Rapid post-disaster road damage assessment is critical for effective emergency response, yet traditional optimization methods suffer from excessive computational time and require domain knowledge for algorithm design, making them unsuitable for time-sensitive disaster scenarios. This study proposes an attention-based encoder-decoder model (AEDM) for rapid drone routing decision in post-disaster road damage assessment. The method employs deep reinforcement learning to determine high-quality drone assessment routes without requiring algorithmic design knowledge. A network transformation method is developed to convert link-based routing problems into equivalent node-based formulations, while a synthetic road network generation technique addresses the scarcity of large-scale training datasets. The model is trained using policy optimization with multiple optima (POMO) with multi-task learning capabilities to handle diverse parameter combinations. Experimental results demonstrate two key strengths of AEDM: it outperforms commercial solvers by 20--71\% and traditional heuristics by 23--35\% in solution quality, while achieving rapid inference (1--2 seconds) versus 100--2,000 seconds for traditional methods. The model exhibits strong generalization across varying problem scales, drone numbers, and time constraints, consistently outperforming baseline methods on unseen parameter distributions and real-world road networks. The proposed method effectively balances computational efficiency with solution quality, making it particularly suitable for time-critical disaster response applications where rapid decision-making is essential for saving lives. The source code for AEDM is publicly available at https://github.com/PJ-HTU/AEDM-for-Post-disaster-road-assessment.

Credit risk modeling relies extensively on Weight of Evidence (WoE) and Information Value (IV) for feature engineering, and Population Stability Index (PSI) for drift monitoring, yet their theoretical foundations remain disconnected. We establish a unified information-theoretic framework revealing these industry-standard metrics as instances of classical information divergences. Specifically, we prove that IV exactly equals PSI (Jeffreys divergence) computed between good and bad credit outcomes over identical bins. Through the delta method applied to WoE transformations, we derive standard errors for IV and PSI, enabling formal hypothesis testing and probabilistic fairness constraints for the first time. We formalize credit modeling's inherent performance-fairness trade-off as maximizing IV for predictive power while minimizing IV for protected attributes. Using automated binning with depth-1 XGBoost stumps, we compare three encoding strategies: logistic regression with one-hot encoding, WoE transformation, and constrained XGBoost. All methods achieve comparable predictive performance (AUC 0.82-0.84), demonstrating that principled, information-theoretic binning outweighs encoding choice. Mixed-integer programming traces Pareto-efficient solutions along the performance-fairness frontier with uncertainty quantification. This framework bridges theory and practice, providing the first rigorous statistical foundation for widely-used credit risk metrics while offering principled tools for balancing accuracy and fairness in regulated environments.

In this paper, we present a learning algorithm that achieves asymptotically optimal regret for Markov decision processes in average reward under a communicating assumption. That is, given a communicating Markov decision process $M$, our algorithm has regret $K(M) \log(T) + \mathrm{o}(\log(T))$ where $T$ is the number of learning steps and $K(M)$ is the best possible constant. This algorithm works by explicitly tracking the constant $K(M)$ to learn optimally, then balances the trade-off between exploration (playing sub-optimally to gain information), co-exploration (playing optimally to gain information) and exploitation (playing optimally to score maximally). We further show that the function $K(M)$ is discontinuous, which is a consequence challenge for our approach. To that end, we describe a regularization mechanism to estimate $K(M)$ with arbitrary precision from empirical data.

As the performance of artificial intelligence (AI) models improves, workflows in which human and AI model-based judgments are combined to make decisions are sought in medicine, finance, and other domains. Though statistical models often make more accurate predictions than human experts on average [Ægisdóttir et al., 2006, Grove et al., 2000, Meehl, 1954], whenever humans have access to additional information over the AI, there is potential to achieve complementary performance by pairing the two, i.e., better performance than either the human or AI alone. For example, a physician may have access to additional information that may not be captured in tabular electronic health records or other structured data [Alur et al., 2024b]. However, evidence of complementary performance between humans and AI is limited, with many studies showing that human-AI teams underperform an AI alone [Buçinca et al., 2020, Bussone et al., 2015, Green and Chen, 2019, Jacobs et al., 2021, Lai and Tan, 2019, Vaccaro and Waldo, 2019, Kononenko, 2001]. A solid understanding of such results is limited by the fact that most analyses of human-AI decision-making focus on ranking the performance of human-AI teams or each individually using measures like posthoc decision accuracy.

