# Machine-Generated Text Attribution on Social Science

Source: [Machine-Generated Text Attribution on Social Science](<https://www.sota2.com/research/sota/machine-generated-text-attribution-on-social-science>)

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

Data updated: 2026-06-05T08:41:13.990Z

Evaluation of model capabilities to attribute text generation sources on the Social Science dataset, measured using Full Macro-F1.

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 | Machine-Generated Text Attribution |
| Dataset (including any stated split) | Social Science |
| Metric | Full Macro-F1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 26 of 26 |
| 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

- [Full Macro-F1](<https://www.sota2.com/research/sota/machine-generated-text-attribution-on-social-science.md?metric=Full%20Macro-F1>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Full Macro-F1 | Result date | Report paper |
| --- | --- | --- | --- |
| Ori. | 90.6 | Not recorded | 6a22589786173ad9c1468b1e |
| Ori. | 89.1 | Not recorded | 6a22589786173ad9c1468b1e |
| RidgeFT | 88 | Not recorded | 6a22589786173ad9c1468b1e |
| RidgeFT | 87.8 | Not recorded | 6a22589786173ad9c1468b1e |
| RidgeFT | 86.8 | Not recorded | 6a22589786173ad9c1468b1e |
| RidgeFT | 86.8 | Not recorded | 6a22589786173ad9c1468b1e |
| RidgeFT | 86.7 | Not recorded | 6a22589786173ad9c1468b1e |
| RidgeFT | 86.7 | Not recorded | 6a22589786173ad9c1468b1e |
| RidgeFT | 86.5 | Not recorded | 6a22589786173ad9c1468b1e |
| RidgeFT | 86.2 | Not recorded | 6a22589786173ad9c1468b1e |
| RidgeFT | 86.2 | Not recorded | 6a22589786173ad9c1468b1e |
| RidgeFT | 85.4 | Not recorded | 6a22589786173ad9c1468b1e |
| RidgeFT | 85.3 | Not recorded | 6a22589786173ad9c1468b1e |
| RidgeFT | 85.1 | Not recorded | 6a22589786173ad9c1468b1e |
| iCaRL\* | 84.5 | Not recorded | 6a22589786173ad9c1468b1e |
| EASE\* | 84.4 | Not recorded | 6a22589786173ad9c1468b1e |
| BiC\* | 83.5 | Not recorded | 6a22589786173ad9c1468b1e |
| LwF\* | 83.3 | Not recorded | 6a22589786173ad9c1468b1e |
| LwF\* | 81.9 | Not recorded | 6a22589786173ad9c1468b1e |
| iCaRL\* | 81.2 | Not recorded | 6a22589786173ad9c1468b1e |
| BiC\* | 80.1 | Not recorded | 6a22589786173ad9c1468b1e |
| PASS | 78 | Not recorded | 6a22589786173ad9c1468b1e |
| PASS | 77.2 | Not recorded | 6a22589786173ad9c1468b1e |
| SimpleCIL | 76.9 | Not recorded | 6a22589786173ad9c1468b1e |
| SimpleCIL | 76.5 | Not recorded | 6a22589786173ad9c1468b1e |
| EASE\* | 75.3 | Not recorded | 6a22589786173ad9c1468b1e |

### Ori.

Full Macro-F1: 90.6. Result ID: 6a228a87fbc373592c209ef7.

[Reporting paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

Recorded evaluation configuration: {"Backbone":"RoBERTa-base","New Model":"GPT-3.5"}. This record does not assert independent reproduction.

### Ori.

Full Macro-F1: 89.1. Result ID: 6a228a87fbc373592c209eff.

[Reporting paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

Recorded evaluation configuration: {"Backbone":"DeBERTa-base","New Model":"GPT-3.5"}. This record does not assert independent reproduction.

### RidgeFT

Full Macro-F1: 88. Result ID: 6a228a87fbc373592c209f07.

[Reporting paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

Recorded evaluation configuration: {"Backbone":"RoBERTa-base","New Model":"Mixtral"}. This record does not assert independent reproduction.

### RidgeFT

Full Macro-F1: 87.8. Result ID: 6a228a87fbc373592c209f08.

[Reporting paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

Recorded evaluation configuration: {"Backbone":"DeBERTa-base","New Model":"Mixtral"}. This record does not assert independent reproduction.

### RidgeFT

Full Macro-F1: 86.8. Result ID: 6a228a87fbc373592c209f09.

[Reporting paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

Recorded evaluation configuration: {"Backbone":"RoBERTa-base","New Model":"Moonshot"}. This record does not assert independent reproduction.

### RidgeFT

Full Macro-F1: 86.8. Result ID: 6a228a87fbc373592c209f0d.

[Reporting paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

Recorded evaluation configuration: {"Backbone":"RoBERTa-base","New Model":"GPT-4o-mini"}. This record does not assert independent reproduction.

### RidgeFT

Full Macro-F1: 86.7. Result ID: 6a228a87fbc373592c209f0e.

[Reporting paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

Recorded evaluation configuration: {"Backbone":"DeBERTa-base","New Model":"GPT-4o-mini"}. This record does not assert independent reproduction.

### RidgeFT

Full Macro-F1: 86.7. Result ID: 6a228a87fbc373592c209f0f.

[Reporting paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

Recorded evaluation configuration: {"Backbone":"RoBERTa-base","New Model":"Average"}. This record does not assert independent reproduction.

