# End-to-end Bridging Resolution on BASHI

Source: [End-to-end Bridging Resolution on BASHI](<https://www.sota2.com/research/sota/end-to-end-bridging-resolution-on-bashi>)

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

Data updated: 2026-05-29T07:42:47.787Z

Evaluation of End-to-end Bridging Resolution performance on the BASHI dataset, reporting Recognition and Resolution Precision, Recall, and F1 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 | End-to-end Bridging Resolution |
| Dataset (including any stated split) | BASHI |
| Metric | Recognition Precision |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Recognition Precision](<https://www.sota2.com/research/sota/end-to-end-bridging-resolution-on-bashi.md?metric=Recognition%20Precision>): Higher is better; unit: PERCENT.

- [Recognition Recall](<https://www.sota2.com/research/sota/end-to-end-bridging-resolution-on-bashi.md?metric=Recognition%20Recall>): Higher is better; unit: PERCENT.

- [Recognition F1](<https://www.sota2.com/research/sota/end-to-end-bridging-resolution-on-bashi.md?metric=Recognition%20F1>): Higher is better; unit: PERCENT.

- [Resolution Precision](<https://www.sota2.com/research/sota/end-to-end-bridging-resolution-on-bashi.md?metric=Resolution%20Precision>): Higher is better; unit: PERCENT.

- [Resolution Recall](<https://www.sota2.com/research/sota/end-to-end-bridging-resolution-on-bashi.md?metric=Resolution%20Recall>): Higher is better; unit: PERCENT.

- [Resolution F1](<https://www.sota2.com/research/sota/end-to-end-bridging-resolution-on-bashi.md?metric=Resolution%20F1>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Recognition Precision | Result date | Report paper |
| --- | --- | --- | --- |
| Kobayashi et al. (2023) | 43 | Not recorded | 6a191da0dbd7150506f8282f |
| LLMBridge | 22.9 | Not recorded | 6a191da0dbd7150506f8282f |
| LLMBridge | 15.8 | Not recorded | 6a191da0dbd7150506f8282f |
| LLMBridge | 10.5 | Not recorded | 6a191da0dbd7150506f8282f |
| LLMBridge | 9.5 | Not recorded | 6a191da0dbd7150506f8282f |

### Kobayashi et al. (2023)

Recognition Precision: 43. Result ID: 6a194324fbc373592c1354a9.

[Reporting paper](<https://www.sota2.com/research/paper/6a191da0dbd7150506f8282f.md>)

Recorded evaluation configuration: {"Evaluation Setting":"End-to-end"}. This record does not assert independent reproduction.

### LLMBridge

Recognition Precision: 22.9. Result ID: 6a194324fbc373592c1354a5.

[Reporting paper](<https://www.sota2.com/research/paper/6a191da0dbd7150506f8282f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a191da0dbd7150506f8282f.md>)

Recorded evaluation configuration: {"Backend Model":"Gemini-3.1-pro-preview","Evaluation Setting":"End-to-end"}. This record does not assert independent reproduction.

### LLMBridge

Recognition Precision: 15.8. Result ID: 6a194324fbc373592c1354a7.

[Reporting paper](<https://www.sota2.com/research/paper/6a191da0dbd7150506f8282f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a191da0dbd7150506f8282f.md>)

Recorded evaluation configuration: {"Backend Model":"Qwen2.5-7B-Instruct-FT","Evaluation Setting":"End-to-end"}. This record does not assert independent reproduction.

### LLMBridge

Recognition Precision: 10.5. Result ID: 6a194324fbc373592c1354a8.

[Reporting paper](<https://www.sota2.com/research/paper/6a191da0dbd7150506f8282f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a191da0dbd7150506f8282f.md>)

Recorded evaluation configuration: {"Backend Model":"Qwen2.5-7B-Instruct","Evaluation Setting":"End-to-end"}. This record does not assert independent reproduction.

### LLMBridge

Recognition Precision: 9.5. Result ID: 6a194324fbc373592c1354a6.

[Reporting paper](<https://www.sota2.com/research/paper/6a191da0dbd7150506f8282f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a191da0dbd7150506f8282f.md>)

Recorded evaluation configuration: {"Backend Model":"Llama-3.3-70B-Instruct","Evaluation Setting":"End-to-end"}. This record does not assert independent reproduction.

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