Students teaching the ChatGPT agent passed the online judge with fewer code submission attempts than control students¶
Claim · All claims
Evidence · 1 study · causalr1·q2
Currency · newest study 2024 · 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? Platform log data showed the experimental group averaged 1.95 code submission attempts versus 2.90 for the control group. → Angxuan Chen 2024
Evidence¶
Angxuan Chen 2024¶
Angxuan Chen, Yuang Wei, Huixiao Le, Yan Zhang. (2024). Learning-by-Teaching with ChatGPT: The Effect of Teachable ChatGPT Agent on Programming Education. arXiv. https://arxiv.org/abs/2412.15226 doi:10.48550/arxiv.2412.15226
q2 · i? · causal · r1
Descriptive log data from the backend auto-judging platform: "the experimental group (EG) had an average of 1.95 code submission attempts, whereas the CG had an average of 2.90 attempts"; no inferential test is reported for this contrast.
"Data from the backend auto-judging platform also revealed that the experimental group (EG) had an average of 1.95 code submission attempts, whereas the CG had an average of 2.90 attempts, indicating that the experimental group passed the auto-judgement with fewer attempts."
Discussion¶
Related Claims¶
- The experimental group answered achievement tests faster (6.18 minutes) than the control group (7.51 minutes) — related
- Students who teach a ChatGPT teachable agent in natural language achieve greater knowledge gains than students who learn the same material from online videos — related
- Teaching a ChatGPT agent does not significantly improve code correctness compared with writing code independently from videos — related
- Teaching a ChatGPT agent does not significantly change students' test anxiety — related
- Immediate post-feedback improvement is near zero on average and does not differ significantly across feedback conditions — related
- Natural language AI feedback is associated with faster convergence to correct solutions — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
chatgpt-teachable-agent-fewer-submission-attempts |
title |
Students teaching the ChatGPT agent passed the online judge with fewer code submission attempts than control students |
description |
Students teaching the ChatGPT agent passed the online judge with fewer code submission attempts than control students |
status |
review |
evidence_strength |
weak |
newest_evidence |
2024 |
generated |
by process:wiki-ingest on 2026-10-10 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — angxuan-chen-2024 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.