# Selective Classification Routing on 35 datasets (test)

Source: [Selective Classification Routing on 35 datasets (test)](<https://www.sota2.com/research/sota/selective-classification-routing-on-35-datasets-test>)

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

Data updated: 2026-03-17T10:27:22.889Z

Evaluation of Selective Classification Routing performance on the test split of the 35 datasets collection, measured by Violation Rate Exceedance.

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 | Selective Classification Routing |
| Dataset (including any stated split) | 35 datasets (test) |
| Metric | Violation Rate Exceedance |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 12 of 12 |
| 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

- [Violation Rate Exceedance](<https://www.sota2.com/research/sota/selective-classification-routing-on-35-datasets-test.md?metric=Violation%20Rate%20Exceedance>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Violation Rate Exceedance | Result date | Report paper |
| --- | --- | --- | --- |
| Gate Conformal | 6 | Not recorded | 69b8e01f0636e5bf4afbebac |
| Gate Conformal | 7 | Not recorded | 69b8e01f0636e5bf4afbebac |
| Gate Conformal | 8 | Not recorded | 69b8e01f0636e5bf4afbebac |
| Gate Conformal | 8 | Not recorded | 69b8e01f0636e5bf4afbebac |
| Regression Conformal | 31 | Not recorded | 69b8e01f0636e5bf4afbebac |
| Regression Conformal | 57 | Not recorded | 69b8e01f0636e5bf4afbebac |
| Naive | 62 | Not recorded | 69b8e01f0636e5bf4afbebac |
| Regression Conformal | 64 | Not recorded | 69b8e01f0636e5bf4afbebac |
| Regression Conformal | 80 | Not recorded | 69b8e01f0636e5bf4afbebac |
| Naive | 106 | Not recorded | 69b8e01f0636e5bf4afbebac |
| Naive | 128 | Not recorded | 69b8e01f0636e5bf4afbebac |
| Naive | 151 | Not recorded | 69b8e01f0636e5bf4afbebac |

### Gate Conformal

Violation Rate Exceedance: 6. Result ID: 69b92c7847f34ce924a28560.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e01f0636e5bf4afbebac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e01f0636e5bf4afbebac.md>)

Recorded evaluation configuration: {"alpha":"0.30"}. This record does not assert independent reproduction.

### Gate Conformal

Violation Rate Exceedance: 7. Result ID: 69b92c7847f34ce924a2855a.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e01f0636e5bf4afbebac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e01f0636e5bf4afbebac.md>)

Recorded evaluation configuration: {"alpha":"0.10"}. This record does not assert independent reproduction.

### Gate Conformal

Violation Rate Exceedance: 8. Result ID: 69b92c7847f34ce924a2855d.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e01f0636e5bf4afbebac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e01f0636e5bf4afbebac.md>)

Recorded evaluation configuration: {"alpha":"0.20"}. This record does not assert independent reproduction.

### Gate Conformal

Violation Rate Exceedance: 8. Result ID: 69b92c7847f34ce924a28563.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e01f0636e5bf4afbebac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e01f0636e5bf4afbebac.md>)

Recorded evaluation configuration: {"alpha":"0.50"}. This record does not assert independent reproduction.

### Regression Conformal

Violation Rate Exceedance: 31. Result ID: 69b92c7847f34ce924a2855b.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e01f0636e5bf4afbebac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa53bd1e209131ce985990.md>)

Recorded evaluation configuration: {"alpha":"0.10"}. This record does not assert independent reproduction.

### Regression Conformal

Violation Rate Exceedance: 57. Result ID: 69b92c7847f34ce924a2855e.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e01f0636e5bf4afbebac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa53bd1e209131ce985990.md>)

Recorded evaluation configuration: {"alpha":"0.20"}. This record does not assert independent reproduction.

### Naive

Violation Rate Exceedance: 62. Result ID: 69b92c7847f34ce924a28565.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e01f0636e5bf4afbebac.md>)

Recorded evaluation configuration: {"alpha":"0.50"}. This record does not assert independent reproduction.

### Regression Conformal

Violation Rate Exceedance: 64. Result ID: 69b92c7847f34ce924a28564.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e01f0636e5bf4afbebac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa53bd1e209131ce985990.md>)

Recorded evaluation configuration: {"alpha":"0.50"}. This record does not assert independent reproduction.

### Regression Conformal

Violation Rate Exceedance: 80. Result ID: 69b92c7847f34ce924a28561.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e01f0636e5bf4afbebac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa53bd1e209131ce985990.md>)

Recorded evaluation configuration: {"alpha":"0.30"}. This record does not assert independent reproduction.

### Naive

Violation Rate Exceedance: 106. Result ID: 69b92c7847f34ce924a28562.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e01f0636e5bf4afbebac.md>)

Recorded evaluation configuration: {"alpha":"0.30"}. This record does not assert independent reproduction.

### Naive

Violation Rate Exceedance: 128. Result ID: 69b92c7847f34ce924a2855f.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e01f0636e5bf4afbebac.md>)

Recorded evaluation configuration: {"alpha":"0.20"}. This record does not assert independent reproduction.

### Naive

Violation Rate Exceedance: 151. Result ID: 69b92c7847f34ce924a2855c.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e01f0636e5bf4afbebac.md>)

Recorded evaluation configuration: {"alpha":"0.10"}. This record does not assert independent reproduction.

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