# Imagination Board Reconstruction on MNIST 8-puzzle Clean

Source: [Imagination Board Reconstruction on MNIST 8-puzzle Clean](<https://www.sota2.com/research/sota/imagination-board-reconstruction-on-mnist-8-puzzle-clean>)

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

Data updated: 2026-03-04T16:11:08.247Z

Evaluation of model performance on reconstructing the target board configuration for the 8-puzzle problem, using the cleaned MNIST subset, measured by F1-score.

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 | Imagination Board Reconstruction |
| Dataset (including any stated split) | MNIST 8-puzzle Clean |
| Metric | F1 Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [F1 Score](<https://www.sota2.com/research/sota/imagination-board-reconstruction-on-mnist-8-puzzle-clean.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | F1 Score | Result date | Report paper |
| --- | --- | --- | --- |
| DWMR+β-VAE | 91 | Not recorded | 69a66c662d603e6de3e3d2cf |
| DWMR+AE | 86 | Not recorded | 69a66c662d603e6de3e3d2cf |
| DWMR | 84 | Not recorded | 69a66c662d603e6de3e3d2cf |
| DeepcubeAI | 77 | Not recorded | 69a66c662d603e6de3e3d2cf |
| β-VAE | 61 | Not recorded | 69a66c662d603e6de3e3d2cf |
| AE | 36 | Not recorded | 69a66c662d603e6de3e3d2cf |

### DWMR+β-VAE

F1 Score: 91. Result ID: 69a859906dbb7075b94fbbd3.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c662d603e6de3e3d2cf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a66c662d603e6de3e3d2cf.md>)

Recorded evaluation configuration: {"Probe":"Linear","Runs":"10"}. This record does not assert independent reproduction.

### DWMR+AE

F1 Score: 86. Result ID: 69a859906dbb7075b94fbbd2.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c662d603e6de3e3d2cf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a66c662d603e6de3e3d2cf.md>)

Recorded evaluation configuration: {"Probe":"Linear","Runs":"10"}. This record does not assert independent reproduction.

### DWMR

F1 Score: 84. Result ID: 69a859906dbb7075b94fbbd1.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c662d603e6de3e3d2cf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a66c662d603e6de3e3d2cf.md>)

Recorded evaluation configuration: {"Probe":"Linear","Runs":"10"}. This record does not assert independent reproduction.

### DeepcubeAI

F1 Score: 77. Result ID: 69a859906dbb7075b94fbbd0.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c662d603e6de3e3d2cf.md>)

Recorded evaluation configuration: {"Probe":"Linear","Runs":"10"}. This record does not assert independent reproduction.

### β-VAE

F1 Score: 61. Result ID: 69a859906dbb7075b94fbbcf.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c662d603e6de3e3d2cf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cbf1e209131cea35c07.md>)

Recorded evaluation configuration: {"Probe":"Linear","Runs":"10"}. This record does not assert independent reproduction.

### AE

F1 Score: 36. Result ID: 69a859906dbb7075b94fbbce.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c662d603e6de3e3d2cf.md>)

Recorded evaluation configuration: {"Probe":"Linear","Runs":"10"}. This record does not assert independent reproduction.

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