AI Art Neural Constellation: Revealing the Collective and Contrastive State of AI-Generated and Human Art
Bibliographic record
Abstract
Discovering the creative potentials of a random signal to various artistic expressions in aesthetic and conceptual richness is a ground for the recent success of generative machine learning as a way of art creation. To understand the new artistic medium better, in this work, we comprehensively analyze AI-generated art within the context of human art heritage using our dataset, "ArtConstellation," comprising annotations for 6,000 WikiArt and 3,200 AI-generated artworks. After training various generative models, we compare the produced art samples with WikiArt data using the last hidden layer of a deep-CNN trained for style classification. By interpreting neural representations with important artistic concepts like Wölfflin’s principles, we find that AI-generated artworks align with modern period art concepts (1800 - 2000). Out-Of-Distribution (OOD) and In-Distribution (ID) detection in CLIP space reveal that AI-generated art is ID to human art with landscapes and geometric abstract figures but OOD with deformed and twisted figures, showcasing unique characteristics. A human survey on emotional experience indicates color composition and familiar subjects as key factors in likability and emotions. We introduce our methodologies and dataset, "ArtNeural-Constellation," as a framework for contrasting human and AI-generated art. Code and data are available here.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".