LADDER: Level Analysis Dataset for Difficulty Evaluation and Ranking
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.
Bibliographic record
Abstract
Standardized datasets are fundamental to scientific research. While fields like natural language processing and computer vision have widely accepted datasets that drive progress, video game research still lacks such resources, particularly for studying level difficulty. Existing studies rely on isolated, custom datasets, limiting cross-study comparisons and hindering the development of generalizable models. To bridge this gap, we introduce LADDER, a novel dataset specifically designed to analyze and evaluate level difficulty in video games. Unlike previous datasets that primarily focus on physiological and behavioral player data, LADDER integrates objective performance metrics (e.g., health lost, number of attempts before success), level characteristics (e.g., number of danger zones, object placement), and perceived difficulty ratings across multiple platformer games. This dataset enables researchers to establish benchmarks, enhance collaboration across disciplines, and improve study reproducibility. LADDER provides a standardized foundation for investigating the relationship between game design elements and player experience. By facilitating difficulty assessment and level balancing, it supports advancements in game design, player modeling, and adaptive gameplay systems. We present an overview of existing datasets, describe the methodology behind LADDER’s construction, and showcase its potential through preliminary analyses. The dataset is freely available online, offering a valuable resource for the scientific community to develop more engaging and accessible gaming experiences.
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 imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 it