Francesca Cairoli
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Francesca Cairoli has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Luca Bortolussi
University of Trieste
8 shared publications - Nicola Paoletti
King’s College London
5 shared publications Luca Bortolussi
3 shared publicationsJyotirmoy V. Deshmukh
University of Southern California
2 shared publicationsLars Lindemann
University of Southern California
2 shared publicationsNicola Paoletti
2 shared publications
Latest Publications
- 12 September 2025
- Published by Springer Nature
- p. 336-356
Conformal Predictive Monitoring for Multi-modal Scenarios
- 12 September 2025
- Published by Springer Nature
- p. 336-356
Conformal Predictive Monitoring for Multi-modal Scenarios
- 12 September 2025
- Published by Springer Nature
- p. 296-316
CoCAI: Copula-Based Conformal Anomaly Identification for Multivariate Time-Series
- 12 September 2025
- Published by Springer Nature
- p. 296-316
CoCAI: Copula-Based Conformal Anomaly Identification for Multivariate Time-Series
- Open Access
Conformal Predictive Monitoring for Multi-Modal Scenarios
We consider the problem of quantitative predictive monitoring (QPM) of stochastic systems, i.e., predicting at runtime the degree of satisfaction of a desired temporal logic property from the current state of the system. Since computational efficiency is key to enable timely intervention against predicted violations, several state-of-the-art QPM approaches rely on fast machine-learning surrogates to provide prediction intervals for the satisfaction values, using conformal inference to offer statistical guarantees. However, these QPM methods suffer when the monitored agent exhibits multi-modal dynamics, whereby certain modes may yield high satisfaction values while others critically violate the property. Existing QPM methods are mode-agnostic and so would yield overly conservative and uninformative intervals that lack meaningful mode-specific satisfaction information. To address this problem, we present GenQPM, a method that leverages deep generative models, specifically score-based diffusion models, to reliably approximate the probabilistic and multi-modal system dynamics without requiring explicit model access. GenQPM employs a mode classifier to partition the predicted trajectories by dynamical mode. For each mode, we then apply conformal inference to produce statistically valid, mode-specific prediction intervals. We demonstrate the effectiveness of GenQPM on a benchmark of agent navigation and autonomous driving tasks, resulting in prediction intervals that are significantly more informative (less conservative) than mode-agnostic baselines.
Open AccessConformal Predictive Monitoring for Multi-Modal Scenarios
We consider the problem of quantitative predictive monitoring (QPM) of stochastic systems, i.e., predicting at runtime the degree of satisfaction of a desired temporal logic property from the current state of the system. Since computational efficiency is key to enable timely intervention against predicted violations, several state-of-the-art QPM approaches rely on fast machine-learning surrogates to provide prediction intervals for the satisfaction values, using conformal inference to offer statistical guarantees. However, these QPM methods suffer when the monitored agent exhibits multi-modal dynamics, whereby certain modes may yield high satisfaction values while others critically violate the property. Existing QPM methods are mode-agnostic and so would yield overly conservative and uninformative intervals that lack meaningful mode-specific satisfaction information. To address this problem, we present GenQPM, a method that leverages deep generative models, specifically score-based diffusion models, to reliably approximate the probabilistic and multi-modal system dynamics without requiring explicit model access. GenQPM employs a mode classifier to partition the predicted trajectories by dynamical mode. For each mode, we then apply conformal inference to produce statistically valid, mode-specific prediction intervals. We demonstrate the effectiveness of GenQPM on a benchmark of agent navigation and autonomous driving tasks, resulting in prediction intervals that are significantly more informative (less conservative) than mode-agnostic baselines.
- Open Access
- 14 May 2025
- Published by Elsevier in Nonlinear Analysis: Hybrid Systems
- Vol. 57
Conformal quantitative predictive monitoring of stochastic systems with conditional validity
- 14 May 2025
- Published by Elsevier in Nonlinear Analysis: Hybrid Systems
- Vol. 57
Open AccessConformal quantitative predictive monitoring of stochastic systems with conditional validity
- 21 April 2025
- Published by Taylor & Francis in International Journal of Systems Science
- Vol. 57 (1) , 77-105
Scalable and reliable stochastic parametric verification with stochastic variational smoothed model checking
- 21 April 2025
- Published by Taylor & Francis in International Journal of Systems Science
- Vol. 57 (1) , 77-105
Scalable and reliable stochastic parametric verification with stochastic variational smoothed model checking
- Open Access
Certified Guidance for Planning with Deep Generative Models
Deep generative models, such as generative adversarial networks and diffusion models, have recently emerged as powerful tools for planning tasks and behavior synthesis in autonomous systems. Various guidance strategies have been introduced to steer the generative process toward outputs that are more likely to satisfy the planning objectives. These strategies avoid the need for model retraining but do not provide any guarantee that the generated outputs will satisfy the desired planning objectives. To address this limitation, we introduce certified guidance, an approach that modifies a generative model, without retraining it, into a new model guaranteed to satisfy a given specification with probability one. We focus on Signal Temporal Logic specifications, which are rich enough to describe nontrivial planning tasks. Our approach leverages neural network verification techniques to systematically explore the latent spaces of the generative models, identifying latent regions that are certifiably correct with respect to the STL property of interest. We evaluate the effectiveness of our method on four planning benchmarks using GANs and diffusion models. Our results confirm that certified guidance produces generative models that are always correct, unlike existing guidance methods that are not certified.
