Gradescope: A Fast, Flexible, and Fair System for Scalable Assessment of Handwritten Work
Abstract
We present a system for online assessment of handwritten homework assignments and exams. First, either instructors or students scan and upload handwritten work. Instructors then grade the work and distribute the results using a web-based platform. Our system optimizes for three key dimensions: speed, consistency, and flexibility. The primary innovation enabling improvements in all three dimensions is a dynamically evolving rubric for each question on an assessment. We also describe how the system minimizes the overhead incurred in the digitization process. Our system has been in use for four years, with instructors at 200 institutions having graded over 10 million pages of student work. We present results as user-reported data and feedback regarding time saved grading, enjoyment, and student experience. Two-thirds of responders report saving 30% or more time relative to their traditional workflow. We also find that the time spent grading an individual response to a question rapidly decays with the number of responses to that question that the grader has already graded.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The criteria drift finding echoes prior work in educational settings, where instructors often update their grading rubrics to reflect common errors as they grade more assignments.
“Our criteria drift finding echoes prior work in educational settings, where instructors often update their grading rubrics to reflect common errors as they grade more assignments [47].”
From Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences (2024) · cites this paper as [47]
Cites
Hattie, J. (2008) · doi:10.4324/9780203887332 · Cited by 3,051 · see citing works
The use of scoring rubrics: Reliability, validity and educational consequences
Jonsson, A., & Svingby, G. (2007) · Educational Research Review · doi:10.1016/j.edurev.2007.05.002 · Cited by 1,509 · see citing works
Schleimer, S., S, W. D., & Aiken, A. (2003) · Proceedings of the 2003 ACM SIGMOD International Conference on Management of Data · doi:10.1145/872757.872770 · Cited by 1,099 · cited 1× · see citing works
“For computer science courses, focus has been on autograding of programming projects [11, 8, 3] and automated plagiarism detection [14].”
BackgroundA review of rubric use in higher education
Reddy, Y. M., & Andrade, H. (2010) · Assessment & Evaluation in Higher Education · doi:10.1080/02602930902862859 · Cited by 917 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences
Shankar, S., Zamfirescu-Pereira, J. D., Hartmann, B., Parameswaran, A., & Arawjo, I. (2024) · Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology · doi:10.1145/3654777.3676450 · Cited by 151 · see citing works
Azcona, D., Hsiao, I.-H., & Smeaton, A. F. (2019) · User Modeling and User-Adapted Interaction · doi:10.1007/s11257-019-09234-7 · Cited by 114 · see citing works
Machine learning based feedback on textual student answers in large courses
Bernius, J. P., Krusche, S., & Bruegge, B. (2022) · Computers and Education: Artificial Intelligence · doi:10.1016/j.caeai.2022.100081 · Cited by 75 · see citing works
Mossad: defeating software plagiarism detection
Devore-McDonald, B., & Berger, E. D. (2020) · Proceedings of the ACM on Programming Languages · doi:10.1145/3428206 · Cited by 35 · see citing works
Fooling MOSS Detection with Pretrained Language Models
Biderman, S., & Raff, E. (2022) · Proceedings of the 31st ACM International Conference on Information & Knowledge Management · doi:10.1145/3511808.3557079 · Cited by 37 · see citing works
- Authors
- Singh, A., Karayev, S., Gutowski, K., & Abbeel, P.
- Affiliations
- Gradescope, Inc., Berkeley, CA, USA
- University of California, Berkeley (US)
- ORCID
- Abbeel, Pieter
- Venue
- Proceedings of the Fourth (2017) ACM Conference on Learning @ Scale
- Publisher
- ACM
- Published
- 2017-04-12
- Pages
- 81-88
- OpenAlex
- W2605994771
- Cited by
- 113
- References
- 4
- Citations by year
- 2026: 13 · 2025: 15 · 2024: 15 · 2023: 18 · 2022: 8 · 2021: 15 · 2020: 9 · 2019: 9 · 2018: 9 · 2017: 2
- FWCI
- 6.09
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM Conference on Learning @ Scale (L@S) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Information Systems › Educational Technology and Assessment
- Physical Sciences › Computer Science › Computer Science Applications › Online Learning and Analytics
- Physical Sciences › Computer Science › Information Systems › Educational Technology and E-Learning
- Keywords
- online assessment, test scoring, student experience
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
