Abstract--Security Operations Centers face massive, heterogeneous alert streams under minute-level service windows, creating the Alert Triage Latency Paradox: verbose reasoning chains ensure accuracy and compliance but incur prohibitive latency and token costs, while minimal chains sacrifice transparency and auditability. Existing solutions fail: signature systems are brittle, anomaly methods lack actionability, and fully cloud-hosted LLMs raise latency, cost, and privacy concerns. We propose AIDR, a hybrid cloud-edge framework that addresses this trade-off through constrained information-density optimization. The core innovation is gradient-based compression of reasoning chains to retain only decision-critical steps--minimal evidence sufficient to justify predictions while respecting token and latency budgets. We demonstrate that this approach preserves decision-relevant information while minimizing complexity. We construct compact datasets by distilling alerts into 3-5 high-information bullets (68% token reduction), train domain-specialized experts via LoRA, and deploy a cloud-edge architecture: a cloud LLM routes alerts to on-premises experts generating SOAR-ready JSON. Experiments demonstrate AIDR achieves higher accuracy and 40.6% latency reduction versus Chain-of-Thought, with robustness to data corruption and out-of-distribution generalization, enabling auditable and efficient SOC triage with full data residency compliance.

We investigate the short-context dominance hypothesis: that for most sequences, a small local prefix suffices to predict their next tokens. Using large language models as statistical oracles, we measure the minimum context length (MCL) needed to reproduce accurate full-context predictions across datasets with sequences of varying lengths. For sequences with 1-7k tokens from long-context documents, we consistently find that 75-80% require only the last 96 tokens at most. Given the dominance of short-context tokens, we then ask whether it is possible to detect challenging long-context sequences for which a short local prefix does not suffice for prediction. We introduce a practical proxy to MCL, called Distributionally Aware MCL (DaMCL), that does not require knowledge of the actual next-token and is compatible with sampling strategies beyond greedy decoding. Our experiments validate that simple thresholding of the metric defining DaMCL achieves high performance in detecting long vs. short context sequences. Finally, to counter the bias that short-context dominance induces in LLM output distributions, we develop an intuitive decoding algorithm that leverages our detector to identify and boost tokens that are long-range-relevant. Across Q&A tasks and model architectures, we confirm that mitigating the bias improves performance.

Today, with the growing obsession with applying Artificial Intelligence (AI), particularly Machine Learning (ML), to software across various contexts, much of the focus has been on the effectiveness of AI models, often measured through common metrics such as F1- score, while fairness receives relatively little attention. This paper presents a review of existing gray literature, examining fairness requirements in AI context, with a focus on how they are defined across various application domains, managed throughout the Software Development Life Cycle (SDLC), and the causes, as well as the corresponding consequences of their violation by AI models. Our gray literature investigation shows various definitions of fairness requirements in AI systems, commonly emphasizing non-discrimination and equal treatment across different demographic and social attributes. Fairness requirement management practices vary across the SDLC, particularly in model training and bias mitigation, fairness monitoring and evaluation, and data handling practices. Fairness requirement violations are frequently linked, but not limited, to data representation bias, algorithmic and model design bias, human judgment, and evaluation and transparency gaps. The corresponding consequences include harm in a broad sense, encompassing specific professional and societal impacts as key examples, stereotype reinforcement, data and privacy risks, and loss of trust and legitimacy in AI-supported decisions. These findings emphasize the need for consistent frameworks and practices to integrate fairness into AI software, paying as much attention to fairness as to effectiveness.

Semi-supervised anomaly detection (AD) has shown great promise by effectively leveraging limited labeled data. However, existing methods are typically structured around scoring individual points or simple pairs. Such {point- or pair-centric} view not only overlooks the contextual nature of anomalies, which are defined by their deviation from a collective group, but also fails to exploit the rich supervisory signals that can be generated from the combinatorial composition of sets. Consequently, such models struggle to exploit the high-order interactions within the data, which are critical for learning discriminative representations. To address these limitations, we propose SetAD, a novel framework that reframes semi-supervised AD as a Set-level Anomaly Detection task. SetAD employs an attention-based set encoder trained via a graded learning objective, where the model learns to quantify the degree of anomalousness within an entire set. This approach directly models the complex group-level interactions that define anomalies. Furthermore, to enhance robustness and score calibration, we propose a context-calibrated anomaly scoring mechanism, which assesses a point's anomaly score by aggregating its normalized deviations from peer behavior across multiple, diverse contextual sets. Extensive experiments on 10 real-world datasets demonstrate that SetAD significantly outperforms state-of-the-art models. Notably, we show that our model's performance consistently improves with increasing set size, providing strong empirical support for the set-based formulation of anomaly detection.

A robust nonproliferation regime has contained the spread of nuclear weapons to just nine states. Yet, emerging and disruptive technologies are reshaping the landscape of nuclear risks, presenting a critical juncture for decision makers. This article lays out the contours of an overlooked but intensifying technological arms race for nuclear (in)visibility, driven by the interplay between proliferation-enabling technologies (PETs) and detection-enhancing technologies (DETs). We argue that the strategic pattern of proliferation will be increasingly shaped by the innovation pace in these domains. Artificial intelligence (AI) introduces unprecedented complexity to this equation, as its rapid scaling and knowledge substitution capabilities accelerate PET development and challenge traditional monitoring and verification methods. To analyze this dynamic, we develop a formal model centered on a Relative Advantage Index (RAI), quantifying the shifting balance between PETs and DETs. Our model explores how asymmetric technological advancement, particularly logistic AI-driven PET growth versus stepwise DET improvements, expands the band of uncertainty surrounding proliferation detectability. Through replicable scenario-based simulations, we evaluate the impact of varying PET growth rates and DET investment strategies on cumulative nuclear breakout risk. We identify a strategic fork ahead, where detection may no longer suffice without broader PET governance. Governments and international organizations should accordingly invest in policies and tools agile enough to keep pace with tomorrow's technology.

