# Statistical Fidelity on Averaged Small Data Splits (Adult, Churn, HTRU2, Magic, Liver, Titanic)

Source: [Statistical Fidelity on Averaged Small Data Splits (Adult, Churn, HTRU2, Magic, Liver, Titanic)](<https://www.sota2.com/research/sota/statistical-fidelity-on-averaged-small-data-splits-adult-churn-htru2-magic-liver-titanic>)

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

Data updated: 2026-03-12T09:14:12.027Z

Evaluation of statistical fidelity across an average of small data splits from six datasets: Adult, Churn, HTRU2, Magic, Liver, and Titanic, reporting metrics such as Precision, Recall, Shape, and Correlation.

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 | Statistical Fidelity |
| Dataset (including any stated split) | Adult, Churn, HTRU2, Magic, Liver, and Titanic averaged (small data splits) |
| Metric | Precision |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [Precision](<https://www.sota2.com/research/sota/statistical-fidelity-on-averaged-small-data-splits-adult-churn-htru2-magic-liver-titanic.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/statistical-fidelity-on-averaged-small-data-splits-adult-churn-htru2-magic-liver-titanic.md?metric=Recall>): Higher is better; unit: PERCENT.

- [Shape Fidelity](<https://www.sota2.com/research/sota/statistical-fidelity-on-averaged-small-data-splits-adult-churn-htru2-magic-liver-titanic.md?metric=Shape%20Fidelity>): Higher is better; unit: SCALAR.

- [Correlation Coefficient](<https://www.sota2.com/research/sota/statistical-fidelity-on-averaged-small-data-splits-adult-churn-htru2-magic-liver-titanic.md?metric=Correlation%20Coefficient>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Precision | Result date | Report paper |
| --- | --- | --- | --- |
| SMOTE | 53 | Not recorded | 69b2488ad030084c22e2f89e |
| ReTabSyn | 51 | Not recorded | 69b2488ad030084c22e2f89e |
| GReaT | 44 | Not recorded | 69b2488ad030084c22e2f89e |
| PTA | 43 | Not recorded | 69b2488ad030084c22e2f89e |
| TabSyn | 41 | Not recorded | 69b2488ad030084c22e2f89e |
| SynRL | 30 | Not recorded | 69b2488ad030084c22e2f89e |
| TVAE | 28 | Not recorded | 69b2488ad030084c22e2f89e |

### SMOTE

Precision: 53. Result ID: 69b283696dbb7075b95d5ee4.

[Reporting paper](<https://www.sota2.com/research/paper/69b2488ad030084c22e2f89e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa60691e209131ce9ef1af.md>)

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

### ReTabSyn

Precision: 51. Result ID: 69b283696dbb7075b95d5ee9.

[Reporting paper](<https://www.sota2.com/research/paper/69b2488ad030084c22e2f89e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b2488ad030084c22e2f89e.md>)

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

### GReaT

Precision: 44. Result ID: 69b283696dbb7075b95d5ee6.

[Reporting paper](<https://www.sota2.com/research/paper/69b2488ad030084c22e2f89e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f291e209131cea442a2.md>)

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

### PTA

Precision: 43. Result ID: 69b283696dbb7075b95d5ee8.

[Reporting paper](<https://www.sota2.com/research/paper/69b2488ad030084c22e2f89e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa771f1e209131cea7134a.md>)

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

### TabSyn

Precision: 41. Result ID: 69b283696dbb7075b95d5ee5.

[Reporting paper](<https://www.sota2.com/research/paper/69b2488ad030084c22e2f89e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73261e209131cea5ab3b.md>)

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

### SynRL

Precision: 30. Result ID: 69b283696dbb7075b95d5ee7.

[Reporting paper](<https://www.sota2.com/research/paper/69b2488ad030084c22e2f89e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77001e209131cea70657.md>)

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

### TVAE

Precision: 28. Result ID: 69b283696dbb7075b95d5ee3.

[Reporting paper](<https://www.sota2.com/research/paper/69b2488ad030084c22e2f89e.md>)

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

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

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.
