7 papers
Testing the Validity of Embedding-Based Similarity and Clustering for Handwritten Physics Solutions
Maike Tauschhuber, Gerd Kortemeyer
Text embeddings are increasingly used in physics education research to organize, compare, and cluster large collections of written text. Their appeal is clear: once student respons…
Ed API: Towards a Shared API for Education Microservices
Maximillan Sölch, Alexandra Neagu, Marcus Messer +5
Learning at scale often requires domain-specific automation such as assessment and feedback. An organization locked in to a general learning platform without these specialist autom…
When AI Evaluates Its Own Work: Validating Learner-Initiated, AI-Generated Physics Practice Problems
Tobias Geisler, Gerd Kortemeyer
Large language models (LLMs) can now generate physics practice problems in real time, yet the educational value of these items hinges on rapid, reliable post-generation vetting. In…
Artificial-Intelligence Grading Assistance for Handwritten Components of a Calculus Exam
Gerd Kortemeyer, Alexander Caspar, Daria Horica
We investigate whether contemporary multimodal LLMs can assist with grading open-ended calculus at scale without eroding validity. In a large first-year exam, students' handwritten…
Assisting the Grading of a Handwritten General Chemistry Exam with Artificial Intelligence
Jan Cvengros, Gerd Kortemeyer
We explore the effectiveness and reliability of an artificial intelligence (AI)-based grading system for a handwritten general chemistry exam, comparing AI-assigned scores to human…
The Boiling-Frog Problem of Physics Education
Gerd Kortemeyer
It is astonishing how rapidly general-purpose AI has crossed familiar thresholds in introductory physics. Comparing outputs from successive models, GPT-5 Thinking moves far beyond…