# Conformal Routing Safety Control on OpenML general-purpose (test)

Source: [Conformal Routing Safety Control on OpenML general-purpose (test)](<https://www.sota2.com/research/sota/conformal-routing-safety-control-on-openml-general-purpose-test>)

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

Data updated: 2026-03-17T10:27:22.909Z

Evaluation of Conformal Routing Safety Control performance on the test split of the OpenML general-purpose dataset, measured by violation rates.

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 | Conformal Routing Safety Control |
| Dataset (including any stated split) | OpenML general-purpose (test) |
| Metric | Violation Exceedance Count |
| 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 Exceedance Count](<https://www.sota2.com/research/sota/conformal-routing-safety-control-on-openml-general-purpose-test.md?metric=Violation%20Exceedance%20Count>): Lower is better; unit: SCALAR.

- [Violation Exceedance Rate (%)](<https://www.sota2.com/research/sota/conformal-routing-safety-control-on-openml-general-purpose-test.md?metric=Violation%20Exceedance%20Rate%20(%25)>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Violation Exceedance Count | Result date | Report paper |
| --- | --- | --- | --- |
| Gate Conformal | 0 | Not recorded | 69b8e01f0636e5bf4afbebac |
| Gate Conformal | 1 | Not recorded | 69b8e01f0636e5bf4afbebac |
| Gate Conformal | 2 | Not recorded | 69b8e01f0636e5bf4afbebac |
| Gate Conformal | 4 | Not recorded | 69b8e01f0636e5bf4afbebac |
| Reg. Conf. | 20 | Not recorded | 69b8e01f0636e5bf4afbebac |
| Naive | 39 | Not recorded | 69b8e01f0636e5bf4afbebac |
| Reg. Conf. | 48 | Not recorded | 69b8e01f0636e5bf4afbebac |
| Reg. Conf. | 50 | Not recorded | 69b8e01f0636e5bf4afbebac |
| Reg. Conf. | 50 | Not recorded | 69b8e01f0636e5bf4afbebac |
| Naive | 53 | Not recorded | 69b8e01f0636e5bf4afbebac |
| Naive | 58 | Not recorded | 69b8e01f0636e5bf4afbebac |
| Naive | 64 | Not recorded | 69b8e01f0636e5bf4afbebac |

### Gate Conformal

Violation Exceedance Count: 0. Result ID: 69b92c7847f34ce924a28566.

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

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

Recorded evaluation configuration: {"Target Alpha (α)":"0.10"}. This record does not assert independent reproduction.

### Gate Conformal

Violation Exceedance Count: 1. Result ID: 69b92c7847f34ce924a28567.

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

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

Recorded evaluation configuration: {"Target Alpha (α)":"0.20"}. This record does not assert independent reproduction.

### Gate Conformal

Violation Exceedance Count: 2. Result ID: 69b92c7847f34ce924a28568.

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

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

Recorded evaluation configuration: {"Target Alpha (α)":"0.30"}. This record does not assert independent reproduction.

### Gate Conformal

Violation Exceedance Count: 4. Result ID: 69b92c7847f34ce924a28569.

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

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

Recorded evaluation configuration: {"Target Alpha (α)":"0.50"}. This record does not assert independent reproduction.

### Reg. Conf.

Violation Exceedance Count: 20. Result ID: 69b92c7847f34ce924a2856a.

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

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

Recorded evaluation configuration: {"Target Alpha (α)":"0.10"}. This record does not assert independent reproduction.

### Naive

Violation Exceedance Count: 39. Result ID: 69b92c7847f34ce924a28571.

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

Recorded evaluation configuration: {"Target Alpha (α)":"0.50"}. This record does not assert independent reproduction.

### Reg. Conf.

Violation Exceedance Count: 48. Result ID: 69b92c7847f34ce924a2856b.

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

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

Recorded evaluation configuration: {"Target Alpha (α)":"0.20"}. This record does not assert independent reproduction.

### Reg. Conf.

Violation Exceedance Count: 50. Result ID: 69b92c7847f34ce924a2856c.

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

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

Recorded evaluation configuration: {"Target Alpha (α)":"0.30"}. This record does not assert independent reproduction.

### Reg. Conf.

Violation Exceedance Count: 50. Result ID: 69b92c7847f34ce924a2856d.

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

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

Recorded evaluation configuration: {"Target Alpha (α)":"0.50"}. This record does not assert independent reproduction.

### Naive

Violation Exceedance Count: 53. Result ID: 69b92c7847f34ce924a28570.

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

Recorded evaluation configuration: {"Target Alpha (α)":"0.30"}. This record does not assert independent reproduction.

### Naive

Violation Exceedance Count: 58. Result ID: 69b92c7847f34ce924a2856f.

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

Recorded evaluation configuration: {"Target Alpha (α)":"0.20"}. This record does not assert independent reproduction.

### Naive

Violation Exceedance Count: 64. Result ID: 69b92c7847f34ce924a2856e.

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

Recorded evaluation configuration: {"Target Alpha (α)":"0.10"}. This record does not assert independent reproduction.

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