Valerio Siniscalco

About

Most recently I spent seven months at the Centre for Mind/Brain Sciences in Trento, supervised by Prof. Uri Hasson, working on topographic regularisation in convolutional networks. Before that, for my BSc thesis at ITU Copenhagen’s NERDS Lab, supervised by Prof. Michele Coscia, I studied representational bias in Wikipedia’s biography network. The dataset it produced is published on Zenodo and is the primary case study for a paper accepted at CIKM 2026.

I have a BSc in Computer Science from the University of Milan and have started an MSc in IT and Cognition at the University of Copenhagen, where I am now based, with coursework in applied machine learning, natural language processing, computer vision, and cognitive science.

Publications

• Multilayer Network Backboning Valerio Siniscalco and Michele Coscia, CIKM 2026 A method paper that extends network backboning to multilayer networks. The multilingual Wikipedia biography network from my BSc thesis is its primary case study.

Projects

• Topographic Neural Ensembles Topographic regularisation experiments at CIMeC, covering seeded model training, ensembling, and the representational analyses. Run through a Hydra and MLflow pipeline that is declarative and reproducible locally and on a cloud GPU, with artifacts in S3 storage.
• Wikipedia Network Backboning Builds the multilayer Wikipedia biography network from the Cross-Verified Database of Notable People, with edge weights from entity-linking-based mention detection in body text.
• Multilingual Mention-Weighted Network of Wikipedia Biographies DOI: 10.5281/zenodo.20247945 The dataset built by the pipeline above, a directed multilayer network of Wikipedia biographies in five languages, aligned across editions by Wikidata ID.

Timeline

1. 2026 –
   MSc, IT and Cognition current University of Copenhagen, Faculty of Humanities Applied machine learning, language technology, and computer vision coursework, covering the technologies behind large language models alongside cognitive science.
2. Jan – Jul 2026
   Research Intern Centre for Mind/Brain Sciences (CIMeC), University of Trento, supervised by Prof. Uri Hasson Topographic regularisation in convolutional networks, implemented in PyTorch. The models were trained as full ensembles and as adapters on a frozen backbone, then studied with representational similarity analysis, calibration metrics, and robustness tests against input corruption and adversarial attacks.
3. Sep – Dec 2025
   Research Intern Networks, Data, and Society (NERDS) Lab, IT University of Copenhagen, supervised by Prof. Michele Coscia BSc thesis, supported by the Danish Data Science Academy. An NLP and network-science pipeline built end to end, from entity linking to statistical backboning over millions of edges, measuring how biographical connectivity across five Wikipedia language editions differs by gender, origin, and era.
4. 2025 – 2026
   Co-Founder, Polyneta Smart-cities startup, Milan Privacy-preserving machine learning and NLP prototypes for municipal data analysis, and winner of the University Startup Challenge.
5. 2022 – 2026
   BSc, Computer Science Università degli Studi di Milano 110/110 cum laude. Thesis: Representational Bias on Wikipedia: A Multilingual, Multi-Attribute Network Analysis, written at ITU Copenhagen’s NERDS Lab.

Music and books I like

• Time Out (1959), The Dave Brubeck Quartet
• 30 νυχτερινά (1983), Μάνος Χατζιδάκις
• L’isola del giorno prima (1994), Umberto Eco
• La gatta Cenerentola (1976), Nuova Compagnia di Canto Popolare
• Quaglia Sovversiva (2025), Marco Castello
• Three Men in a Boat (1889), Jerome K. Jerome
• Tino’s Breaks, Volumes 1 & 2 (2001), Tino
• Some Prefer Nettles (1929), Jun’ichirō Tanizaki
• Samba esquema novo (1963), Jorge Ben