilaria Bartolini, Diego Calvanese, Paolo Ciaccia, Sergio Greco, Davide Lanti, Emilia Lenzi, Davide Martinenghi, Cristian Molinaro, Marco Patella, Letizia Tanca, Riccardo Torlone, Irina Trubitsyna
• Divergence-aware Approaches to Mitigate Subgroup Disparities in Speech Models 434–445
  Alkis Koudounas, Eliana Pastor, Flavio Giobergia, Elena Baralis,
• An Associative Approach to Fair Co-clustering 446–454
  Federico Peiretti, Ruggero Pensa

Session 7: Applications

• Extraction and Investigation of Power Neurons in the Caenorhabditis elegans Connectome 455–469
  Christopher Buratti, Michele Marchetti, Federica Parlapiano, Giorgio Terracina, Domenico Ursino
• A Deep Learning-Based Framework for Stock Analysis 470–477
  Fausto Ricchiuti, Giancarlo Sperlì
• Optimizing Defect Detection: A Machine Learning-Ready Data Processing Pipeline 478–486
  Loredana Cristaldi, Emilia Lenzi, Davide Martinenghi, Luca Martiri, Andrea Moschetti, Letizia Tanca, Marco Zanoni
• The Role of Artificial Intelligence in ESG Ranking Evaluation 487–494
  Simona Fioretto, Enea Vincenzo Napolitano, Elio Masciari
• Metadata as a Key Driver in Healthcare Data Analysis 495–505
  Chiara Criscuolo, Davide Piantella, Pierluigi Reali, Maria Gabriella Signorini, Letizia Tanca
• A Digital Forensics Approach for Validating Screen Captures in Legal Proceedings 506–515
  Claudia Greco, Michele Ianni, Antonella Guzzo, Giancarlo Fortino
• Leveraging Ontologies to Enhance Personalised and Sustainable Food Recommendations with LLMs 516–524
  Ada Bagozi, Devis Bianchini, Michele Melchiori, Anisa Rula
• MiCare: An IoT-Based System for Real-Time Mental Health Monitoring and Early Disease Detection 525–540
  Marco Cremaschi, Sara Nocco, Alessandra Agostini, Andrea Maurino

Session 8: Interpretable Data-centric AI

• Explanations for Negative Query Answers under Inconsistency-Tolerant Semantics 541–550
  Thomas Lukasiewicz, Enrico Malizia, Cristian Molinaro
• Using Heterogeneous Graph Neural Networks for Explainable Next-Activity Prediction 551–559
  Vincenzo Pasquadibisceglie, Raffaele Scaringi, Annalisa Appice, Giovanna Castellano, Donato Malerba
• From XAI to XEE: eXplainable End-to-End using Influence and Provenance 560–569
  Paolo Missier, Riccardo Torlone, Pasquale Leonardo Lazzaro, Luca Gregori, Clyde Fernandes, Tianyang Xie
• Explaining Entity Matching Models with CREW 570–579
  Riccardo Benassi, Michele Luca Contalbo, Francesco Del Buono, Francesco Guerra, Giacomo Guiduzzi, Matteo Paganelli, Sara Pederzoli, Donato Tiano, Maurizio Vincini
• Supporting the Analysis and Explanation of Dependencies through an LLM-Powered Tool 580–593
  Loredana Caruccio, Tullio Pizzuti, Giuseppe Polese

Session 9: Natural Language and Text Processing

• JusBuild: a RAG-based Architecture for Legal Document Building - Discussion paper 594–603
  Silvana Castano, Alfio Ferrara, Stefano Montanelli, Sergio Picascia, Davide Riva
• Managing Legal Data: A Framework for Document Annotation and Retrieval 604–614
  Valerio Bellandi, Stefano Siccardi
• In-Context LLM Query Execution on Textual Documents 615–625
  Dario Satriani, Enzo Veltri, Donatello Santoro, Paolo Papotti
• WhosAI: A Contrastive Learning Framework for Machine-Generated Text Detection and Attribution 626–636
  Lucio La Cava, Andrea Tagarelli
• Text-to-Refused-SQL: A Comprehensive Evaluation of LLMs Refusal in Text-to-SQL 637–651
  Giovanni Sullutrone, Luca Sala, Lisa Trigiante, Sonia Bergamaschi

Doctoral Consortium

• A Symbolic/Sub-Symbolic-Based Framework for Indicators Management 652–658
  Cristina Rossetti
• Preserving Privacy When Processing User Queries in IR 659–666
  Francesco Luigi De Faveri
• Towards Joint Information Retrieval and Recommender Systems 667–674
  Simone Merlo
• Design and Development of a Polystore System for Heterogeneous Biomedical Data 675–681
  Mirco Cazzaro
• Advancing Cross-Document Relation Extraction with Hybrid Retrieval and Knowledge-Augmented Reasoning 682–688
  Marco Martinelli
• Towards the Definition of a Unified Metamodeling Semantics for Knowledge Graphs 689–694
  Roberto Maria Delfino
• Semantic Explanations and Reasoning for Machine Learning Models: An Ontology-Based Approach 695–700
  Laura Papi
• Querying OpenEO Datacubes through Virtual Knowledge Graphs 701–707
  Albulen Pano

Research Projects Exhibition

• Research Project Exhibition Track SEBD 2025 708–724
  Francesca De Luzi, Flavia Monti, Massimo Mecella