Designing AI-Resistant Assignments via Iterative Perturbation to Promote Interactive Learning
Published poster
Sam Gilson
Proceedings of the 57th ACM Technical Symposium on Computer Science Education V.2 (SIGCSE TS 2026), p. 1745
Citation year: 2026.
Summary
This poster presents iterative perturbation as an approach to assignment design: test a question with a target chatbot, revise the question, and evaluate the new response against an explicit rubric. The design challenge is to make the chatbot’s limitations observable while keeping the mathematical task appropriate for students.
What this study can tell us
This is a poster record. The summary describes the design approach; it is not a claim that the poster established an improvement in student learning.
Concepts used in this work
Citation
@inproceedings{gilson2026designing,
title = {{Designing AI-Resistant Assignments via Iterative Perturbation to Promote Interactive Learning}},
author = {Sam Gilson},
year = {2026},
booktitle = {Proceedings of the 57th ACM Technical Symposium on Computer Science Education V.2},
pages = {1745},
doi = {10.1145/3770761.3777058},
url = {https://sgilson7.github.io/papers/gilson2026designing/}
}