Open AccessCertified Guidance for Planning with Deep Generative Models
Deep generative models, such as generative adversarial networks and diffusion models, have recently emerged as powerful tools for planning tasks and behavior synthesis in autonomous systems. Various guidance strategies have been introduced to steer the generative process toward outputs that are more likely to satisfy the planning objectives. These strategies avoid the need for model retraining but do not provide any guarantee that the generated outputs will satisfy the desired planning objectives. To address this limitation, we introduce certified guidance, an approach that modifies a generative model, without retraining it, into a new model guaranteed to satisfy a given specification with probability one. We focus on Signal Temporal Logic specifications, which are rich enough to describe nontrivial planning tasks. Our approach leverages neural network verification techniques to systematically explore the latent spaces of the generative models, identifying latent regions that are certifiably correct with respect to the STL property of interest. We evaluate the effectiveness of our method on four planning benchmarks using GANs and diffusion models. Our results confirm that certified guidance produces generative models that are always correct, unlike existing guidance methods that are not certified.
- Open Access
Learning-Based Approaches to Predictive Monitoring with Conformal Statistical Guarantees
This tutorial focuses on efficient methods to predictive monitoring (PM), the problem of detecting at runtime future violations of a given requirement from the current state of a system. While performing model checking at runtime would offer a precise solution to the PM problem, it is generally computationally expensive. To address this scalability issue, several lightweight approaches based on machine learning have recently been proposed. These approaches work by learning an approximate yet efficient surrogate (deep learning) model of the expensive model checker. A key challenge remains to ensure reliable predictions, especially in safety-critical applications. We review our recent work on predictive monitoring, one of the first to propose learning-based approximations for CPS verification of temporal logic specifications and the first in this context to apply conformal prediction (CP) for rigorous uncertainty quantification. These CP-based uncertainty estimators offer statistical guarantees regarding the generalization error of the learning model, and they can be used to determine unreliable predictions that should be rejected. In this tutorial, we present a general and comprehensive framework summarizing our approach to the predictive monitoring of CPSs, examining in detail several variants determined by three main dimensions: system dynamics (deterministic, non-deterministic, stochastic), state observability, and semantics of requirements' satisfaction (Boolean or quantitative).
Open AccessLearning-Based Approaches to Predictive Monitoring with Conformal Statistical Guarantees
This tutorial focuses on efficient methods to predictive monitoring (PM), the problem of detecting at runtime future violations of a given requirement from the current state of a system. While performing model checking at runtime would offer a precise solution to the PM problem, it is generally computationally expensive. To address this scalability issue, several lightweight approaches based on machine learning have recently been proposed. These approaches work by learning an approximate yet efficient surrogate (deep learning) model of the expensive model checker. A key challenge remains to ensure reliable predictions, especially in safety-critical applications. We review our recent work on predictive monitoring, one of the first to propose learning-based approximations for CPS verification of temporal logic specifications and the first in this context to apply conformal prediction (CP) for rigorous uncertainty quantification. These CP-based uncertainty estimators offer statistical guarantees regarding the generalization error of the learning model, and they can be used to determine unreliable predictions that should be rejected. In this tutorial, we present a general and comprehensive framework summarizing our approach to the predictive monitoring of CPSs, examining in detail several variants determined by three main dimensions: system dynamics (deterministic, non-deterministic, stochastic), state observability, and semantics of requirements' satisfaction (Boolean or quantitative).
- 1 October 2023
- Published by Springer Nature
- p. 461-487
Learning-Based Approaches to Predictive Monitoring with Conformal Statistical Guarantees
- 1 October 2023
- Published by Springer Nature
- p. 461-487
Learning-Based Approaches to Predictive Monitoring with Conformal Statistical Guarantees
- 1 October 2023
- Published by Springer Nature
- p. 45-65
Scalable Stochastic Parametric Verification with Stochastic Variational Smoothed Model Checking
- 1 October 2023
- Published by Springer Nature
- p. 45-65
Scalable Stochastic Parametric Verification with Stochastic Variational Smoothed Model Checking
- 1 September 2023
- Published by Elsevier in Theoretical Computer Science
- Vol. 977
Generative abstraction of Markov population processes
- 1 September 2023
- Published by Elsevier in Theoretical Computer Science
- Vol. 977
Generative abstraction of Markov population processes