The authors report that an AI-assisted harness enabled weekly closed-book tests to replace lectures in one small upper-level course while preserving student accountability, based on survey data from 18 students and project git history.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
support 1representative citing papers
Standard LLM chats produce high perceived understanding but low objective learning in students, while future-self explanations best align confidence with actual gains and guided hints maximize learning with moderate workload.
Proposes mCCDF plots to visualize ordinal regression results and communicate key takeaways from analyses of ordinal data like Likert scales.
The paper proposes a hybrid e-assessment method that retains paper exams while using vision LLMs with two-pass validation to semi-automate grading of handwritten structured answers for better scalability in large cohorts.
citing papers explorer
-
Test-Driven, AI-Assisted Learning: Replacing Lectures with Weekly Closed-Book Tests
The authors report that an AI-assisted harness enabled weekly closed-book tests to replace lectures in one small upper-level course while preserving student accountability, based on survey data from 18 students and project git history.
-
Confidence Without Competence in AI-Assisted Knowledge Work
Standard LLM chats produce high perceived understanding but low objective learning in students, while future-self explanations best align confidence with actual gains and guided hints maximize learning with moderate workload.
-
Adapting CCDF Plots for Visualizing Ordinal Regression Results
Proposes mCCDF plots to visualize ordinal regression results and communicate key takeaways from analyses of ordinal data like Likert scales.
-
Hybrid E-Assessment in Higher Education: Semi-Automated Grading of Paper-Based Written Examinations
The paper proposes a hybrid e-assessment method that retains paper exams while using vision LLMs with two-pass validation to semi-automate grading of handwritten structured answers for better scalability in large cohorts.