Benchmarking-Cultures-25 dataset accompanies a paper submitted to FAccT 2026. It contains a core curated dataset, derived datasets, and figures used in the research. The dataset was created by Stefan Baack, Christo Buschek, and Maty Bohacek and was last updated on May 7, 2026.
Use Cases
- Analyze AI benchmarking practices based on the curated core dataset
- Study research culture in AI development based on derived datasets
- Reproduce figures and analysis from the FAccT submission
Strengths
- Dataset is structured with a core curated component and derived components
- Accompanies a peer-reviewed submission to the FAccT 2026 conference
- Last updated on May 7, 2026
Limitations
- Column-level documentation is absent; field semantics must be inferred after download
- Row count is unknown, which may limit suitability assessment
- Description metadata is limited; actual data quality requires manual inspection after download
Provenance
- Source
- huggingface
- Freshness
- Last updated 2026-05-07 21:57:31