# Edge Recovery on SBG 32 graphs, 20 win. size (test)

Source: [Edge Recovery on SBG 32 graphs, 20 win. size (test)](<https://www.sota2.com/research/sota/edge-recovery-on-sbg-32-graphs-20-win-size-test>)

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

Data updated: 2026-06-08T06:12:39.589Z

Evaluation of Edge Recovery performance on the SBG dataset subset configured with 32 graphs and a window size of 20, using the test split. Performance is measured using MCC, Precision, and Recall.

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 | Edge Recovery |
| Dataset (including any stated split) | SBG 32 graphs, 20 win. size (test) |
| Metric | MCC |
| 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

- [MCC](<https://www.sota2.com/research/sota/edge-recovery-on-sbg-32-graphs-20-win-size-test.md?metric=MCC>): Higher is better; unit: PERCENT.

- [Precision](<https://www.sota2.com/research/sota/edge-recovery-on-sbg-32-graphs-20-win-size-test.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/edge-recovery-on-sbg-32-graphs-20-win-size-test.md?metric=Recall>): Higher is better; unit: PERCENT.

## Recorded results

| Method | MCC | Result date | Report paper |
| --- | --- | --- | --- |
| GraphDictLog | 48.1 | Not recorded | 68fa75971e209131cea68d1c |
| WindowLogModel | 33.6 | Not recorded | 68fa75971e209131cea68d1c |
| GraphDictHier | 32.8 | Not recorded | 68fa75971e209131cea68d1c |
| GraphDictSpectral | 29.6 | Not recorded | 68fa75971e209131cea68d1c |
| TGFA | 14 | Not recorded | 68fa75971e209131cea68d1c |

### GraphDictLog

MCC: 48.1. Result ID: 6a265d54fbc373592c225040.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75971e209131cea68d1c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75971e209131cea68d1c.md>)

Recorded evaluation configuration: {"graphs":"32","win. size":"20"}. This record does not assert independent reproduction.

### WindowLogModel

MCC: 33.6. Result ID: 6a265d54fbc373592c22503c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75971e209131cea68d1c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65a81e209131cea0baba.md>)

Recorded evaluation configuration: {"graphs":"32","win. size":"20"}. This record does not assert independent reproduction.

### GraphDictHier

MCC: 32.8. Result ID: 6a265d54fbc373592c22503e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75971e209131cea68d1c.md>)

Recorded evaluation configuration: {"graphs":"32","win. size":"20"}. This record does not assert independent reproduction.

### GraphDictSpectral

MCC: 29.6. Result ID: 6a265d54fbc373592c22503f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75971e209131cea68d1c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75971e209131cea68d1c.md>)

Recorded evaluation configuration: {"graphs":"32","win. size":"20"}. This record does not assert independent reproduction.

### TGFA

MCC: 14. Result ID: 6a265d54fbc373592c22503d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75971e209131cea68d1c.md>)

Recorded evaluation configuration: {"graphs":"32","win. size":"20"}. This record does not assert independent reproduction.

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