# Causal Graph Discovery on Asia (8 nodes, 8 edges)

Source: [Causal Graph Discovery on Asia (8 nodes, 8 edges)](<https://www.sota2.com/research/sota/causal-graph-discovery-on-asia-8-nodes-8-edges>)

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

Data updated: 2026-04-06T07:15:01.486Z

Evaluation of Causal Graph Discovery methods on the specific small-scale Asia graph configuration defined by 8 nodes and 8 edges, measured using Accuracy, F Score, NPE, and Ratio.

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 | Causal Graph Discovery |
| Dataset (including any stated split) | Asia 8 nodes, 8 edges |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 18 of 18 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/causal-graph-discovery-on-asia-8-nodes-8-edges.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [F Score](<https://www.sota2.com/research/sota/causal-graph-discovery-on-asia-8-nodes-8-edges.md?metric=F%20Score>): Higher is better; unit: PERCENT.

- [NPE](<https://www.sota2.com/research/sota/causal-graph-discovery-on-asia-8-nodes-8-edges.md?metric=NPE>): Lower is better; unit: SCALAR.

- [Ratio](<https://www.sota2.com/research/sota/causal-graph-discovery-on-asia-8-nodes-8-edges.md?metric=Ratio>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| BFS with LLMs | 88 | Not recorded | 68fa74351e209131cea60743 |
| BFS with LLMs | 80 | Not recorded | 68fa74351e209131cea60743 |
| BFS with LLMs | 80 | Not recorded | 68fa74351e209131cea60743 |
| GES | 70 | Not recorded | 68fa74351e209131cea60743 |
| GES | 67 | Not recorded | 68fa74351e209131cea60743 |
| PC | 55 | Not recorded | 68fa74351e209131cea60743 |
| NOTEARS | 50 | Not recorded | 68fa74351e209131cea60743 |
| PC | 50 | Not recorded | 68fa74351e209131cea60743 |
| DAGMA | 50 | Not recorded | 68fa74351e209131cea60743 |
| DAGMA | 50 | Not recorded | 68fa74351e209131cea60743 |
| Pairwise | 47 | Not recorded | 68fa74351e209131cea60743 |
| NOTEARS | 44 | Not recorded | 68fa74351e209131cea60743 |
| NOTEARS | 44 | Not recorded | 68fa74351e209131cea60743 |
| Pairwise | 38 | Not recorded | 68fa74351e209131cea60743 |
| PC | 33 | Not recorded | 68fa74351e209131cea60743 |
| Pairwise | 33 | Not recorded | 68fa74351e209131cea60743 |
| GES | 23 | Not recorded | 68fa74351e209131cea60743 |
| DAGMA | 22 | Not recorded | 68fa74351e209131cea60743 |

### BFS with LLMs

Accuracy: 88. Result ID: 69d35d0d47f34ce924bab653.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74351e209131cea60743.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74351e209131cea60743.md>)

Recorded evaluation configuration: {"# of Samples":"100"}. This record does not assert independent reproduction.

### BFS with LLMs

Accuracy: 80. Result ID: 69d35d0d47f34ce924bab659.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74351e209131cea60743.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74351e209131cea60743.md>)

Recorded evaluation configuration: {"# of Samples":"1000"}. This record does not assert independent reproduction.

### BFS with LLMs

Accuracy: 80. Result ID: 69d35d0d47f34ce924bab65f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74351e209131cea60743.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74351e209131cea60743.md>)

Recorded evaluation configuration: {"# of Samples":"10000"}. This record does not assert independent reproduction.

### GES

Accuracy: 70. Result ID: 69d35d0d47f34ce924bab65a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74351e209131cea60743.md>)

Recorded evaluation configuration: {"# of Samples":"10000"}. This record does not assert independent reproduction.

### GES

Accuracy: 67. Result ID: 69d35d0d47f34ce924bab654.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74351e209131cea60743.md>)

Recorded evaluation configuration: {"# of Samples":"1000"}. This record does not assert independent reproduction.

### PC

Accuracy: 55. Result ID: 69d35d0d47f34ce924bab65b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74351e209131cea60743.md>)

Recorded evaluation configuration: {"# of Samples":"10000"}. This record does not assert independent reproduction.

### NOTEARS

Accuracy: 50. Result ID: 69d35d0d47f34ce924bab650.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74351e209131cea60743.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65041e209131cea07e92.md>)

Recorded evaluation configuration: {"# of Samples":"100"}. This record does not assert independent reproduction.

### PC

Accuracy: 50. Result ID: 69d35d0d47f34ce924bab655.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74351e209131cea60743.md>)

Recorded evaluation configuration: {"# of Samples":"1000"}. This record does not assert independent reproduction.

### DAGMA

Accuracy: 50. Result ID: 69d35d0d47f34ce924bab657.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74351e209131cea60743.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e5b1e209131cea3f52d.md>)

[Implementation](<https://github.com/kevinsbello/dagma>)

Recorded evaluation configuration: {"# of Samples":"1000"}. This record does not assert independent reproduction.

### DAGMA

Accuracy: 50. Result ID: 69d35d0d47f34ce924bab65d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74351e209131cea60743.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e5b1e209131cea3f52d.md>)

[Implementation](<https://github.com/kevinsbello/dagma>)

Recorded evaluation configuration: {"# of Samples":"10000"}. This record does not assert independent reproduction.

### Pairwise

Accuracy: 47. Result ID: 69d35d0d47f34ce924bab65e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74351e209131cea60743.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74811e209131cea62098.md>)

Recorded evaluation configuration: {"# of Samples":"10000"}. This record does not assert independent reproduction.

### NOTEARS

Accuracy: 44. Result ID: 69d35d0d47f34ce924bab656.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74351e209131cea60743.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65041e209131cea07e92.md>)

Recorded evaluation configuration: {"# of Samples":"1000"}. This record does not assert independent reproduction.

### NOTEARS

Accuracy: 44. Result ID: 69d35d0d47f34ce924bab65c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74351e209131cea60743.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65041e209131cea07e92.md>)

Recorded evaluation configuration: {"# of Samples":"10000"}. This record does not assert independent reproduction.

### Pairwise

Accuracy: 38. Result ID: 69d35d0d47f34ce924bab658.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74351e209131cea60743.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74811e209131cea62098.md>)

Recorded evaluation configuration: {"# of Samples":"1000"}. This record does not assert independent reproduction.

### PC

Accuracy: 33. Result ID: 69d35d0d47f34ce924bab64f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74351e209131cea60743.md>)

Recorded evaluation configuration: {"# of Samples":"100"}. This record does not assert independent reproduction.

### Pairwise

Accuracy: 33. Result ID: 69d35d0d47f34ce924bab652.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74351e209131cea60743.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74811e209131cea62098.md>)

Recorded evaluation configuration: {"# of Samples":"100"}. This record does not assert independent reproduction.

### GES

Accuracy: 23. Result ID: 69d35d0d47f34ce924bab64e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74351e209131cea60743.md>)

Recorded evaluation configuration: {"# of Samples":"100"}. This record does not assert independent reproduction.

### DAGMA

Accuracy: 22. Result ID: 69d35d0d47f34ce924bab651.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74351e209131cea60743.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e5b1e209131cea3f52d.md>)

[Implementation](<https://github.com/kevinsbello/dagma>)

Recorded evaluation configuration: {"# of Samples":"100"}. This record does not assert independent reproduction.

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