Clusters did not differ significantly in the number of prompts sent to ChatGPT¶
Claim · All claims
Evidence · 1 study · associationalr2·q3
Currency · newest study 2026 · 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.
q3 i? Prompt counts did not differ significantly between text reconstructors (M = 9.11, SD = 4.91) and text integrators (M = 7.61, SD = 4.08), t(119) = −1.84, p = 0.069. → Teresa Luther · Kate Belcher · Joachim Kimmerle · Detmar Meurers · Ulrike Cress 2026
Evidence¶
Teresa Luther · Kate Belcher · Joachim Kimmerle · Detmar Meurers · Ulrike Cress 2026¶
Teresa Luther · Kate Belcher · Joachim Kimmerle · Detmar Meurers · Ulrike Cress (2026). Collaborative knowledge construction with generative AI: Exploring argumentative co-writing processes through n-gram and cluster analysis. Intern. J. Comput.-Support. Collab. Learn. https://doi.org/10.1007/s11412-026-09470-1
q3 · i? · associational · r2
Null result from the n=131 study testing whether prompt frequency explained uptake differences; "no significant difference between Cluster 3 and Cluster 2". Equivalence was not tested. Mean prompts: reproducers 7.63, reconstructors 9.11, integrators 7.61.
"An independent samples t-test revealed no significant difference between Cluster 3 and Cluster 2 (t(119) = − 1.84, p = 0.069, 95% CI [− 3.13, 0.12])."
Discussion¶
Related Claims¶
- Correlations between the number of prompt mistakes and number of messages sent were non-significant or weak, giving little evidence that mistake count influenced prompting effort — related
- Current ChatGPT users were overrepresented among text reconstructors and underrepresented among text integrators (Cramér's V = 0.26) — related
- AI-supported argumentative writing yields three distinct uptake clusters (text reproducers, text integrators, text reconstructors) based on recurring n-gram overlap — a broader claim this one bears on
- Text reproducers copied nearly all of their final text from ChatGPT with long verbatim sequences, while text integrators showed fragment-level micro-uptake — related
- Affinity for technology interaction differed across clusters, with text reproducers highest and integrators scoring higher than reconstructors (d = 0.59) — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
clusters-no-difference-in-prompt-count |
title |
Clusters did not differ significantly in the number of prompts sent to ChatGPT |
description |
Clusters did not differ significantly in the number of prompts sent to ChatGPT |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2026 |
generated |
by process:wiki-ingest on 2026-10-18 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — teresa-luther-kate-belcher-joachim-kimmerle-detmar-meurers-ulrike-cress-2026 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.