# Time Watermarking Detection and Verification on generated text 800 trials Qwen2.5-7B (test)

Source: [Time Watermarking Detection and Verification on generated text 800 trials Qwen2.5-7B (test)](<https://www.sota2.com/research/sota/time-watermarking-detection-and-verification-on-generated-text-800-trials-qwen2-5-7b-test>)

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

Data updated: 2026-04-15T06:42:37.717Z

Evaluation of Time Watermarking Detection and Verification performance on text generated by Qwen2.5-7B across 800 test trials. Metrics focus on the accuracy of identifying the generation time for both watermarked and non-watermarked texts, alongside average verification scores.

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 | Time Watermarking Detection and Verification |
| Dataset (including any stated split) | generated text 800 trials Qwen2.5-7B (test) |
| Metric | Count: Correctly Identified Watermarked Texts |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 1 of 1 |
| 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

- [Count: Correctly Identified Watermarked Texts](<https://www.sota2.com/research/sota/time-watermarking-detection-and-verification-on-generated-text-800-trials-qwen2-5-7b-test.md?metric=Count%3A%20Correctly%20Identified%20Watermarked%20Texts>): Higher is better; unit: SCALAR.

- [Accuracy: Correctly Identified Watermarked Texts (%)](<https://www.sota2.com/research/sota/time-watermarking-detection-and-verification-on-generated-text-800-trials-qwen2-5-7b-test.md?metric=Accuracy%3A%20Correctly%20Identified%20Watermarked%20Texts%20(%25)>): Higher is better; unit: PERCENT.

- [Count: False Positives (Non-watermarked identified)](<https://www.sota2.com/research/sota/time-watermarking-detection-and-verification-on-generated-text-800-trials-qwen2-5-7b-test.md?metric=Count%3A%20False%20Positives%20(Non-watermarked%20identified)>): Lower is better; unit: SCALAR.

- [FPR: Non-watermarked Identified (%)](<https://www.sota2.com/research/sota/time-watermarking-detection-and-verification-on-generated-text-800-trials-qwen2-5-7b-test.md?metric=FPR%3A%20Non-watermarked%20Identified%20(%25)>): Lower is better; unit: PERCENT.

- [Avg Verification Score (Watermarked)](<https://www.sota2.com/research/sota/time-watermarking-detection-and-verification-on-generated-text-800-trials-qwen2-5-7b-test.md?metric=Avg%20Verification%20Score%20(Watermarked)>): Higher is better; unit: SCALAR.

- [Avg Verification Score (Non-watermarked)](<https://www.sota2.com/research/sota/time-watermarking-detection-and-verification-on-generated-text-800-trials-qwen2-5-7b-test.md?metric=Avg%20Verification%20Score%20(Non-watermarked)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Count: Correctly Identified Watermarked Texts | Result date | Report paper |
| --- | --- | --- | --- |
| TimeMark | 800 | Not recorded | 69df1ba67d0172140ec7ba24 |

### TimeMark

Count: Correctly Identified Watermarked Texts: 800. Result ID: 69df334a47f34ce924c7784a.

[Reporting paper](<https://www.sota2.com/research/paper/69df1ba67d0172140ec7ba24.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1ba67d0172140ec7ba24.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B","Number of trials":"800","Verification Step":"Step 2"}. This record does not assert independent reproduction.

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