# Counterfactual Recourse Evaluation on ADULT (test)

Source: [Counterfactual Recourse Evaluation on ADULT (test)](<https://www.sota2.com/research/sota/counterfactual-recourse-evaluation-on-adult-test>)

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

Data updated: 2026-05-19T09:33:23.150Z

Evaluation of counterfactual recourse methods on the test split of the ADULT dataset, measured using Accuracy (Acc.), Value Difference (VD), Counterfactual Recourse Gap (CRG), and Directional Similarity (DirSim).

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 | Counterfactual Recourse Evaluation |
| Dataset (including any stated split) | ADULT (test) |
| Metric | Acc. |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [Acc.](<https://www.sota2.com/research/sota/counterfactual-recourse-evaluation-on-adult-test.md?metric=Acc.>): Higher is better; unit: PERCENT.

- [VD](<https://www.sota2.com/research/sota/counterfactual-recourse-evaluation-on-adult-test.md?metric=VD>): Lower is better; unit: SCALAR.

- [CRG](<https://www.sota2.com/research/sota/counterfactual-recourse-evaluation-on-adult-test.md?metric=CRG>): Lower is better; unit: SCALAR.

- [DirSim](<https://www.sota2.com/research/sota/counterfactual-recourse-evaluation-on-adult-test.md?metric=DirSim>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Acc. | Result date | Report paper |
| --- | --- | --- | --- |
| CFQ-QAT | 85.7 | Not recorded | 6a0bee90dbc836b87d82c3a9 |
| PTQ INT8 | 85.6 | Not recorded | 6a0bee90dbc836b87d82c3a9 |
| CF-PTQ + sensitivity allocation | 85.5 | Not recorded | 6a0bee90dbc836b87d82c3a9 |
| Mixed-precision PTQ | 85.4 | Not recorded | 6a0bee90dbc836b87d82c3a9 |
| CF-PTQ calibration | 85.4 | Not recorded | 6a0bee90dbc836b87d82c3a9 |
| PTQ INT4 | 85 | Not recorded | 6a0bee90dbc836b87d82c3a9 |

### CFQ-QAT

Acc.: 85.7. Result ID: 6a0c2e54fbc373592c029cdc.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee90dbc836b87d82c3a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0bee90dbc836b87d82c3a9.md>)

Recorded evaluation configuration: {"Budget":"mixed","Time overhead":"1.42×"}. This record does not assert independent reproduction.

### PTQ INT8

Acc.: 85.6. Result ID: 6a0c2e54fbc373592c029cd7.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee90dbc836b87d82c3a9.md>)

Recorded evaluation configuration: {"Budget":"8-bit","Time overhead":"1.00×"}. This record does not assert independent reproduction.

### CF-PTQ + sensitivity allocation

Acc.: 85.5. Result ID: 6a0c2e54fbc373592c029cdb.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee90dbc836b87d82c3a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0bee90dbc836b87d82c3a9.md>)

Recorded evaluation configuration: {"Budget":"mixed","Time overhead":"1.29×"}. This record does not assert independent reproduction.

### Mixed-precision PTQ

Acc.: 85.4. Result ID: 6a0c2e54fbc373592c029cd9.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee90dbc836b87d82c3a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65a41e209131cea0b895.md>)

Recorded evaluation configuration: {"Budget":"mixed","Time overhead":"1.08×"}. This record does not assert independent reproduction.

### CF-PTQ calibration

Acc.: 85.4. Result ID: 6a0c2e54fbc373592c029cda.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee90dbc836b87d82c3a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0bee90dbc836b87d82c3a9.md>)

Recorded evaluation configuration: {"Budget":"mixed","Time overhead":"1.17×"}. This record does not assert independent reproduction.

### PTQ INT4

Acc.: 85. Result ID: 6a0c2e54fbc373592c029cd8.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee90dbc836b87d82c3a9.md>)

Recorded evaluation configuration: {"Budget":"4-bit","Time overhead":"1.00×"}. This record does not assert independent reproduction.

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