# Handwritten Mathematical Expression Recognition on OffRaSHME (val)

Source: [Handwritten Mathematical Expression Recognition on OffRaSHME (val)](<https://www.sota2.com/research/sota/handwritten-mathematical-expression-recognition-on-offrashme-val>)

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

Data updated: 2026-02-26T05:58:47.291Z

Evaluation of Handwritten Mathematical Expression Recognition performance on the validation split of the OffRaSHME dataset, using Precision, Recall, and F-measure.

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 | Handwritten Mathematical Expression Recognition |
| Dataset (including any stated split) | OffRaSHME (val) |
| Metric | Precision (%) |
| 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

- [Precision (%)](<https://www.sota2.com/research/sota/handwritten-mathematical-expression-recognition-on-offrashme-val.md?metric=Precision%20(%25)>): Higher is better; unit: PERCENT.

- [Recall (%)](<https://www.sota2.com/research/sota/handwritten-mathematical-expression-recognition-on-offrashme-val.md?metric=Recall%20(%25)>): Higher is better; unit: PERCENT.

- [F1 Score (%)](<https://www.sota2.com/research/sota/handwritten-mathematical-expression-recognition-on-offrashme-val.md?metric=F1%20Score%20(%25)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Precision (%) | Result date | Report paper |
| --- | --- | --- | --- |
| ADP | 94 | Not recorded | 68fa6a1f1e209131cea2619b |
| WAP + TD | 93.43 | Not recorded | 68fa6a1f1e209131cea2619b |
| WAP | 89.49 | Not recorded | 68fa6a1f1e209131cea2619b |
| ExCTC | 29.96 | Not recorded | 68fa6a1f1e209131cea2619b |

### ADP

Precision (%): 94. Result ID: 698e10caffc3901de09a8572.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a1f1e209131cea2619b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a1f1e209131cea2619b.md>)

[Implementation](<https://github.com/Wang-Tianwei/Implicit-feature-alignment>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### WAP + TD

Precision (%): 93.43. Result ID: 698e10caffc3901de09a8570.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a1f1e209131cea2619b.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### WAP

Precision (%): 89.49. Result ID: 698e10caffc3901de09a856f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a1f1e209131cea2619b.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ExCTC

Precision (%): 29.96. Result ID: 698e10caffc3901de09a8571.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a1f1e209131cea2619b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a1f1e209131cea2619b.md>)

[Implementation](<https://github.com/Wang-Tianwei/Implicit-feature-alignment>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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