Claims

An earlier YOLO-5-based handwriting recognition method reached only 88.28% accuracy on examination table fields, which the authors judge insufficient for summative assessment

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person · recheck by 2029: tool and model accuracy changes quickly

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? A domain-specifically trained YOLO-5-based method achieved 88.28% recognition performance on handwritten examination entries, which the authors consider insufficient because roughly one error per ten letters would risk legally relevant misgrading. → Hartwig Grabowski 2026

Evidence

Hartwig Grabowski 2026

Hartwig Grabowski, Michael Canz. (2026). Hybrid E-Assessment in Higher Education: Semi-Automated Grading of Paper-Based Written Examinations. https://arxiv.org/abs/2606.08855 doi:10.48550/arxiv.2606.08855

q2 · i? · design · r2

The article reports its authors' earlier implementation, a YOLO-5-based recognizer trained on image segments from examination table fields: "recognition performance remained at 88.28%". The authors state this level is insufficient for summative assessment. No effect size or sample size is printed for this result.

"An earlier implementation used a YOLO-5-based method (Redmon et al., 2016) trained on image segments extracted from the relevant table fields (Grabowski, 2023). Despite this domain-specific training, recognition performance remained at 88.28%."

Discussion

Page metadata
Field Value
type claim
id yolo5-handwriting-recognition-88-percent-insufficient
title An earlier YOLO-5-based handwriting recognition method reached only 88.28% accuracy on examination table fields, which the authors judge insufficient for summative assessment
description An earlier YOLO-5-based handwriting recognition method reached only 88.28% accuracy on examination table fields, which the authors judge insufficient for summative assessment
status review
evidence_strength weak
newest_evidence 2026
recheck_by 2029
generated by process:wiki-ingest on 2026-10-11
trust unverified — no one has confirmed this page's content
sources 1 — hartwig-grabowski-2026

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