Knowledge Resource · Open access
Research Summary: Generative AI performance in core undergraduate mathematics: a curriculum-level case study
- Original authors
- Attribution requires verification
- Original source
- arXiv — Computers and Society
- Summary & Analysis prepared by
- Aziz Shuaib Ausi
- Resource type
- Research Summary / Knowledge Resource
- Resource published on AZIZ OS
- 11 September 2026
- Reading time
- 1 min
- Publication type
- Knowledge Resource
- Availability
- Open access
About this Summary & Analysis
AZIZ OS provides independently prepared summaries and analytical interpretations of externally published research and knowledge sources. The underlying works remain attributable to their original authors and rights holders. This resource is intended to improve accessibility and understanding and does not replace the original publication.
A study investigated the performance of Generative AI (GenAI) tools, such as OpenAI's ChatGPT, on core undergraduate mathematics assessments. The research utilized existing examination questions as a proxy for course content, applying an empirical approach to generate, transcribe, and blind-mark GenAI submissions across eight first-year mathematics assessments. This research is part of a broader re-evaluation of traditional assessment practices and the exploration of alternatives to in-person, closed-book examinations in higher education.
Why it matters
The integration and performance of GenAI in academic settings necessitate a re-evaluation of educational strategies and assessment methodologies. Understanding GenAI capabilities across core curricula is crucial for maintaining academic integrity, ensuring pedagogical effectiveness, and preparing institutions for technological shifts in learning and evaluation.
Key insights
- Generative AI tools are impacting educational assessment paradigms.
- Universities are exploring alternative assessment methods beyond traditional invigilated exams.
- Concerns exist regarding academic integrity and pedagogical alignment in uninvigilated assessment settings.
- The study empirically tested GenAI performance on typical first-year undergraduate mathematics questions.
- GenAI submissions were blind-marked against current examination questions from a full curriculum.
Source
arXiv — Computers and Society — https://arxiv.org/abs/2509.13359
Related resources
Previous
On the Societal Impact of Machine Learning
Next
Ordinary, Reasonable Chatbots: Do AI Models Track Human Legal Judgments?
Towards On-Device Evidence Gathering for Intimate Partner Infiltration: A Feasibility Study for Joint Identity-Action Detection
Knowledge Resource
Students' Perceptions of Peer Grading
Knowledge Resource
Don't Trust the Super-App: A Case Study of Russia's Max
Knowledge Resource
Ordinary, Reasonable Chatbots: Do AI Models Track Human Legal Judgments?
Knowledge Resource
On the Societal Impact of Machine Learning
Knowledge Resource
(Whose defaults?) Is artificial intelligence reorienting archaeological methods?
Knowledge Resource
Citation
Cite the original work (APA 7)
The original source is authoritative for this citation. Cite the source publication directly — this attribution is pending verification. Open the original source.
Verification
This is an authenticated AZIZ OS resource record.
- Verification ID
- ASA-EXE-2026-00438
- Version
- v1.0 · r0
- Issued
- 11 September 2026
- Resource prepared by
- Aziz Shuaib Ausi
- Resource status
- Research Summary / Knowledge Resource
- Underlying work
- Generative AI performance in core undergraduate mathematics: a curriculum-level case study
- Original authors
- Attribution requires verification
- Original source
- arXiv — Computers and Society
- Provenance status
- Attribution requires verification
- Rights
- Underlying publication rights remain with the respective copyright holder(s). Refer to the original source for authoritative publication and licensing information.
This verification confirms the AZIZ OS resource record and its documented provenance. It does not establish authorship of the underlying external work.