# Classification on DN-sketch (test)

Source: [Classification on DN-sketch (test)](<https://www.sota2.com/research/sota/classification-on-dn-sketch-test>)

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

Data updated: 2026-02-26T06:06:18.585Z

Evaluation of Classification performance on the test split of the DN-sketch dataset, typically measured by test loss.

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) | DN-sketch (test) |
| Metric | Test Loss |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 13 of 13 |
| 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

- [Test Loss](<https://www.sota2.com/research/sota/classification-on-dn-sketch-test.md?metric=Test%20Loss>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Test Loss | Result date | Report paper |
| --- | --- | --- | --- |
| RW | 0.869 | Not recorded | 68fa6ca11e209131cea3513f |
| WM | 0.894 | Not recorded | 68fa6ca11e209131cea3513f |
| IF | 0.926 | Not recorded | 68fa6ca11e209131cea3513f |
| WM | 0.989 | Not recorded | 68fa6ca11e209131cea3513f |
| RW | 0.993 | Not recorded | 68fa6ca11e209131cea3513f |
| IF | 1.058 | Not recorded | 68fa6ca11e209131cea3513f |
| WM | 1.065 | Not recorded | 68fa6ca11e209131cea3513f |
| IF | 1.089 | Not recorded | 68fa6ca11e209131cea3513f |
| RW | 1.093 | Not recorded | 68fa6ca11e209131cea3513f |
| GIF | 1.245 | Not recorded | 68fa6ca11e209131cea3513f |
| ERM | 1.263 | Not recorded | 68fa6ca11e209131cea3513f |
| ERM | 1.502 | Not recorded | 68fa6ca11e209131cea3513f |
| ERM | 1.579 | Not recorded | 68fa6ca11e209131cea3513f |

### RW

Test Loss: 0.869. Result ID: 698f297c3a6c314849f67078.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ca11e209131cea3513f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ca11e209131cea3513f.md>)

Recorded evaluation configuration: {"Aggregation":"MV"}. This record does not assert independent reproduction.

### WM

Test Loss: 0.894. Result ID: 698f297c3a6c314849f67079.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ca11e209131cea3513f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ca11e209131cea3513f.md>)

Recorded evaluation configuration: {"Aggregation":"MV"}. This record does not assert independent reproduction.

### IF

Test Loss: 0.926. Result ID: 698f297c3a6c314849f67076.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ca11e209131cea3513f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ca11e209131cea3513f.md>)

Recorded evaluation configuration: {"Aggregation":"MV"}. This record does not assert independent reproduction.

### WM

Test Loss: 0.989. Result ID: 698f297c3a6c314849f67081.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ca11e209131cea3513f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ca11e209131cea3513f.md>)

Recorded evaluation configuration: {"Aggregation":"Snorkel"}. This record does not assert independent reproduction.

### RW

Test Loss: 0.993. Result ID: 698f297c3a6c314849f67080.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ca11e209131cea3513f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ca11e209131cea3513f.md>)

Recorded evaluation configuration: {"Aggregation":"Snorkel"}. This record does not assert independent reproduction.

### IF

Test Loss: 1.058. Result ID: 698f297c3a6c314849f6707b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ca11e209131cea3513f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ca11e209131cea3513f.md>)

Recorded evaluation configuration: {"Aggregation":"DS"}. This record does not assert independent reproduction.

### WM

Test Loss: 1.065. Result ID: 698f297c3a6c314849f6707d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ca11e209131cea3513f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ca11e209131cea3513f.md>)

Recorded evaluation configuration: {"Aggregation":"DS"}. This record does not assert independent reproduction.

### IF

Test Loss: 1.089. Result ID: 698f297c3a6c314849f6707f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ca11e209131cea3513f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ca11e209131cea3513f.md>)

Recorded evaluation configuration: {"Aggregation":"Snorkel"}. This record does not assert independent reproduction.

### RW

Test Loss: 1.093. Result ID: 698f297c3a6c314849f6707c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ca11e209131cea3513f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ca11e209131cea3513f.md>)

Recorded evaluation configuration: {"Aggregation":"DS"}. This record does not assert independent reproduction.

### GIF

Test Loss: 1.245. Result ID: 698f297c3a6c314849f67077.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ca11e209131cea3513f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66ad1e209131cea11a41.md>)

Recorded evaluation configuration: {"Aggregation":"MV"}. This record does not assert independent reproduction.

### ERM

Test Loss: 1.263. Result ID: 698f297c3a6c314849f67075.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ca11e209131cea3513f.md>)

Recorded evaluation configuration: {"Aggregation":"MV"}. This record does not assert independent reproduction.

### ERM

Test Loss: 1.502. Result ID: 698f297c3a6c314849f6707e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ca11e209131cea3513f.md>)

Recorded evaluation configuration: {"Aggregation":"Snorkel"}. This record does not assert independent reproduction.

### ERM

Test Loss: 1.579. Result ID: 698f297c3a6c314849f6707a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ca11e209131cea3513f.md>)

Recorded evaluation configuration: {"Aggregation":"DS"}. This record does not assert independent reproduction.

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