Claims

Strategy-based assessment recognised 62 of 72 correct student programs (86%) from four model solutions with no false positives

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2016 · not yet checked against its sources · not reviewed by a person

Subclaims

Reading the evidence codes

q is the design tier, i the impact, n the sample, and the kind with its r the rigour judged within that kind: what each code means.

This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.

q2 i? In a 2009 assessment experiment on 94 student solutions to a Haskell lab assignment, the tool recognised 62 of the 72 programs judged good or good-with-modifications (86%), and none of the incorrect or imperfect programs were recognised. → Gerdes 2016

Evidence

Gerdes 2016

Gerdes, A., Heeren, B., Jeuring, J., & van Binsbergen, L. T. (2016). Ask-Elle: an Adaptable Programming Tutor for Haskell Giving Automated Feedback. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-015-0080-x

q2 · i? · design · r2

Assessment experiment on 94 student solutions to the fromBin exercise collected from a first-year functional programming course at Utrecht University (2008), previously graded by hand. "From these 72 programs, our assessment tool recognises 62 programs (86%)" using four model solutions. The article also reports no false positives: all incorrect and imperfect programs were rejected.

"From these 72 programs, our assessment tool recognises 62 programs (86%). Another, and perhaps better, way of looking at these numbers is that 62 student solutions are accepted based on just four model solutions."

Discussion

Page metadata
Field Value
type claim
id ask-elle-assessment-recognises-62-of-72-programs
title Strategy-based assessment recognised 62 of 72 correct student programs (86%) from four model solutions with no false positives
description Strategy-based assessment recognised 62 of 72 correct student programs (86%) from four model solutions with no false positives
status review
evidence_strength moderate
newest_evidence 2016
generated by process:wiki-ingest on 2026-10-28
trust unverified — no one has confirmed this page's content
sources 1 — gerdes-2016

Frontmatter is the page's machine-readable record — see the Schema & Guide.