# Social Cue Score Prediction on DnD Group Gesture

Source: [Social Cue Score Prediction on DnD Group Gesture](<https://www.sota2.com/research/sota/social-cue-score-prediction-on-dnd-group-gesture>)

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

Data updated: 2026-04-10T09:05:27.860Z

Evaluation of models predicting social cue scores for multiple users based on the DnD Group Gesture dataset, measured by user-specific error rates.

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 | Social Cue Score Prediction |
| Dataset (including any stated split) | DnD Group Gesture |
| Metric | Social Cue Error (User 1) |
| Unit | PERCENT |
| Direction | Lower 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

- [Social Cue Error (User 1)](<https://www.sota2.com/research/sota/social-cue-score-prediction-on-dnd-group-gesture.md?metric=Social%20Cue%20Error%20(User%201)>): Lower is better; unit: PERCENT.

- [Social Cue Error (User 2)](<https://www.sota2.com/research/sota/social-cue-score-prediction-on-dnd-group-gesture.md?metric=Social%20Cue%20Error%20(User%202)>): Lower is better; unit: PERCENT.

- [Social Cue Error (User 3)](<https://www.sota2.com/research/sota/social-cue-score-prediction-on-dnd-group-gesture.md?metric=Social%20Cue%20Error%20(User%203)>): Lower is better; unit: PERCENT.

- [Social Cue Error (User 4)](<https://www.sota2.com/research/sota/social-cue-score-prediction-on-dnd-group-gesture.md?metric=Social%20Cue%20Error%20(User%204)>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Social Cue Error (User 1) | Result date | Report paper |
| --- | --- | --- | --- |
| PolySLGen | 30 | Not recorded | 69d8842e7d0172140ec77b12 |
| SOLAMI | 32 | Not recorded | 69d8842e7d0172140ec77b12 |
| LM-L2L Adapted | 35 | Not recorded | 69d8842e7d0172140ec77b12 |

### PolySLGen

Social Cue Error (User 1): 30. Result ID: 69d8bd5047f34ce924c1d006.

[Reporting paper](<https://www.sota2.com/research/paper/69d8842e7d0172140ec77b12.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d8842e7d0172140ec77b12.md>)

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

### SOLAMI

Social Cue Error (User 1): 32. Result ID: 69d8bd5047f34ce924c1d005.

[Reporting paper](<https://www.sota2.com/research/paper/69d8842e7d0172140ec77b12.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76031e209131cea6aeb2.md>)

[Implementation](<https://solami-ai.github.io/>)

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

### LM-L2L Adapted

Social Cue Error (User 1): 35. Result ID: 69d8bd5047f34ce924c1d004.

[Reporting paper](<https://www.sota2.com/research/paper/69d8842e7d0172140ec77b12.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70621e209131cea4ac8e.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.
