Jonathon Cai

EECS Department, University of California, Berkeley

Technical Report No. UCB/EECS-2020-34

May 1, 2020

http://www2.eecs.berkeley.edu/Pubs/TechRpts/2020/EECS-2020-34.pdf

We present a system, AutoRubric, for autograding template-based student programs submitted on exams. AutoRubric automates a particularly time-consuming aspect of the grading process: assigning partial credit via a rubric specification. AutoRubric takes as input a rubric and an exam question template, as well as a set of programs to grade, and scores the programs. To address program variability, AutoRubric checks for equivalences with respect to rubric items by using SMT solvers. We present results on 1500 real student exam programs, demonstrating that in less than two minutes AutoRubric automates 43.1% of the grading effort, achieving 95.8% recall and 100% precision.

Advisors: John DeNero

---

BibTeX citation:

@mastersthesis{Cai:EECS-2020-34,
    Author= {Cai, Jonathon},
    Title= {AutoRubric: Autograding Template-Based Exam Programs},
    School= {EECS Department, University of California, Berkeley},
    Year= {2020},
    Month= {May},
    Url= {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2020/EECS-2020-34.html},
    Number= {UCB/EECS-2020-34},
    Abstract= {We present a system, AutoRubric, for autograding template-based student programs submitted on exams. AutoRubric automates a particularly time-consuming aspect of the grading process: assigning partial credit via a rubric specification. AutoRubric takes as input a rubric and an exam question template, as well as a set of programs to grade, and scores the programs. To address program variability, AutoRubric checks for equivalences with respect to rubric items by using SMT solvers. We present results on 1500 real student exam programs, demonstrating that in less than two minutes AutoRubric automates 43.1% of the grading effort, achieving 95.8% recall and 100% precision.},
}

EndNote citation:

%0 Thesis
%A Cai, Jonathon 
%T AutoRubric: Autograding Template-Based Exam Programs
%I EECS Department, University of California, Berkeley
%D 2020
%8 May 1
%@ UCB/EECS-2020-34
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2020/EECS-2020-34.html
%F Cai:EECS-2020-34