# Accuracy Estimation on GTSD D1 (test)

Source: [Accuracy Estimation on GTSD D1 (test)](<https://www.sota2.com/research/sota/accuracy-estimation-on-gtsd-d1-test>)

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

Data updated: 2026-02-26T05:25:36.428Z

Evaluation of model performance on the GTSD D1 dataset (test split) focusing on accuracy estimation capabilities, measured by metrics like Estimated Accuracy and AUPR.

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 | Accuracy Estimation |
| Dataset (including any stated split) | GTSD D1 (test) |
| Metric | AUPR |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [AUPR](<https://www.sota2.com/research/sota/accuracy-estimation-on-gtsd-d1-test.md?metric=AUPR>): Higher is better; unit: PERCENT.

- [Estimated Accuracy](<https://www.sota2.com/research/sota/accuracy-estimation-on-gtsd-d1-test.md?metric=Estimated%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AUPR | Result date | Report paper |
| --- | --- | --- | --- |
| Accuracy Monitor | 65.85 | Not recorded | 68fa67d21e209131cea18b0c |
| Entropy | 62.48 | Not recorded | 68fa67d21e209131cea18b0c |
| TS | 62.11 | Not recorded | 68fa67d21e209131cea18b0c |
| MP | 61.06 | Not recorded | 68fa67d21e209131cea18b0c |

### Accuracy Monitor

AUPR: 65.85. Result ID: 698d48b08b517eb43320599c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67d21e209131cea18b0c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67d21e209131cea18b0c.md>)

Recorded evaluation configuration: {"Target DNN":"CNN trained on GTSD","Labeled data percentage":"1%"}. This record does not assert independent reproduction.

### Entropy

AUPR: 62.48. Result ID: 698d48b08b517eb43320599e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67d21e209131cea18b0c.md>)

Recorded evaluation configuration: {"Target DNN":"CNN trained on GTSD"}. This record does not assert independent reproduction.

### TS

AUPR: 62.11. Result ID: 698d48b08b517eb43320599f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67d21e209131cea18b0c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa638b1e209131ce9ff6d1.md>)

Recorded evaluation configuration: {"Target DNN":"CNN trained on GTSD"}. This record does not assert independent reproduction.

### MP

AUPR: 61.06. Result ID: 698d48b08b517eb43320599d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67d21e209131cea18b0c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64e41e209131cea0731a.md>)

[Implementation](<https://www.sota2.com/github.com/hendrycks/error-detection>)

Recorded evaluation configuration: {"Target DNN":"CNN trained on GTSD"}. This record does not assert independent reproduction.

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