Public AI benchmark results are widely broadcast by model developers as indicators of model quality within a growing and competitive market. However, these advertised scores do not necessarily reflect the traits of interest to those who will ultimately apply AI models. In this paper, we seek to understand if and how AI benchmarks are used to inform decision-making. Based on the analyses of interviews with 19 individuals who have used, or decided against using, benchmarks in their day-to-day work, we find that across these settings, participants use benchmarks as a signal of relative performance difference between models. However, whether this signal was considered a definitive sign of model superiority, sufficient for downstream decisions, varied. In academia, public benchmarks were generally viewed as suitable measures for capturing research progress. By contrast, in both product and policy, benchmarks -- even those developed internally for specific tasks -- were often found to be inadequate for informing substantive decisions. Of the benchmarks deemed unsatisfactory, respondents reported that their goals were neither well-defined nor reflective of real-world use. Based on the study results, we conclude that effective benchmarks should provide meaningful, real-world evaluations, incorporate domain expertise, and maintain transparency in scope and goals. They must capture diverse, task-relevant capabilities, be challenging enough to avoid quick saturation, and account for trade-offs in model performance rather than relying on a single score. Additionally, proprietary data collection and contamination prevention are critical for producing reliable and actionable results. By adhering to these criteria, benchmarks can move beyond mere marketing tricks into robust evaluative frameworks.

Humans and AIs are often paired on decision tasks with the expectation of achieving complementary performance -- where the combination of human and AI outperforms either one alone. However, how to improve performance of a human-AI team is often not clear without knowing more about what particular information and strategies each agent employs. In this paper, we propose a model based in statistically decision theory to analyze human-AI collaboration from the perspective of what information could be used to improve a human or AI decision. We demonstrate our model on a deepfake detection task to investigate seven video-level features by their unexploited value of information. We compare the human alone, AI alone and human-AI team and offer insights on how the AI assistance impacts people's usage of the information and what information that the AI exploits well might be useful for improving human decisions.

Surprisal theory posits that the cognitive effort required to comprehend a word is determined by its contextual predictability, quantified as surprisal. Traditionally, surprisal theory treats words as distinct entities, overlooking any potential similarity between them. Giulianelli et al. (2023) address this limitation by introducing information value, a measure of predictability designed to account for similarities between communicative units. Our work leverages Ricotta and Szeidl's (2006) diversity index to extend surprisal into a metric that we term similarity-adjusted surprisal, exposing a mathematical relationship between surprisal and information value. Similarity-adjusted surprisal aligns with information value when considering graded similarities and reduces to standard surprisal when words are treated as distinct. Experimental results with reading time data indicate that similarity-adjusted surprisal adds predictive power beyond standard surprisal for certain datasets, suggesting it serves as a complementary measure of comprehension effort.

We demonstrate that adaptively controlling the size of individual regression trees in a random forest can improve predictive performance, contrary to the conventional wisdom that trees should be fully grown. A fast pruning algorithm, alpha-trimming, is proposed as an effective approach to pruning trees within a random forest, where more aggressive pruning is performed in regions with a low signal-to-noise ratio. The amount of overall pruning is controlled by adjusting the weight on an information criterion penalty as a tuning parameter, with the standard random forest being a special case of our alpha-trimmed random forest. A remarkable feature of alpha-trimming is that its tuning parameter can be adjusted without refitting the trees in the random forest once the trees have been fully grown once. In a benchmark suite of 46 example data sets, mean squared prediction error is often substantially lowered by using our pruning algorithm and is never substantially increased compared to a random forest with fully-grown trees at default parameter settings.

Giulianelli and Fernández, 2021; Wallbridge When viewed as information transmission, successful et al., 2022). However, token-level autoregressive language production can be seen as an act approximations of utterance probability have a of reducing the uncertainty over future states that a few problematic properties. A well-known issue comprehender may be anticipating. Saying a word, is that different realisations of the same concept for example, may cut the space of possibilities in or communicative intent compete for probability half, while uttering a whole sentence may restrict mass (Holtzman et al., 2021), which implies that the comprehender's expectations to a far smaller the surprisal of semantically equivalent realisations space. Measuring the amount of information is overestimated. Moreover, token-level carried by a linguistic signal is fundamental to surprisal estimates conflate different dimensions of the computational modelling of human language predictability. As evidenced by recent studies (Arehalli processing. Such quantifications are used in et al., 2022; Kuhn et al., 2023), this makes psycholinguistic and neurobiological models of it difficult to appreciate whether the information language processing (Levy, 2008; Willems et al., carried by an utterance is a result, for example, of 2016; Futrell and Levy, 2017; Armeni et al., 2017), the unexpectedness of its lexical material, syntactic to study the processing mechanisms of neural arrangements, semantic content, or speech act type.

Information value (IV) is a quite popular technique for features selection before the modeling phase. There are practical criteria, based on fixed thresholds for IV, but at the same time mysterious and lacking theoretical arguments, to decide if a predictor has sufficient predictive power to be considered in the modeling phase. However, the mathematical development and statistical inference methods for this technique are almost nonexistent in the literature. In this paper we present a theoretical framework for IV, and at the same time, we propose a non-parametric hypothesis test to evaluate the predictive power of features contemplated in a data set. Due to its relationship with divergence measures developed in the Information Theory, we call our proposal the J - Divergence test. We show how to efficiently compute our test statistic and we study its performance on simulated data. In various scenarios, particularly in unbalanced data sets, we show its superiority over conventional criteria based on fixed thresholds. Furthermore, we apply our test on fraud identification data and provide an open-source Python library, called "statistical-iv"(https://pypi.org/project/statistical-iv/), where we implement our main results.