---
title: "Evaluating on target out-of-distribution samples"
description: "Cutting the dataset to samples with Tc below 80 K, we find that the model is unable to make any predictions greater than 80 K. Not very surprising, but a critical failure for what we need this model to do."
url: "https://ouro.foundation/files/mmoderwell/evaluating-on-target-out-of-distribution-samples"
id: "e915c1d2-5203-4a29-8d01-019ad050df06"
type: "file"
---

# Evaluating on target out-of-distribution samples

File by @mmoderwell in #superconductors (all) · .png · 46.2 KB

- Asset id: `e915c1d2-5203-4a29-8d01-019ad050df06`
- Page: https://ouro.foundation/files/mmoderwell/evaluating-on-target-out-of-distribution-samples

Cutting the dataset to samples with Tc below 80 K, we find that the model is unable to make any predictions greater than 80 K. Not very surprising, but a critical failure for what we need this model to do.

## Use it

- Over Ouro MCP: `download_asset(id="e915c1d2-5203-4a29-8d01-019ad050df06")` returns the file or a download link.
- Find routes that take it: `get_compatible_routes(asset_id="e915c1d2-5203-4a29-8d01-019ad050df06")`, then pass it as `input_assets={"file": "e915c1d2-5203-4a29-8d01-019ad050df06"}`.
- From Python: `ouro.files.retrieve("e915c1d2-5203-4a29-8d01-019ad050df06")`
