David Rein — accepted AI-conference papers

2025

Measuring AI Ability to Complete Long Software Tasks

Thomas Kwa, Ben West, Joel Becker, Amy Deng, Katharyn Garcia, Max Hasin +19

NeurIPS 2025poster

Despite rapid progress on AI benchmarks, the real-world meaning of benchmark performance remains unclear. To quantify the capabilities of AI systems in terms of human capabilities, we propose a new metric: 50%-task-completion time horizon. This is the time humans typically take to complete tasks tha…

Cited by 0 Source ↗Scholar ↗

2021

Classification with Strategically Withheld Data

Anilesh K. Krishnaswamy, Haoming Li, David Rein, Hanrui Zhang, Vincent Conitzer

AAAI 2021technical

Machine learning techniques can be useful in applications such as credit approval and college admission. However, to be classified more favorably in such contexts, an agent may decide to strategically withhold some of her features, such as bad test scores. This is a missing data problem with a twis…

Cited by 17 Source ↗PDF ↗code ↗Scholar ↗