Review-based AI overall difficulty correlates strongly with problem-level student pass rate across 79 parallel-class exam problems¶
Claim · All claims
Evidence · 1 study · associationalr2·q2·i3large
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 i3 Raw AI overall difficulty correlated with student problem pass rate at Spearman rho = -0.871 (p<0.001), and remained at Spearman rho = -0.866 after removing the 12 exposed item-bank problems. → Hongfei Yan 2026
Evidence¶
Hongfei Yan 2026¶
Hongfei Yan, Jiangkai Xiong, Yiqing Li, and Chong Chen. (2026). From Evaluated Models to Evaluation Aids: A Multi-Evidence Study of LLM-Based Difficulty Calibration for Programming Examinations. https://arxiv.org/abs/2608.07523 doi:10.48550/arxiv.2608.07523
q2 · i3 · associational · r2
Cross-sectional review-based calibration of 79 problems from 11 parallel-class final machine exams, using a single auditable API reviewer. Printed effect size: Spearman rho = -0.871; "Table 7 shows a strong negative correlation between AI review difficulty and actual student problem pass rates."
"The Spearman correlation between raw AI overall difficulty and student pass rate is -0.871 (p<0.001, Fisher-approximate 95% CI [-0.916, -0.805]), and -0.857 after exposure adjustment."
Discussion¶
Related Claims¶
- AI review difficulty also correlates with problem-level non-attempt rate, providing process evidence beyond pass rate — related
- The AI review ruler's problem-level correlation weakens in an introductory course, where exam-level correlation is near zero and cohort composition dominates — related
- Exam-level AI difficulty correlations with student performance are directionally consistent but weaker and only exploratory — related
- Exposed item-bank problems did not show an overall 'seen before, hence easier' pattern in this sample — related
- The negative AI-difficulty–performance correlation is stable across exposure-discount values 0 to 0.40, and is strongest with no adjustment — a broader claim this one bears on
- The same review ruler supports longitudinal cross-semester problem tracking for one teacher's Data Structures and Algorithms B course — related
- Item-difficulty orderings diverge across cohorts, with the weakest correlation between academics and students (r = 0.188) and no stable shared developmental hierarchy — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
review-based-ai-difficulty-problem-level-correlation |
title |
Review-based AI overall difficulty correlates strongly with problem-level student pass rate across 79 parallel-class exam problems |
description |
Review-based AI overall difficulty correlates strongly with problem-level student pass rate across 79 parallel-class exam problems |
status |
review |
evidence_strength |
moderate |
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 — hongfei-yan-2026 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.