# Watermarking Robustness on DTS Deletion - 30%

Source: [Watermarking Robustness on DTS Deletion - 30%](<https://www.sota2.com/research/sota/watermarking-robustness-on-dts-deletion-30-percent>)

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

Data updated: 2026-04-07T07:15:45.655Z

Evaluation of watermarking robustness on the DTS dataset under a 30% deletion scenario, measured using metrics such as ROC-AUC and thresholded false positive rates (T@F).

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 | Watermarking Robustness |
| Dataset (including any stated split) | DTS Deletion - 30% |
| Metric | ROC-AUC |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

- [ROC-AUC](<https://www.sota2.com/research/sota/watermarking-robustness-on-dts-deletion-30-percent.md?metric=ROC-AUC>): Higher is better; unit: SCALAR.

- [T@1%F](<https://www.sota2.com/research/sota/watermarking-robustness-on-dts-deletion-30-percent.md?metric=T%401%25F>): Lower is better; unit: PERCENT.

- [T@10%F](<https://www.sota2.com/research/sota/watermarking-robustness-on-dts-deletion-30-percent.md?metric=T%4010%25F>): Lower is better; unit: PERCENT.

## Recorded results

| Method | ROC-AUC | Result date | Report paper |
| --- | --- | --- | --- |
| Letter ICW | 0.998 | Not recorded | 68fa78b31e209131cea79d68 |
| YCZ+23 | 0.98 | Not recorded | 68fa78b31e209131cea79d68 |
| PostMark | 0.908 | Not recorded | 68fa78b31e209131cea79d68 |
| Acrostics ICW | 0.881 | Not recorded | 68fa78b31e209131cea79d68 |
| PostMark | 0.877 | Not recorded | 68fa78b31e209131cea79d68 |
| Lexical ICW | 0.857 | Not recorded | 68fa78b31e209131cea79d68 |
| Lexical ICW | 0.849 | Not recorded | 68fa78b31e209131cea79d68 |
| Letter ICW | 0.566 | Not recorded | 68fa78b31e209131cea79d68 |
| Acrostics ICW | 0.534 | Not recorded | 68fa78b31e209131cea79d68 |

### Letter ICW

ROC-AUC: 0.998. Result ID: 69d4aead47f34ce924bc068b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78b31e209131cea79d68.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78b31e209131cea79d68.md>)

Recorded evaluation configuration: {"Language Model":"GPT-o3-mini"}. This record does not assert independent reproduction.

### YCZ+23

ROC-AUC: 0.98. Result ID: 69d4aead47f34ce924bc0685.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78b31e209131cea79d68.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f591e209131cea45300.md>)

Recorded evaluation configuration: {"Language Model":"N/A"}. This record does not assert independent reproduction.

### PostMark

ROC-AUC: 0.908. Result ID: 69d4aead47f34ce924bc068a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78b31e209131cea79d68.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75311e209131cea6646e.md>)

Recorded evaluation configuration: {"Language Model":"GPT-o3-mini"}. This record does not assert independent reproduction.

### Acrostics ICW

ROC-AUC: 0.881. Result ID: 69d4aead47f34ce924bc068d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78b31e209131cea79d68.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78b31e209131cea79d68.md>)

Recorded evaluation configuration: {"Language Model":"GPT-o3-mini"}. This record does not assert independent reproduction.

### PostMark

ROC-AUC: 0.877. Result ID: 69d4aead47f34ce924bc0686.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78b31e209131cea79d68.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75311e209131cea6646e.md>)

Recorded evaluation configuration: {"Language Model":"GPT-4o-mini"}. This record does not assert independent reproduction.

### Lexical ICW

ROC-AUC: 0.857. Result ID: 69d4aead47f34ce924bc068c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78b31e209131cea79d68.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78b31e209131cea79d68.md>)

Recorded evaluation configuration: {"Language Model":"GPT-o3-mini"}. This record does not assert independent reproduction.

### Lexical ICW

ROC-AUC: 0.849. Result ID: 69d4aead47f34ce924bc0688.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78b31e209131cea79d68.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78b31e209131cea79d68.md>)

Recorded evaluation configuration: {"Language Model":"GPT-4o-mini"}. This record does not assert independent reproduction.

### Letter ICW

ROC-AUC: 0.566. Result ID: 69d4aead47f34ce924bc0687.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78b31e209131cea79d68.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78b31e209131cea79d68.md>)

Recorded evaluation configuration: {"Language Model":"GPT-4o-mini"}. This record does not assert independent reproduction.

### Acrostics ICW

ROC-AUC: 0.534. Result ID: 69d4aead47f34ce924bc0689.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78b31e209131cea79d68.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78b31e209131cea79d68.md>)

Recorded evaluation configuration: {"Language Model":"GPT-4o-mini"}. This record does not assert independent reproduction.

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