# Threshold Digital Signature Signing on ML-DSA-44

Source: [Threshold Digital Signature Signing on ML-DSA-44](<https://www.sota2.com/research/sota/threshold-digital-signature-signing-on-ml-dsa-44>)

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

Data updated: 2026-03-24T17:10:18.951Z

Evaluation of the Threshold Digital Signature Signing task using the ML-DSA-44 dataset, focusing on performance metrics like pBCC rate and signing latency (preprocess, online, total time).

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 | Threshold Digital Signature Signing |
| Dataset (including any stated split) | ML-DSA-44 |
| Metric | Online Latency (ms) |
| Unit | TIME |
| 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

- [Online Latency (ms)](<https://www.sota2.com/research/sota/threshold-digital-signature-signing-on-ml-dsa-44.md?metric=Online%20Latency%20(ms)>): Lower is better; unit: TIME.

- [pBCC Rate](<https://www.sota2.com/research/sota/threshold-digital-signature-signing-on-ml-dsa-44.md?metric=pBCC%20Rate>): Lower is better; unit: PERCENT.

- [Preprocess Latency (ms)](<https://www.sota2.com/research/sota/threshold-digital-signature-signing-on-ml-dsa-44.md?metric=Preprocess%20Latency%20(ms)>): Lower is better; unit: TIME.

- [Total Latency (ms)](<https://www.sota2.com/research/sota/threshold-digital-signature-signing-on-ml-dsa-44.md?metric=Total%20Latency%20(ms)>): Lower is better; unit: TIME.

## Recorded results

| Method | Online Latency (ms) | Result date | Report paper |
| --- | --- | --- | --- |
| TALUS-TEE | 0.16 | Not recorded | 69c21ad40636e5bf4afc4d25 |
| TALUS-MPC | 0.46 | Not recorded | 69c21ad40636e5bf4afc4d25 |
| Mithril | 1.4 | Not recorded | 69c21ad40636e5bf4afc4d25 |

### TALUS-TEE

Online Latency (ms): 0.16. Result ID: 69c2c56347f34ce924ac8470.

[Reporting paper](<https://www.sota2.com/research/paper/69c21ad40636e5bf4afc4d25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c21ad40636e5bf4afc4d25.md>)

Recorded evaluation configuration: {"Threshold (T)":"3","Total parties (N)":"3","Amortization strategy":"1/pBCC (offline)"}. This record does not assert independent reproduction.

### TALUS-MPC

Online Latency (ms): 0.46. Result ID: 69c2c56347f34ce924ac8471.

[Reporting paper](<https://www.sota2.com/research/paper/69c21ad40636e5bf4afc4d25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c21ad40636e5bf4afc4d25.md>)

Recorded evaluation configuration: {"Threshold (T)":"3","Total parties (N)":"3","Amortization strategy":"1/pBCC (offline)"}. This record does not assert independent reproduction.

### Mithril

Online Latency (ms): 1.4. Result ID: 69c2c56347f34ce924ac8472.

[Reporting paper](<https://www.sota2.com/research/paper/69c21ad40636e5bf4afc4d25.md>)

Recorded evaluation configuration: {"Threshold (T)":"3","Total parties (N)":"3","Implementation platform":"MacOS M3, Go/CIRCL","Amortization strategy":"over successful signing","Online mode":"rejection sampling (Fiat–Shamir with aborts)"}. This record does not assert independent reproduction.

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