Compute dotkaio/competition_math via the HuggingFace `evaluate` library. Use when the user has predictions + references and wants the canonical implementation of dotkaio/competition_math.
Installs into .claude/skills of the current project.
Are you the author of Dotkaio Competition Math?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/qhjqhj00-dotkaio-competition-math)
---
name: dotkaio-competition-math
description: Compute dotkaio/competition_math via the HuggingFace `evaluate` library. Use when the user has predictions + references and wants the canonical implementation of dotkaio/competition_math.
metadata:
skill_kind: metric
source_lib: huggingface-evaluate
hf_module: dotkaio/competition_math
source: library_introspection
---
# dotkaio-competition-math
> Metric `dotkaio/competition_math` from the HuggingFace `evaluate` library.
## When to invoke
User asks to compute `dotkaio/competition_math` or wants HF evaluate's canonical version.
## Recipe
```python
import evaluate
metric = evaluate.load("dotkaio/competition_math")
result = metric.compute(predictions=preds, references=refs)
print(result)
```
## Don'ts
- Don't assume your in-house `dotkaio/competition_math` matches HF — version conventions vary.
- Many evaluate metrics have task-specific arguments (`average=`, `lang=`, `model_type=`); read the metric card before reporting numbers.
