Posicube Mean Reciprocal Rank

---
name: posicube-mean-reciprocal-rank
description: Compute posicube/mean_reciprocal_rank via the HuggingFace `evaluate` library. Use when the user has predictions + references and wants the canonical implementation of posicube/mean_reciprocal_rank.
metadata:
  skill_kind: metric
  source_lib: huggingface-evaluate
  hf_module: posicube/mean_reciprocal_rank
  source: library_introspection
---

# posicube-mean-reciprocal-rank

> Metric `posicube/mean_reciprocal_rank` from the HuggingFace `evaluate` library.

## When to invoke

User asks to compute `posicube/mean_reciprocal_rank` or wants HF evaluate's canonical version.

## Recipe

```python
import evaluate
metric = evaluate.load("posicube/mean_reciprocal_rank")
result = metric.compute(predictions=preds, references=refs)
print(result)
```

## Don'ts

- Don't assume your in-house `posicube/mean_reciprocal_rank` matches HF — version conventions vary.
- Many evaluate metrics have task-specific arguments (`average=`, `lang=`, `model_type=`); read the metric card before reporting numbers.