# Fact Tracing on T-REx

Source: [Fact Tracing on T-REx](<https://www.sota2.com/research/sota/fact-tracing-on-t-rex>)

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

Data updated: 2026-04-20T08:34:28.626Z

Evaluation of model performance on fact tracing capabilities using the T-REx dataset, measured using Mean Reciprocal Rank (MRR) and Recall@10.

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 | fact-tracing |
| Dataset (including any stated split) | T-REx |
| Metric | MRR |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [MRR](<https://www.sota2.com/research/sota/fact-tracing-on-t-rex.md?metric=MRR>): Higher is better; unit: PERCENT.

- [Recall@10](<https://www.sota2.com/research/sota/fact-tracing-on-t-rex.md?metric=Recall%4010>): Higher is better; unit: PERCENT.

## Recorded results

| Method | MRR | Result date | Report paper |
| --- | --- | --- | --- |
| RISE | 43.7 | Not recorded | 69e5b32a7d0172140ec7e12c |
| TrackStar | 36.3 | Not recorded | 69e5b32a7d0172140ec7e12c |
| RISE | 30.72 | Not recorded | 69e5b32a7d0172140ec7e12c |
| RISE | 23.49 | Not recorded | 69e5b32a7d0172140ec7e12c |
| TrackStar | 1.65 | Not recorded | 69e5b32a7d0172140ec7e12c |
| TrackStar | 1.27 | Not recorded | 69e5b32a7d0172140ec7e12c |

### RISE

MRR: 43.7. Result ID: 69e5e51147f34ce924cc1740.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b32a7d0172140ec7e12c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e5b32a7d0172140ec7e12c.md>)

Recorded evaluation configuration: {"Pool":"20K","Model":"Pythia-1B"}. This record does not assert independent reproduction.

### TrackStar

MRR: 36.3. Result ID: 69e5e51147f34ce924cc173f.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b32a7d0172140ec7e12c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa765a1e209131cea6c90f.md>)

Recorded evaluation configuration: {"Pool":"20K","Model":"Pythia-1B"}. This record does not assert independent reproduction.

### RISE

MRR: 30.72. Result ID: 69e5e51147f34ce924cc1742.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b32a7d0172140ec7e12c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e5b32a7d0172140ec7e12c.md>)

Recorded evaluation configuration: {"Pool":"200K","Model":"Pythia-1B"}. This record does not assert independent reproduction.

### RISE

MRR: 23.49. Result ID: 69e5e51147f34ce924cc1744.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b32a7d0172140ec7e12c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e5b32a7d0172140ec7e12c.md>)

Recorded evaluation configuration: {"Pool":"1M","Model":"Pythia-1B"}. This record does not assert independent reproduction.

### TrackStar

MRR: 1.65. Result ID: 69e5e51147f34ce924cc1741.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b32a7d0172140ec7e12c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa765a1e209131cea6c90f.md>)

Recorded evaluation configuration: {"Pool":"200K","Model":"Pythia-1B"}. This record does not assert independent reproduction.

### TrackStar

MRR: 1.27. Result ID: 69e5e51147f34ce924cc1743.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b32a7d0172140ec7e12c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa765a1e209131cea6c90f.md>)

Recorded evaluation configuration: {"Pool":"1M","Model":"Pythia-1B"}. This record does not assert independent reproduction.

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