# Synthetic Data Distinguishability on ACS Census

Source: [Synthetic Data Distinguishability on ACS Census](<https://www.sota2.com/research/sota/synthetic-data-distinguishability-on-acs-census>)

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

Data updated: 2026-06-11T06:44:56.370Z

Evaluation of synthetic data distinguishability performance on the ACS Census dataset, measured using DRS C1/C2, C2ST, and Linkage metrics.

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 | Synthetic Data Distinguishability |
| Dataset (including any stated split) | ACS Census |
| Metric | DRS C1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [DRS C1](<https://www.sota2.com/research/sota/synthetic-data-distinguishability-on-acs-census.md?metric=DRS%20C1>): Higher is better; unit: PERCENT.

- [DRS C2](<https://www.sota2.com/research/sota/synthetic-data-distinguishability-on-acs-census.md?metric=DRS%20C2>): Higher is better; unit: PERCENT.

- [C2ST](<https://www.sota2.com/research/sota/synthetic-data-distinguishability-on-acs-census.md?metric=C2ST>): Higher is better; unit: SCALAR.

- [Linkage](<https://www.sota2.com/research/sota/synthetic-data-distinguishability-on-acs-census.md?metric=Linkage>): Higher is better; unit: PERCENT.

## Recorded results

| Method | DRS C1 | Result date | Report paper |
| --- | --- | --- | --- |
| CTGAN | 100 | Not recorded | 6a28f33c90966ade919c16eb |
| TVAE | 100 | Not recorded | 6a28f33c90966ade919c16eb |
| Gaussian Copula | 100 | Not recorded | 6a28f33c90966ade919c16eb |

### CTGAN

DRS C1: 100. Result ID: 6a2a58c2fbc373592c26c946.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f33c90966ade919c16eb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66901e209131cea10e19.md>)

[Implementation](<https://github.com/DAI-Lab/CTGAN>)

Recorded evaluation configuration: {"Evaluator":"Gemini"}. This record does not assert independent reproduction.

### TVAE

DRS C1: 100. Result ID: 6a2a58c2fbc373592c26c947.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f33c90966ade919c16eb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66901e209131cea10e19.md>)

[Implementation](<https://github.com/DAI-Lab/CTGAN>)

Recorded evaluation configuration: {"Evaluator":"Gemini"}. This record does not assert independent reproduction.

### Gaussian Copula

DRS C1: 100. Result ID: 6a2a58c2fbc373592c26c948.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f33c90966ade919c16eb.md>)

Recorded evaluation configuration: {"Evaluator":"Gemini"}. This record does not assert independent reproduction.

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