# Fault Detection on Cryogenic fault scenarios n=200 (held-out)

Source: [Fault Detection on Cryogenic fault scenarios n=200 (held-out)](<https://www.sota2.com/research/sota/fault-detection-on-cryogenic-fault-scenarios-n-200-held-out>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-07-08T07:14:34.465Z

Evaluation of Fault Detection performance on the held-out split of the Cryogenic fault scenarios (n=200) dataset, reporting Detection F1 and McNemar statistics.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Fault Detection |
| Dataset (including any stated split) | Cryogenic fault scenarios n=200 (held-out) |
| Metric | Detection F1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Detection F1](<https://www.sota2.com/research/sota/fault-detection-on-cryogenic-fault-scenarios-n-200-held-out.md?metric=Detection%20F1>): Higher is better; unit: PERCENT.

- [McNemar Statistic](<https://www.sota2.com/research/sota/fault-detection-on-cryogenic-fault-scenarios-n-200-held-out.md?metric=McNemar%20Statistic>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Detection F1 | Result date | Report paper |
| --- | --- | --- | --- |
| Supervised RF | 99.7 | Not recorded | 6a4dd9b94da6617fe9198ca4 |
| Zero-shot agent | 97.9 | Not recorded | 6a4dd9b94da6617fe9198ca4 |

### Supervised RF

Detection F1: 99.7. Result ID: 6a4df8ca60b88bb339d6e2de.

[Reporting paper](<https://www.sota2.com/research/paper/6a4dd9b94da6617fe9198ca4.md>)

Recorded evaluation configuration: {"mode":"supervised"}. This record does not assert independent reproduction.

### Zero-shot agent

Detection F1: 97.9. Result ID: 6a4df8ca60b88bb339d6e2dd.

[Reporting paper](<https://www.sota2.com/research/paper/6a4dd9b94da6617fe9198ca4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a4dd9b94da6617fe9198ca4.md>)

Recorded evaluation configuration: {"mode":"zero-shot"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.