Challenges

2025 Challenge: AI, Work, and Professional Integrity

The RB and LPX Foundation invites submissions for its 2025 public challenge on the role of AI in professional life. As large-scale models and automation tools reshape workflows across industries, organizations and individuals face difficult questions not only about what AI can do, but what it should do.

This year’s challenge addresses three related concerns:

1. the ethical consequences of how organizations adopt and deploy AI tools,
2. the transformation of professional training in response to new machine learning paradigms, and
3. the effects of hype-driven narratives that exaggerate technical capability or promote short-term financial gain over sustainable practice.

We ask participants to propose frameworks, research prototypes, or documented practices that engage with one or more of these concerns. Submissions might explore ways to document ethical AI use in organizations, outline new training models that support critical engagement with AI tools, or provide empirical analysis of how exaggerated claims affect public trust or workplace decision-making.

During the last few years, the RB and LPX Foundation has offered challenges to produce novel ML applications. Our motivation was to encourage the public to engage in ML as a scientific adventure in the spirit of a makerspace. There was interest in the public and what seemed a generally positive sentiment towards data science and machine learning.

The tone changed a bit with the availability of LLMs and generative AI. Many now express distrust of AI and ML because of ethical concerns about how large companies harvested data without concern for the rights of small artists or privacy.

Generative AI has inspired an explosion of interest. ML had been a field requiring advanced knowledge of mathematics and computer science. Tools such as GPT, Midjourney and Stable Diffusion have opened up AI by providing intuitive natural language interfaces.

The power of these models hides a danger. While they can generate text and images that seem of similar quality to what a human artist or scholar can produce, that generated work hides the history behind the original data used to train these models. They generate based on statistical models from huge amounts of data with no attribution to the individual images and text in the data sets used to train the models.

The 2021 challenge focuses on air pollution measurement and prediction. Wildfires in the US West raised clouds of smoke which lingered for months. This dramatic incident only highlighted existing problems caused by decades of industrial and other pollution.

Air is life and polluted air harms us all, especially those of us with respiratory problems. Polluted air damages humans, animals and plants. Anything that we can do to reduce harm from air pollution, we should do. The first step in solving a problem is to know the problem by measuring and modeling.

For this year, we will begin offering challenge problems. These will be problems that are relevant to ecology, medicine or social welfare. For each of these problems, we will offer a data set or a way to create a data set, regression targets and baseline implementations.

This year, our three problems are

1. Analyzing professional graphs such as the publicly published IMBD movie dataset to detect effects of gender on career trajectory
2. Training RL agents to optimize sensory placement to detect wildfires in urban wilderness interface
3. Prototyping models to detect topological types of knotted graphs similar to topological types of organic molecules such as DNA and complicated proteins