# Multi-modal manipulation detection on ROM BBC domain 1.0 (test)

Source: [Multi-modal manipulation detection on ROM BBC domain 1.0 (test)](<https://www.sota2.com/research/sota/multi-modal-manipulation-detection-on-rom-bbc-domain-1-0-test>)

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

Data updated: 2026-03-04T16:44:54.051Z

Evaluation of Multi-modal manipulation detection performance on the test split of the ROM BBC domain 1.0 dataset, reporting ACC, mAP, and mIoU.

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 | Multi-modal manipulation detection |
| Dataset (including any stated split) | ROM BBC domain 1.0 (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher 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

- [Accuracy](<https://www.sota2.com/research/sota/multi-modal-manipulation-detection-on-rom-bbc-domain-1-0-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [mAP](<https://www.sota2.com/research/sota/multi-modal-manipulation-detection-on-rom-bbc-domain-1-0-test.md?metric=mAP>): Higher is better; unit: PERCENT.

- [mIoU](<https://www.sota2.com/research/sota/multi-modal-manipulation-detection-on-rom-bbc-domain-1-0-test.md?metric=mIoU>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| REFORM | 90.34 | Not recorded | 69a66c552d603e6de3e3d0dd |
| REFORM | 81.98 | Not recorded | 69a66c552d603e6de3e3d0dd |
| GPT-4o | 37.21 | Not recorded | 69a66c552d603e6de3e3d0dd |

### REFORM

Accuracy: 90.34. Result ID: 69a861786dbb7075b94ff672.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c552d603e6de3e3d0dd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a66c552d603e6de3e3d0dd.md>)

Recorded evaluation configuration: {"Setting":"Train on NYT"}. This record does not assert independent reproduction.

### REFORM

Accuracy: 81.98. Result ID: 69a861786dbb7075b94ff673.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c552d603e6de3e3d0dd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a66c552d603e6de3e3d0dd.md>)

Recorded evaluation configuration: {"Setting":"Train on Guardian"}. This record does not assert independent reproduction.

### GPT-4o

Accuracy: 37.21. Result ID: 69a861786dbb7075b94ff671.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c552d603e6de3e3d0dd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75681e209131cea67a98.md>)

Recorded evaluation configuration: {"Setting":"Zero-Shot"}. This record does not assert independent reproduction.

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