# Classification on BLM crystal collimator dataset

Source: [Classification on BLM crystal collimator dataset](<https://www.sota2.com/research/sota/classification-on-blm-crystal-collimator-dataset>)

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

Data updated: 2026-04-09T23:17:57.472Z

Evaluation of Classification performance on the BLM crystal collimator dataset, reporting Clean accuracy and Relative Accuracy (RA) metrics.

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 | Classification |
| Dataset (including any stated split) | BLM crystal collimator dataset |
| Metric | Clean Accuracy |
| 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

- [Clean Accuracy](<https://www.sota2.com/research/sota/classification-on-blm-crystal-collimator-dataset.md?metric=Clean%20Accuracy>): Higher is better; unit: PERCENT.

- [Relative Accuracy @ 0.05](<https://www.sota2.com/research/sota/classification-on-blm-crystal-collimator-dataset.md?metric=Relative%20Accuracy%20%40%200.05>): Higher is better; unit: PERCENT.

- [Relative Accuracy @ 0.10](<https://www.sota2.com/research/sota/classification-on-blm-crystal-collimator-dataset.md?metric=Relative%20Accuracy%20%40%200.10>): Higher is better; unit: PERCENT.

- [Relative Accuracy @ 0.20](<https://www.sota2.com/research/sota/classification-on-blm-crystal-collimator-dataset.md?metric=Relative%20Accuracy%20%40%200.20>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Clean Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Adv-trained (fine-tune) | 94.3 | Not recorded | 69d7326a7d0172140ec769b5 |
| Baseline | 93.9 | Not recorded | 69d7326a7d0172140ec769b5 |

### Adv-trained (fine-tune)

Clean Accuracy: 94.3. Result ID: 69d8327747f34ce924bfdae1.

[Reporting paper](<https://www.sota2.com/research/paper/69d7326a7d0172140ec769b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d7326a7d0172140ec769b5.md>)

Recorded evaluation configuration: {"training strategy":"Adversarial training (fine-tune)"}. This record does not assert independent reproduction.

### Baseline

Clean Accuracy: 93.9. Result ID: 69d8327747f34ce924bfdae0.

[Reporting paper](<https://www.sota2.com/research/paper/69d7326a7d0172140ec769b5.md>)

Recorded evaluation configuration: {"training strategy":"Standard baseline training"}. This record does not assert independent reproduction.

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