Politecnico di Milano

Clinical usability of an explainable AI decision support tool and evaluation of multimodal models in NSCLC

Abstract Despite a decade in, immunotherapy (IO) treatment selection in non-small cell lung cancer (NSCLC) remains largely guided by subgroup analyses and imperfect programmed death ligand 1 (PD-L1) and clinical scores. To our knowledge, I 3 LUNG ( NCT05537922 ) is currently the...

Combined Experimental and Theoretical Study on Neopentanol Pyrolysis

Abstract The multi-channel, unimolecular dissociation of neopentanol at high temperatures was studied by three experimental methods and a complementary high-level theoretical analysis. In addition to bond dissociation channels leading to radical products, two roaming radical chan...

Crushing of carbon-fiber reinforced thermoplastic energy absorbers under axial impact: Numerical modeling and experimental tests

This study presents a numerical and experimental investigation aimed at assessing the impact behavior, energy absorption characteristics, and failure modes of thermoplastic composite energy absorbers subjected to axial impact loads. The energy absorbers consist of thin-walled cyl...

A multi-level framework for capacity adjustment and flexible decision-making under data constraints in production planning and control

Abstract Capacity adjustment (CA) remains a persistent challenge in production planning and control (PPC), especially in workload-controlled environments where firms must regulate effective capacity through labor, machine, material, and inventory interventions. Analytical approac...

A quantitative framework for ultrafast ptychography through digital twin control of extreme-ultraviolet beams

Ptychography is a powerful imaging method that has transformed microscopy at large-scale and laboratory facilities. Its combination with extreme-ultraviolet light has enabled tabletop microscopes that visualize nanoscale dynamics and characterize ultrafast pulses. However, the pe...

How External Regulations Influence ESG Integration in Construction Firms: A Managerial Cognition Perspective

Abstract Limited understanding of how external regulations influence construction firms’ environmental, social, and governance (ESG) integration constrains policy effectiveness and industry sustainability performance. Drawing on neo-institutional theory and managerial cognition (...

Physics-guided CNN surrogate model of viscoelastic dampers and its application in structural seismic control

Accurate characterization of the time-domain nonlinear mechanical behavior of viscoelastic dampers (VEDs) remains challenging. Traditional frequency-domain models cannot simultaneously consider loading history, strain amplitude, and ambient temperature, whereas high-fidelity time...

Cultural participation as an indicator of local government performance: evidence from Italian municipalities

Abstract This paper investigates whether cultural participation can be interpreted as an outcome-based indicator of local government efficiency in the cultural policy domain. Rather than focusing solely on budgetary effort, the study examines the extent to which municipal cultura...

What does the correlation between the anthropomorphisation of technologies and the automation of humans mean?

Abstract In recent years, the phenomenon of anthropomorphisation of technologies, especially artificial intelligence, has been extensively studied. The reciprocal phenomenon, which may be defined as the automation of humans, has been studied less extensively. And the correlation...

Existence and Uniqueness Results for a Mean-Field Game of Optimal Investment

Abstract We establish the existence and uniqueness of the equilibrium for a stochastic mean-field game of optimal investment. The analysis covers both finite and infinite time horizons, and the mean-field interaction of the representative company with a mass of identical and indi...

Geometric and topological deep learning for predicting thermo-mechanical performance in cold spray deposition process modeling

This study presents a geometric deep learning framework for predicting cold spray particle impact responses using finite element simulation data. A parametric dataset was generated through automated Abaqus simulations spanning a systematic range of particle velocity, particle tem...

Who Are You Hanging Out With? The Conditional Importance of Investment Managers’ Personal Reputation in the Formation of Venture Capital Syndication Ties

Abstract We examine how the two dimensions of VC managers' personal reputation, that is, ‘being known’ and ‘being known for quality’, jointly influence the formation of initial syndication ties. We propose that VC managers follow a two‐stage cognitive process. In the first stage,...

Sustainable logistics and supply chain performance with human–machine collaboration in the context of Industry 5.0: a holistic structural model analysis

Purpose This study aims to examine the relationships between human–machine collaboration (HMC), operational efficiency (OE), resource efficiency (RE), workforce capability (WC), and sustainable logistics and supply chain performance (SLSCP) within the context of Industry 5.0. The...

Invited perspectives: Towards usable compound event research

Abstract. Supporting stakeholders with science-based decision-making to mitigate and adapt to climate change impacts is a central mandate of the climate research community. In particular, mapping out scenario-dependent climate risk landscapes is one of the most pressing challenge...

Hyperelastic constitutive model discovery with differentiable finite elements and structure-preserving neural networks

Abstract The discovery of constitutive laws from experimentally accessible measurements is a central problem in nonlinear computational mechanics. Many data-driven constitutive identification approaches rely either on paired strain–stress data or on full-field displacement measur...

Responsibility and planning amid growing urban complexity and AI proliferation: many hands, many things, many tasks

Abstract This paper focuses on issues pertaining to the risks and responsibilities associated with growing complexity and the spread of AI technologies in the urban context. Arguing that such risks are often systemic, it analyses three structural responsibility problems, each lin...

A risk science perspective on inductive risk

Abstract The concept of inductive risk—commonly understood as the possibility of error in accepting or rejecting a scientific hypothesis—has been a topic of discussion in the philosophy of science since the 1950s. The primary focus has been on its implications for the legitimacy...

Proportional infinite-width infinite-depth limit for deep linear neural networks

In this paper, we study the distributional properties of linear neural networks with random parameters in the context of large networks, where the number of layers diverges in proportion to the number of neurons per layer. Prior works have shown that in the infinite-width regime,...

Fostering Circularity in the Stone Industry: Multi-Criteria Analysis of Existing Sustainable Indicators for Decision-Making Support

The stone industry generates substantial waste along the quarrying, cutting and finishing chain, with only about 22% of the extracted material processed into final products, while roughly 64% is lost as slurry and 8% as solid waste. Compared to other industries such as wood and s...

Image-based estimation of ambient particulate matter: a scoping review

Abstract Air quality is a major public health concern, while particulate matter (PM) measurements remain limited by the spatial coverage and high operational costs of reference monitoring stations. This scoping review synthesises the literature on image-based PM estimation from o...