# Label Homogeneity on EMBER (test)

Source: [Label Homogeneity on EMBER (test)](<https://www.sota2.com/research/sota/label-homogeneity-on-ember-test>)

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

Data updated: 2026-02-26T05:37:43.775Z

Evaluation of Label Homogeneity performance on the test split of the EMBER dataset, reporting mean and standard deviation across benign and malicious samples.

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 | Label Homogeneity |
| Dataset (including any stated split) | EMBER (test) |
| Metric | Benign Mean |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Benign Mean](<https://www.sota2.com/research/sota/label-homogeneity-on-ember-test.md?metric=Benign%20Mean>): Higher is better; unit: PERCENT.

- [Benign Std Dev](<https://www.sota2.com/research/sota/label-homogeneity-on-ember-test.md?metric=Benign%20Std%20Dev>): Lower is better; unit: SCALAR.

- [Malicious Mean](<https://www.sota2.com/research/sota/label-homogeneity-on-ember-test.md?metric=Malicious%20Mean>): Higher is better; unit: PERCENT.

- [Malicious Std Dev](<https://www.sota2.com/research/sota/label-homogeneity-on-ember-test.md?metric=Malicious%20Std%20Dev>): Lower is better; unit: SCALAR.

- [Overall Mean](<https://www.sota2.com/research/sota/label-homogeneity-on-ember-test.md?metric=Overall%20Mean>): Higher is better; unit: PERCENT.

- [Overall Std Dev](<https://www.sota2.com/research/sota/label-homogeneity-on-ember-test.md?metric=Overall%20Std%20Dev>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Benign Mean | Result date | Report paper |
| --- | --- | --- | --- |
| leaf similarity | 9280 | Not recorded | 68fa70b91e209131cea4cd58 |
| leaf similarity | 4710 | Not recorded | 68fa70b91e209131cea4cd58 |
| leaf similarity | 968 | Not recorded | 68fa70b91e209131cea4cd58 |
| leaf similarity | 100 | Not recorded | 68fa70b91e209131cea4cd58 |

### leaf similarity

Benign Mean: 9280. Result ID: 699155cd3a6c314849076728.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Implementation](<https://github.com/CrowdStrike/embersim-databank>)

Recorded evaluation configuration: {"K":100,"Similarity Method":"leaf similarity"}. This record does not assert independent reproduction.

### leaf similarity

Benign Mean: 4710. Result ID: 699155cd3a6c314849076727.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Implementation](<https://github.com/CrowdStrike/embersim-databank>)

Recorded evaluation configuration: {"K":50,"Similarity Method":"leaf similarity"}. This record does not assert independent reproduction.

### leaf similarity

Benign Mean: 968. Result ID: 699155cd3a6c314849076726.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Implementation](<https://github.com/CrowdStrike/embersim-databank>)

Recorded evaluation configuration: {"K":10,"Similarity Method":"leaf similarity"}. This record does not assert independent reproduction.

### leaf similarity

Benign Mean: 100. Result ID: 699155cd3a6c314849076725.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b91e209131cea4cd58.md>)

[Implementation](<https://github.com/CrowdStrike/embersim-databank>)

Recorded evaluation configuration: {"K":1,"Similarity Method":"leaf similarity"}. This record does not assert independent reproduction.

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