# Role Prediction on 4D-OR

Source: [Role Prediction on 4D-OR](<https://www.sota2.com/research/sota/role-prediction-on-4d-or>)

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

Data updated: 2026-04-23T10:57:58.818Z

Evaluation of Role Prediction performance on the 4D-OR dataset, measured using Macro F1 score.

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 | Role Prediction |
| Dataset (including any stated split) | 4D-OR |
| Metric | Macro F1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [Macro F1](<https://www.sota2.com/research/sota/role-prediction-on-4d-or.md?metric=Macro%20F1>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Macro F1 | Result date | Report paper |
| --- | --- | --- | --- |
| Gaze-LLE | 92 | Not recorded | 69e9a78b55a3c32af89f7050 |
| LABRAD-OR | 89 | Not recorded | 68fa6ee91e209131cea42d8d |
| LABRAD | 89 | Not recorded | 69e9a78b55a3c32af89f7050 |
| S^2Former | 89 | Not recorded | 69e9a78b55a3c32af89f7050 |
| 4D-OR | 87 | Not recorded | 69e9a78b55a3c32af89f7050 |
| 4D-OR | 85 | Not recorded | 68fa6ee91e209131cea42d8d |
| ORacle | 85 | Not recorded | 69e9a78b55a3c32af89f7050 |
| Gaze-LLE | 62 | Not recorded | 69e9a78b55a3c32af89f7050 |

### Gaze-LLE

Macro F1: 92. Result ID: 69e9fb1947f34ce924d202f5.

[Reporting paper](<https://www.sota2.com/research/paper/69e9a78b55a3c32af89f7050.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e9a78b55a3c32af89f7050.md>)

Recorded evaluation configuration: {"mode":"fine-tuned"}. This record does not assert independent reproduction.

### LABRAD-OR

Macro F1: 89. Result ID: 6990862f3a6c314849012e4e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ee91e209131cea42d8d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee91e209131cea42d8d.md>)

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

### LABRAD

Macro F1: 89. Result ID: 69e9fb1947f34ce924d202f1.

[Reporting paper](<https://www.sota2.com/research/paper/69e9a78b55a3c32af89f7050.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee91e209131cea42d8d.md>)

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

### S^2Former

Macro F1: 89. Result ID: 69e9fb1947f34ce924d202f2.

[Reporting paper](<https://www.sota2.com/research/paper/69e9a78b55a3c32af89f7050.md>)

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

### 4D-OR

Macro F1: 87. Result ID: 69e9fb1947f34ce924d202f0.

[Reporting paper](<https://www.sota2.com/research/paper/69e9a78b55a3c32af89f7050.md>)

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

### 4D-OR

Macro F1: 85. Result ID: 6990862f3a6c314849012e4d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ee91e209131cea42d8d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0d1e209131cea31ba1.md>)

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

### ORacle

Macro F1: 85. Result ID: 69e9fb1947f34ce924d202f3.

[Reporting paper](<https://www.sota2.com/research/paper/69e9a78b55a3c32af89f7050.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72dc1e209131cea58fe2.md>)

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

### Gaze-LLE

Macro F1: 62. Result ID: 69e9fb1947f34ce924d202f4.

[Reporting paper](<https://www.sota2.com/research/paper/69e9a78b55a3c32af89f7050.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e9a78b55a3c32af89f7050.md>)

Recorded evaluation configuration: {"mode":"off-the-shelf"}. This record does not assert independent reproduction.

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