New Open Database Standardizes Collegiate Running Performance Data
Key takeaways
- NRCD is the first large-scale, open database of US collegiate running results.
- It includes nearly 129,000 performances with rich metadata.
- A unified standardization framework significantly improves performance comparability.
- The resource supports advanced research in athlete modeling and gender equity.
Who benefits
Summary
The National Running Club Database (NRCD) is introduced as the first openly available, large-scale dataset of collegiate running results, comprising nearly 129,000 performances from over 28,000 athletes across various sports and spanning 2004-2026. Alongside the dataset, a unified performance standardization framework is released, which significantly reduces within-athlete variability by adjusting for distance, elevation, and weather, supporting advanced research in athlete modeling and gender equity.
Why it matters
Professionals in sports analytics, coaching, public health, and academic research can access a rich, standardized dataset to conduct more robust studies on athlete performance, training efficacy, environmental impacts, and gender equity in sports.
How to implement this in your domain
- 1Access the NRCD dataset and the `nrcd` Python package from the provided GitHub repository.
- 2Integrate the NRCD into your sports analytics platforms or research projects.
- 3Apply the unified performance standardization framework to your own running data for more accurate comparisons.
- 4Utilize the dataset for longitudinal athlete modeling, talent identification, or injury prevention research.
- 5Contribute to the community-governed database by submitting new data or improvements to the standardization pipeline.
Original post by Jonathan A. Karr Jr., Ryan M. Fryer, Ben Darden, Nicholas Pell, Kayla Ambrose, Evan Hall, Ramzi K. Bualuan, Nitesh V. Chawla
"arXiv:2608.14776v1 Announce Type: new Abstract: Collegiate running in the United States generates thousands of race results annually in cross country and track and field, yet no large-scale dataset has been publicly available for research. Existing websites such as Athletic.net,…"
View on XOriginally posted by Jonathan A. Karr Jr., Ryan M. Fryer, Ben Darden, Nicholas Pell, Kayla Ambrose, Evan Hall, Ramzi K. Bualuan, Nitesh V. Chawla on X · view source
Want to go deeper?
Turn these trends into skills with Learnijoy's hands-on AI & tech courses.
Explore coursesMore in AI Research
Digital Twin Simulates Liver Health and Disease Progression
Researchers developed HEPATWIN, a physiology-informed digital twin of the human liver that integrates metabolic processes and patient-specific inputs to simulate liver function and early-stage disease progression, generating clinically observable biomarker trajectories.
Explaining Multi-Objective Reinforcement Learning with Counterfactuals
This paper introduces command-space counterfactual explanations for Pareto-Conditioned Networks (PCNs), allowing users to understand how slight shifts in desired return commands would alter an agent's actions in multi-objective reinforcement learning scenarios.
LLM Framework Generates and Verifies Parallel DEVS Statecharts
This research introduces PDEVS-LLM, an agentic framework that uses large language models to assist human modelers in generating and verifying Parallel Discrete Event System Specification (PDEVS) statecharts, improving accuracy through controlled correction and logical consistency checks.