### RidgeFT

Full Macro-F1: 86.5. Result ID: 6a228a87fbc373592c209efe.

[Reporting paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

Recorded evaluation configuration: {"Backbone":"RoBERTa-base","New Model":"GPT-3.5"}. This record does not assert independent reproduction.

### RidgeFT

Full Macro-F1: 86.2. Result ID: 6a228a87fbc373592c209f0a.

[Reporting paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

Recorded evaluation configuration: {"Backbone":"DeBERTa-base","New Model":"Moonshot"}. This record does not assert independent reproduction.

### RidgeFT

Full Macro-F1: 86.2. Result ID: 6a228a87fbc373592c209f10.

[Reporting paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

Recorded evaluation configuration: {"Backbone":"DeBERTa-base","New Model":"Average"}. This record does not assert independent reproduction.

### RidgeFT

Full Macro-F1: 85.4. Result ID: 6a228a87fbc373592c209f0b.

[Reporting paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

Recorded evaluation configuration: {"Backbone":"RoBERTa-base","New Model":"Llama-3.1"}. This record does not assert independent reproduction.

### RidgeFT

Full Macro-F1: 85.3. Result ID: 6a228a87fbc373592c209f0c.

[Reporting paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

Recorded evaluation configuration: {"Backbone":"DeBERTa-base","New Model":"Llama-3.1"}. This record does not assert independent reproduction.

### RidgeFT

Full Macro-F1: 85.1. Result ID: 6a228a87fbc373592c209f06.

[Reporting paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

Recorded evaluation configuration: {"Backbone":"DeBERTa-base","New Model":"GPT-3.5"}. This record does not assert independent reproduction.

### iCaRL\*

Full Macro-F1: 84.5. Result ID: 6a228a87fbc373592c209ef9.

[Reporting paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa634e1e209131ce9fded4.md>)

Recorded evaluation configuration: {"Backbone":"RoBERTa-base","New Model":"GPT-3.5"}. This record does not assert independent reproduction.

### EASE\*

Full Macro-F1: 84.4. Result ID: 6a228a87fbc373592c209efb.

[Reporting paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72981e209131cea57699.md>)

Recorded evaluation configuration: {"Backbone":"RoBERTa-base","New Model":"GPT-3.5"}. This record does not assert independent reproduction.

### BiC\*

Full Macro-F1: 83.5. Result ID: 6a228a87fbc373592c209efa.

[Reporting paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65dc1e209131cea0ce26.md>)

[Implementation](<https://github.com/srebuffi/iCaRL>)

Recorded evaluation configuration: {"Backbone":"RoBERTa-base","New Model":"GPT-3.5"}. This record does not assert independent reproduction.

### LwF\*

Full Macro-F1: 83.3. Result ID: 6a228a87fbc373592c209ef8.

[Reporting paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63201e209131ce9fd0b3.md>)

Recorded evaluation configuration: {"Backbone":"RoBERTa-base","New Model":"GPT-3.5"}. This record does not assert independent reproduction.

### LwF\*

Full Macro-F1: 81.9. Result ID: 6a228a87fbc373592c209f00.

[Reporting paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63201e209131ce9fd0b3.md>)

Recorded evaluation configuration: {"Backbone":"DeBERTa-base","New Model":"GPT-3.5"}. This record does not assert independent reproduction.

### iCaRL\*

Full Macro-F1: 81.2. Result ID: 6a228a87fbc373592c209f01.

[Reporting paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa634e1e209131ce9fded4.md>)

Recorded evaluation configuration: {"Backbone":"DeBERTa-base","New Model":"GPT-3.5"}. This record does not assert independent reproduction.

### BiC\*

Full Macro-F1: 80.1. Result ID: 6a228a87fbc373592c209f02.

[Reporting paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65dc1e209131cea0ce26.md>)

[Implementation](<https://github.com/srebuffi/iCaRL>)

Recorded evaluation configuration: {"Backbone":"DeBERTa-base","New Model":"GPT-3.5"}. This record does not assert independent reproduction.

### PASS

Full Macro-F1: 78. Result ID: 6a228a87fbc373592c209f04.

[Reporting paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

Recorded evaluation configuration: {"Backbone":"DeBERTa-base","New Model":"GPT-3.5"}. This record does not assert independent reproduction.

### PASS

Full Macro-F1: 77.2. Result ID: 6a228a87fbc373592c209efc.

[Reporting paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

Recorded evaluation configuration: {"Backbone":"RoBERTa-base","New Model":"GPT-3.5"}. This record does not assert independent reproduction.

### SimpleCIL

Full Macro-F1: 76.9. Result ID: 6a228a87fbc373592c209efd.

[Reporting paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74641e209131cea616e7.md>)

Recorded evaluation configuration: {"Backbone":"RoBERTa-base","New Model":"GPT-3.5"}. This record does not assert independent reproduction.

### SimpleCIL

Full Macro-F1: 76.5. Result ID: 6a228a87fbc373592c209f05.

[Reporting paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74641e209131cea616e7.md>)

Recorded evaluation configuration: {"Backbone":"DeBERTa-base","New Model":"GPT-3.5"}. This record does not assert independent reproduction.

### EASE\*

Full Macro-F1: 75.3. Result ID: 6a228a87fbc373592c209f03.

[Reporting paper](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b1e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72981e209131cea57699.md>)

Recorded evaluation configuration: {"Backbone":"DeBERTa-base","New Model":"GPT-3.5"}. This record does not assert independent reproduction.

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