Kyle Miller

Aaditya Singh, Adam Fry, Adam Perelman et al. · berkeley, mila

This is the system card published alongside the OpenAI GPT-5 launch, August 2025. GPT-5 is a unified system with a smart and fast model that answers most questions, a deeper reasoning model for harder problems, and a real-time router that quickly decides which model to use based on conversation type, complexity, tool needs, and explicit intent (for example, if you say 'think hard about this' in the prompt). The router is continuously trained on real signals, including when users switch models, preference rates for responses, and measured correctness, improving over time. Once usage limits are reached, a mini version of each model handles remaining queries. This system card focuses primarily on gpt-5-thinking and gpt-5-main, while evaluations for other models are available in the appendix. The GPT-5 system not only outperforms previous models on benchmarks and answers questions more quickly, but -- more importantly -- is more useful for real-world queries. We've made significant advances in reducing hallucinations, improving instruction following, and minimizing sycophancy, and have leveled up GPT-5's performance in three of ChatGPT's most common uses: writing, coding, and health. All of the GPT-5 models additionally feature safe-completions, our latest approach to safety training to prevent disallowed content. Similarly to ChatGPT agent, we have decided to treat gpt-5-thinking as High capability in the Biological and Chemical domain under our Preparedness Framework, activating the associated safeguards. While we do not have definitive evidence that this model could meaningfully help a novice to create severe biological harm -- our defined threshold for High capability -- we have chosen to take a precautionary approach.

Stephen Price, Kyle Miller, Marco Musto et al.

Cold spraying is an increasingly common approach for repairing and manufacturing components due to its solid-state manufacturing capabilities. However, process optimization remains difficult due to many interdependent parameters and the lack of large-scale, machine-readable data to support modeling. While the scientific literature contains many relevant experiments, results are inconsistently reported (often in tables and figures) and use non-uniform units, limiting utilization at scale. To address these limitations, this work presents HUGO-CS, a literature-derived dataset of 4,383 cold-spray experiments with 144 features from 1,124 sources, exceeding the previous largest dataset (137 samples) by 30x. With completely manual extraction requiring an average of 91 minutes per document, this work designs and leverages a Hybrid-labeled, Uncertainty-aware, General-purpose, Observational extraction framework, called HUGO, to support this extraction. HUGO combines automated LLM-based labeling with targeted manual label refinement to handle this experimental result extraction process from scientific literature. To balance labeling efficiency with extraction accuracy, HUGO introduces a Hierarchical Risk Mitigation (HRM) to route LLM outputs with a high risk of potential errors for manual review, while retaining low-risk records as auto-labeled. Lastly, HUGO post-processing consolidates categorical descriptors, maps reported feedstock chemistries into structured continuous compositions, and normalizes units across sources. Of the 4,383 reported experiments, 1,765 are hand-labeled, providing a high-quality labeled subset for benchmarking, error analysis, and higher-fidelity data points. All code to replicate this work, along with the complete HUGO-CS dataset, are released under a CC-BY license at https://github.com/sprice134/HUGO.

Kyle Miller, Artur Dubrawski

This paper reviews current literature in the field of predictive maintenance from the system point of view. We differentiate the existing capabilities of condition estimation and failure risk forecasting as currently applied to simple components, from the capabilities needed to solve the same tasks for complex assets. System-level analysis faces more complex latent degradation states, it has to comprehensively account for active maintenance programs at each component level and consider coupling between different maintenance actions, while reflecting increased monetary and safety costs for system failures. As a result, methods that are effective for forecasting risk and informing maintenance decisions regarding individual components do not readily scale to provide reliable sub-system or system level insights. A novel holistic modeling approach is needed to incorporate available structural and physical knowledge and naturally handle the complexities of actively fielded and maintained assets.

Eric Lei, Kyle Miller, Michael R. Pinsky et al.

Multi-view data are increasingly prevalent in practice. It is often relevant to analyze the relationships between pairs of views by multi-view component analysis techniques such as Canonical Correlation Analysis (CCA). However, data may easily exhibit nonlinear relations, which CCA cannot reveal. We aim to investigate the usefulness of nonlinear multi-view relations to characterize multi-view data in an explainable manner. To address this challenge, we propose a method to characterize globally nonlinear multi-view relationships as a mixture of linear relationships. A clustering method, it identifies partitions of observations that exhibit the same relationships and learns those relationships simultaneously. It defines cluster variables by multi-view rather than spatial relationships, unlike almost all other clustering methods. Furthermore, we introduce a supervised classification method that builds on our clustering method by employing multi-view relationships as discriminative factors. The value of these methods resides in their capability to find useful structure in the data that single-view or current multi-view methods may struggle to find. We demonstrate the potential utility of the proposed approach using an application in clinical informatics to detect and characterize slow bleeding in patients whose central venous pressure (CVP) is monitored at the bedside. Presently, CVP is considered an insensitive measure of a subject's intravascular volume status or its change. However, we reason that features of CVP during inspiration and expiration should be informative in early identification of emerging changes of patient status. We empirically show how the proposed method can help discover and analyze multiple-to-multiple correlations, which could be nonlinear or vary throughout the population, by finding explainable structure of operational interest to practitioners.

Yichong Xu, Hongyang Zhang, Aarti Singh et al.

We study the problem of interactively learning a binary classifier using noisy labeling and pairwise comparison oracles, where the comparison oracle answers which one in the given two instances is more likely to be positive. Learning from such oracles has multiple applications where obtaining direct labels is harder but pairwise comparisons are easier, and the algorithm can leverage both types of oracles. In this paper, we attempt to characterize how the access to an easier comparison oracle helps in improving the label and total query complexity. We show that the comparison oracle reduces the learning problem to that of learning a threshold function. We then present an algorithm that interactively queries the label and comparison oracles and we characterize its query complexity under Tsybakov and adversarial noise conditions for the comparison and labeling oracles. Our lower bounds show that our label and total query complexity is almost optimal.

Matt Barnes, Kyle Miller, Artur Dubrawski

One significant challenge to scaling entity resolution algorithms to massive datasets is understanding how performance changes after moving beyond the realm of small, manually labeled reference datasets. Unlike traditional machine learning tasks, when an entity resolution algorithm performs well on small hold-out datasets, there is no guarantee this performance holds on larger hold-out datasets. We prove simple bounding properties between the performance of a match function on a small validation set and the performance of a pairwise entity resolution algorithm on arbitrarily sized datasets. Thus, our approach enables optimization of pairwise entity resolution algorithms for large datasets, using a small set of labeled data.