Delays in air transport can be seen as the result of two independent contributions, respectively stemming from the local dynamics of each airport and from a global propagation process; yet, assessing the relative importance of these two aspects in the final behaviour of the system is a challenging task. We here propose the use of the score obtained in a classification task, performed over vectors representing the profiles of delays at each airport, as a way of assessing their identifiability. We show how Deep Learning models are able to recognise airports with high precision, thus suggesting that delays are defined more by the characteristics of each airport than by the global network effects. This identifiability is higher for large and highly connected airports, constant through years, but modulated by season and geographical location. We finally discuss some operational implications of this approach.

Network-based representations have introduced a revolution in neuroscience, expanding the understanding of the brain from the activity of individual regions to the interactions between them. This augmented network view comes at the cost of high dimensionality, which hinders both our capacity of deciphering the main mechanisms behind pathologies, and the significance of any statistical and/or machine learning task used in processing this data. A link selection method, allowing to remove irrelevant connections in a given scenario, is an obvious solution that provides improved utilization of these network representations. In this contribution we review a large set of statistical and machine learning link selection methods and evaluate them on real brain functional networks. Results indicate that most methods perform in a qualitatively similar way, with NBS (Network Based Statistics) winning in terms of quantity of retained information, AnovaNet in terms of stability and ExT (Extra Trees) in terms of lower computational cost. While machine learning methods are conceptually more complex than statistical ones, they do not yield a clear advantage. At the same time, the high heterogeneity in the set of links retained by each method suggests that they are offering complementary views to the data. The implications of these results in neuroscience tasks are finally discussed.

Experimental ADMET profiling is essential to drug discovery but incredibly costly that only a fraction of candidate molecules can be measured, motivating active learning to prioritize informative compounds. However, evidence remains limited on how acquisition strategies and uncertainty estimators interact across different ADMET tasks. Thus, we present a protocol-matched benchmark of seven acquisition strategies and two uncertainty approaches (Deep Ensembles and MC Dropout) across eight ADMET regression endpoints. Our framework combines molecular prediction, uncertainty estimation, batch aquisition and empirically calibrated prediction intervals, with a strict chemotype split to evaluate generalization to held-out chemical groups. The results reveal that active-learning benefits were endpointand strategy-dependent, with the broadest favorable pattern observed for solubility and diversity-aware approaches showing the most consistently favorable behavior across endpoints. Deep Ensembles achieved lower mean RMSE than MC Dropout in 45 of 56 matched comparisons, although this predictive advantage did not consistently translate into better acquisition. Post-hoc analyses associated this disconnect with weak uncertainty-error alignment and reduced chemotype coverage in selected batches. This bench-mark offers a reproducible basis for choosing endpoint-specific acquisition strategies, assessing prediction quality alongside computational cost, and designing prospective studies with matched random controls.