12
0

Pensieve Grader: An AI-Powered, Ready-to-Use Platform for Effortless Handwritten STEM Grading

Yoonseok Yang
Minjune Kim
Marlon Rondinelli
Keren Shao
Main:5 Pages
5 Figures
Bibliography:2 Pages
1 Tables
Abstract

Grading handwritten, open-ended responses remains a major bottleneck in large university STEM courses. We introduce Pensieve (this https URL), an AI-assisted grading platform that leverages large language models (LLMs) to transcribe and evaluate student work, providing instructors with rubric-aligned scores, transcriptions, and confidence ratings. Unlike prior tools that focus narrowly on specific tasks like transcription or rubric generation, Pensieve supports the entire grading pipeline-from scanned student submissions to final feedback-within a human-in-the-loop interface.Pensieve has been deployed in real-world courses at over 20 institutions and has graded more than 300,000 student responses. We present system details and empirical results across four core STEM disciplines: Computer Science, Mathematics, Physics, and Chemistry. Our findings show that Pensieve reduces grading time by an average of 65%, while maintaining a 95.4% agreement rate with instructor-assigned grades for high-confidence predictions.

View on arXiv
@article{yang2025_2507.01431,
  title={ Pensieve Grader: An AI-Powered, Ready-to-Use Platform for Effortless Handwritten STEM Grading },
  author={ Yoonseok Yang and Minjune Kim and Marlon Rondinelli and Keren Shao },
  journal={arXiv preprint arXiv:2507.01431},
  year={ 2025 }
}
Comments on this paper