# Domain Adaptation on Synthetic Benchmark

Source: [Domain Adaptation on Synthetic Benchmark](<https://www.sota2.com/research/sota/domain-adaptation-on-synthetic-benchmark>)

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

Data updated: 2026-03-26T13:38:27.223Z

Evaluation of Domain Adaptation performance on the Synthetic Benchmark, reporting metrics related to Geometry, Risk, Variance, and Energy.

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 | Domain Adaptation |
| Dataset (including any stated split) | Synthetic Benchmark |
| Metric | Geometry Score |
| 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

- [Geometry Score](<https://www.sota2.com/research/sota/domain-adaptation-on-synthetic-benchmark.md?metric=Geometry%20Score>): Higher is better; unit: PERCENT.

- [Risk Score](<https://www.sota2.com/research/sota/domain-adaptation-on-synthetic-benchmark.md?metric=Risk%20Score>): Lower is better; unit: PERCENT.

- [Variance](<https://www.sota2.com/research/sota/domain-adaptation-on-synthetic-benchmark.md?metric=Variance>): Lower is better; unit: SCALAR.

- [Energy Score](<https://www.sota2.com/research/sota/domain-adaptation-on-synthetic-benchmark.md?metric=Energy%20Score>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Geometry Score | Result date | Report paper |
| --- | --- | --- | --- |
| Finetune | 58 | Not recorded | 69c4bd760636e5bf4afc750f |
| DANN | 44 | Not recorded | 69c4bd760636e5bf4afc750f |
| Bayesian DA | 39 | Not recorded | 69c4bd760636e5bf4afc750f |
| Probabilistic Latent Transport | 27 | Not recorded | 69c4bd760636e5bf4afc750f |

### Finetune

Geometry Score: 58. Result ID: 69c536bc47f34ce924aed72e.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bd760636e5bf4afc750f.md>)

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

### DANN

Geometry Score: 44. Result ID: 69c536bc47f34ce924aed72f.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bd760636e5bf4afc750f.md>)

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

### Bayesian DA

Geometry Score: 39. Result ID: 69c536bc47f34ce924aed730.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bd760636e5bf4afc750f.md>)

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

### Probabilistic Latent Transport

Geometry Score: 27. Result ID: 69c536bc47f34ce924aed731.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bd760636e5bf4afc750f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c4bd760636e5bf4afc750f.md>)

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.