Diabetes is a serious worldwide health issue, and successful intervention depends on early detection. However, overlapping risk factors and data asymmetry make prediction difficult. To use extensive health survey data to create a machine learning framework for diabetes classification that is both accurate and comprehensible, to produce results that will aid in clinical decision-making. Using the BRFSS dataset, we assessed a number of supervised learning techniques. SMOTE and Tomek Links were used to correct class imbalance. To improve prediction performance, both individual models and ensemble techniques such as stacking were investigated. The 2015 BRFSS dataset, which includes roughly 253,680 records with 22 numerical features, is used in this study. Strong ROC-AUC performance of approximately 0.96 was attained by the individual models Random Forest, XGBoost, CatBoost, and LightGBM.The stacking ensemble with XGBoost and KNN yielded the best overall results with 94.82\% accuracy, ROC-AUC of 0.989, and PR-AUC of 0.991, indicating a favourable balance between recall and precision. In our study, we proposed and developed a React Native-based application with a Python Flask backend to support early diabetes prediction, providing users with an accessible and efficient health monitoring tool.

AI systems that output their reasoning in natural language offer an opportunity for safety -- we can \emph{monitor} their chain of thought (CoT) for undesirable reasoning, such as the pursuit of harmful objectives. However, the extent to which CoT faithfully reflects the underlying reasoning process, and hence the extent to which it can be usefully monitored, may be influenced by certain aspects of training. We investigate how different \emph{training incentives}, applied to a reasoning model, affect its monitorability. We introduce a novel methodology for measuring monitorability according to whether a monitor can predict a key latent variable using the model's reasoning. When controlling for accuracy, we do not find evidence for consistent effects from commonly used incentives (length penalties and KL regularisation), but we find that adversarial optimisation (penalising monitor accuracy) degrades monitor performance, while direct optimisation for monitorability does not reliably lead to improvements. Our code is available at https://github.com/QiyaoWei/reasoning-under-pressure.

Representational similarity metrics are fundamental tools in neuroscience and AI, yet we lack systematic comparisons of their discriminative power across model families. We introduce a quantitative framework to evaluate representational similarity measures based on their ability to separate model families-across architectures (CNNs, Vision Transformers, Swin Transformers, ConvNeXt) and training regimes (supervised vs. self-supervised). Using three complementary separability measures-dprime from signal detection theory, silhouette coefficients and ROC-AUC, we systematically assess the discriminative capacity of commonly used metrics including RSA, linear predictivity, Procrustes, and soft matching. We show that separability systematically increases as metrics impose more stringent alignment constraints. Among mapping-based approaches, soft-matching achieves the highest separability, followed by Procrustes alignment and linear predictivity. Non-fitting methods such as RSA also yield strong separability across families. These results provide the first systematic comparison of similarity metrics through a separability lens, clarifying their relative sensitivity and guiding metric choice for large-scale model and brain comparisons.

Verifiers can improve language model capabilities by scoring and ranking responses from generated candidates. Currently, high-quality verifiers are either unscalable (e.g., humans) or limited in utility (e.g., tools like Lean). While LM judges and reward models have become broadly useful as general-purpose verifiers, a significant performance gap remains between them and oracle verifiers (verifiers with perfect accuracy). To help close this gap, we introduce Weaver, a framework for designing a strong verifier by combining multiple weak, imperfect verifiers. We find weighted ensembles of verifiers, which typically require learning from labeled data, significantly outperform unweighted combinations due to differences in verifier accuracies. To reduce dependency on labeled data, Weaver leverages weak supervision to estimate each verifier's accuracy and combines outputs into a unified score that better reflects true response quality. However, directly applying weak supervision algorithms poses challenges, including inconsistent verifier output formats and handling low-quality verifiers. Weaver addresses these using dataset statistics to normalize outputs and filter specific verifiers. We study Weaver's effectiveness in test-time repeated sampling, where a model generates multiple candidate responses and selects one. Our evaluations show Weaver significantly improves over Pass@1-performance when selecting the first candidate-across reasoning and math tasks, achieving o3-mini-level accuracy with Llama 3.3 70B Instruct as generator, and an ensemble of 70B or smaller judge and reward models as verifiers (87.7% average). This gain mirrors the jump between GPT-4o and o3-mini (69.0% vs. 86.7%), which required extensive finetuning and post-training. To reduce computational costs of verifier ensembles, we train a 400M cross-encoder using Weaver's combined output scores.

Inspired by graph-based methodologies, we introduce a novel graph-spanning algorithm designed to identify changes in both offline and online data across low to high dimensions. This versatile approach is applicable to Euclidean and graph-structured data with unknown distributions, while maintaining control over error probabilities. Theoretically, we demonstrate that the algorithm achieves high detection power when the magnitude of the change surpasses the lower bound of the minimax separation rate, which scales on the order of $\sqrt{nd}$. Our method outperforms other techniques in terms of accuracy for both Gaussian and non-Gaussian data. Notably, it maintains strong detection power even with small observation windows, making it particularly effective for online environments where timely and precise change detection is critical.