Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment user interfaces and libraries that enable a better understanding of AI systems. These interfaces and libraries empower developers and stakeholders of AI systems to develop and monitor AI more responsibly, and take better data-driven actions.

[NeurIPS 2025 (D&B)] Rethinking Evaluation of Infrared Small Target Detection

Propagation of distributions by Monte-Carlo sampling: Real number types with uncertainty represented by samples.

Analysis of digital elevation models and elevation point clouds

[ECCV'24] On the Error Analysis of 3D Gaussian Splatting and an Optimal Projection Strategy

Evaluation package that allows benchmarking of agentic AIs from various sources and frameworks by producing statistical results which can be compared across different use cases and datasets.

Helping AI practitioners better understand their datasets and models in text classification. From ServiceNow.

Model verification, validation, and error analysis

OlliePy is a python package which can help data scientists in exploring their data and evaluating and analysing their machine learning experiments by utilising the power and structure of modern web applications. The data scientist only needs to provide the data and any required information and OlliePy will generate the rest.

Process global-scale satellite and airborne elevation data into time series of glacier mass change: Hugonnet et al. (2021).

Responsible AI Workshop: a series of tutorials & walkthroughs to illustrate how put responsible AI into practice

A tool for classifying mistakes in the output of parsers

A tool for classifying errors in coreference resolution

Tests the Black-Scholes model's performance on forecasting option call prices of a selected option chain dataset. Discusses factors such as volatility and time to expiration that affect the estimations of call option prices and how this occurs within the dynamics of the model.

A package for handling numeric quantities with asymmetric uncertainties.

Error analysis, diagnostic tests and plots for nested sampling calculations.

Process case studies on DEM uncertainty analysis at the Mont-Blanc massif and Northern Patagonian Icefield: Hugonnet et al. (2022).

🤖 AI-powered log analysis tool - Parse, group, and understand your logs with intelligent error detection and automated insights

CECS (C/C++ Error Control System) is a pure C libary, with C++ support, for textual informative error control. Errors, Warnings or Info that is recording during runtime can be traced back to the file and line where the error occured.

Advanced Streamlit + Plotly sentiment analysis lab for TF-IDF word/char features, multi-model training, ROC/PR-AUC evaluation, cost-aware threshold tuning, error analysis, and live prediction.