# Semantic Decomposition on WordNet Decomposition Dataset (test)

Source: [Semantic Decomposition on WordNet Decomposition Dataset (test)](<https://www.sota2.com/research/sota/semantic-decomposition-on-wordnet-decomposition-dataset-test>)

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

Data updated: 2026-02-26T05:52:16.439Z

Evaluation of Semantic Decomposition performance on the test split of the WordNet Decomposition Dataset, typically measured using ranking metrics like Mean Rank and Top-K accuracy.

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 | Semantic Decomposition |
| Dataset (including any stated split) | WordNet Decomposition Dataset (test) |
| Metric | Mean Rank (k=2000) |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 10 of 10 |
| 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

- [Mean Rank (k=2000)](<https://www.sota2.com/research/sota/semantic-decomposition-on-wordnet-decomposition-dataset-test.md?metric=Mean%20Rank%20(k%3D2000)>): Lower is better; unit: SCALAR.

- [Median Rank (k=2000)](<https://www.sota2.com/research/sota/semantic-decomposition-on-wordnet-decomposition-dataset-test.md?metric=Median%20Rank%20(k%3D2000)>): Lower is better; unit: SCALAR.

- [Top-1 Accuracy](<https://www.sota2.com/research/sota/semantic-decomposition-on-wordnet-decomposition-dataset-test.md?metric=Top-1%20Accuracy>): Higher is better; unit: PERCENT.

- [Top-10 Accuracy](<https://www.sota2.com/research/sota/semantic-decomposition-on-wordnet-decomposition-dataset-test.md?metric=Top-10%20Accuracy>): Higher is better; unit: PERCENT.

- [Top-100 Accuracy](<https://www.sota2.com/research/sota/semantic-decomposition-on-wordnet-decomposition-dataset-test.md?metric=Top-100%20Accuracy>): Higher is better; unit: PERCENT.

- [Top-2000 Accuracy](<https://www.sota2.com/research/sota/semantic-decomposition-on-wordnet-decomposition-dataset-test.md?metric=Top-2000%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Mean Rank (k=2000) | Result date | Report paper |
| --- | --- | --- | --- |
| Holistic | 58 | Not recorded | 68fa61611e209131ce9f3d33 |
| Super | 60 | Not recorded | 68fa61611e209131ce9f3d33 |
| Super | 80 | Not recorded | 68fa61611e209131ce9f3d33 |
| Holistic | 81 | Not recorded | 68fa61611e209131ce9f3d33 |
| Addition | 103 | Not recorded | 68fa61611e209131ce9f3d33 |
| Multiplication | 165 | Not recorded | 68fa61611e209131ce9f3d33 |
| Comp | 198 | Not recorded | 68fa61611e209131ce9f3d33 |
| Decomp | 250 | Not recorded | 68fa61611e209131ce9f3d33 |
| Addition | 433 | Not recorded | 68fa61611e209131ce9f3d33 |
| Multiplication | 543 | Not recorded | 68fa61611e209131ce9f3d33 |

### Holistic

Mean Rank (k=2000): 58. Result ID: 698bcc2d7a967eddb7716b2b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa61611e209131ce9f3d33.md>)

Recorded evaluation configuration: {"Number of candidates considered":"36,149"}. This record does not assert independent reproduction.

### Super

Mean Rank (k=2000): 60. Result ID: 698c65ed37894ef7d9ce1659.

[Reporting paper](<https://www.sota2.com/research/paper/68fa61611e209131ce9f3d33.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61611e209131ce9f3d33.md>)

Recorded evaluation configuration: {"Number of candidates considered":"2,000"}. This record does not assert independent reproduction.

### Super

Mean Rank (k=2000): 80. Result ID: 698bcc2d7a967eddb7716b28.

[Reporting paper](<https://www.sota2.com/research/paper/68fa61611e209131ce9f3d33.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61611e209131ce9f3d33.md>)

Recorded evaluation configuration: {"Number of candidates considered":"2000"}. This record does not assert independent reproduction.

### Holistic

Mean Rank (k=2000): 81. Result ID: 698c65ed37894ef7d9ce165c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa61611e209131ce9f3d33.md>)

Recorded evaluation configuration: {"Number of candidates considered":"72,924"}. This record does not assert independent reproduction.

### Addition

Mean Rank (k=2000): 103. Result ID: 698c65ed37894ef7d9ce165a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa61611e209131ce9f3d33.md>)

Recorded evaluation configuration: {"Number of candidates considered":"2,000"}. This record does not assert independent reproduction.

### Multiplication

Mean Rank (k=2000): 165. Result ID: 698c65ed37894ef7d9ce165b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa61611e209131ce9f3d33.md>)

Recorded evaluation configuration: {"Number of candidates considered":"2,000"}. This record does not assert independent reproduction.

### Comp

Mean Rank (k=2000): 198. Result ID: 698c65ed37894ef7d9ce1658.

[Reporting paper](<https://www.sota2.com/research/paper/68fa61611e209131ce9f3d33.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61611e209131ce9f3d33.md>)

Recorded evaluation configuration: {"Number of candidates considered":"72,924"}. This record does not assert independent reproduction.

### Decomp

Mean Rank (k=2000): 250. Result ID: 698bcc2d7a967eddb7716b27.

[Reporting paper](<https://www.sota2.com/research/paper/68fa61611e209131ce9f3d33.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61611e209131ce9f3d33.md>)

Recorded evaluation configuration: {"Number of candidates considered":"5.3 × 10^9"}. This record does not assert independent reproduction.

### Addition

Mean Rank (k=2000): 433. Result ID: 698bcc2d7a967eddb7716b29.

[Reporting paper](<https://www.sota2.com/research/paper/68fa61611e209131ce9f3d33.md>)

Recorded evaluation configuration: {"Number of candidates considered":"2000"}. This record does not assert independent reproduction.

### Multiplication

Mean Rank (k=2000): 543. Result ID: 698bcc2d7a967eddb7716b2a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa61611e209131ce9f3d33.md>)

Recorded evaluation configuration: {"Number of candidates considered":"2000"}. This record does not assert independent reproduction.

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