MétaCan
Menu
Back to cohort
Record W4405338045 · doi:10.1080/10400419.2024.2440691

Using AI to Generate Visual Art: Do Individual Differences in Creativity Predict AI-Assisted Art Quality?

2024· article· en· W4405338045 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueCreativity Research Journal · 2024
Typearticle
Languageen
FieldPsychology
TopicCreativity in Education and Neuroscience
Canadian institutionsUniversity of Waterloo
FundersNational Science Foundation
KeywordsCreativityPsychologyQuality (philosophy)Cognitive psychologySocial psychologyEpistemology

Abstract

fetched live from OpenAlex

As artificial intelligence (AI) advances in the realm of generative art, a critical question emerges: does human creativity matter? That is, do more-creative people produce more-creative AI-assisted artwork? To explore this, we conducted an online, pre-registered study in which we measured individual differences in creativity through two divergent-thinking tasks: The Alternate Uses Task and the Divergent Associations Task. Separately, participants produced creative wordsets for a hypothetical AI-art generator, which we then input into DALL-E to generate images. A group of trained raters independently assessed these images for creativity. Results revealed that both DAT performance and semantic diversity of the wordsets positively associated with the creativity of the AI-assisted images, suggesting that individuals with stronger divergent-thinking skills, and those who generated more-creative wordsets, tended to inspire more-creative AI-assisted artwork. Mediation analyses supported this conclusion by demonstrating a significant pathway between individual creative ability and AI-art creativity, mediated by semantic diversity. However, while our models yielded significant results, the effect sizes were modest, suggesting that the relationship between individual creative ability and AI-assisted creative outputs is relatively small. Taken together, these results suggest that while individual creativity appears to contribute to the quality of AI-assisted artwork, its influence may be relatively limited.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.010
metaresearch head score (Gemma)0.002
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Scholarly communication, Research integrity, Insufficient payload (model declined to judge)
Consensus categoriesInsufficient payload (model declined to judge)
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.241
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0100.002
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0020.003
Science and technology studies0.0010.001
Scholarly communication0.0020.001
Open science0.0010.000
Research integrity0.0000.003
Insufficient payload (model declined to judge)0.0040.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.395
GPT teacher head0.574
Teacher spread0.179 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it