Learning-process and psychological constructs correlate only weakly with aggregate final artistic performance¶

Claim · All claims
Evidence · 1 study · associational r2 · q2 · i0 negligible
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i0 Perceived support (r = 0.06), creative experience (r = −0.04), skill transfer (r = 0.03), and quality confidence (r = 0.02) showed negligible correlations with final total score. → Shen 2026

Evidence¶

Shen 2026¶

Shen, N., Lee, L. S., and He, A. (2026). Generative AI in creative education: baseline-linked evidence on learning processes, artistic performance, and authorship. Frontiers in Psychology. https://doi.org/10.3389/fpsyg.2026.1956939

q2 · i0 · associational · r2

Correlational analysis of the 133-case linked dataset (Figure 2) shows the learning-process and psychological variables were only weakly related to final total, with printed correlations all below |r| = .10. The article states these constructs "showed little overlap withaggregatefinalperformance."

"support (r = 0.06), creative experience (r =− 0.04), skill transfer (r = 0.03), and quality confidence (r = 0.02) showed little overlap withaggregatefinalperformance."

Discussion¶

Related Claims¶

• Authorship captures a more distinct aspect of artistic evaluation than other performance dimensions — related
• Baseline-to-final performance change was centered near zero with a mean of −1.83 — related
• Professional developers write prompts of moderate baseline quality, which does not meaningfully scale with programming experience — related
• ChatGPT use does not change absolute self-evaluation accuracy, but self-evaluation judgments fail to correlate with performance under ChatGPT assistance — related
• ChatGPT use boosts university students' self-efficacy for task resolution, but self-efficacy barely tracks actual performance — related
• Questionnaire constructs showed acceptable to strong internal consistency (α = 0.740 to 0.945) — related
• Creativity research increasingly relies on self-reports, which correlate little or not at all with creative performance — a broader claim this one bears on