# Symptom Status Recognition on CMDD 1.0 (test)

Source: [Symptom Status Recognition on CMDD 1.0 (test)](<https://www.sota2.com/research/sota/symptom-status-recognition-on-cmdd-1-0-test>)

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

Data updated: 2026-02-26T06:08:58.263Z

Evaluation of Symptom Status Recognition performance on the test split of the CMDD 1.0 dataset, reporting window-level and dialogue-level 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 | Symptom Status Recognition |
| Dataset (including any stated split) | CMDD 1.0 (test) |
| Metric | Window-Level Precision |
| Unit | PERCENT |
| 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

- [Window-Level Precision](<https://www.sota2.com/research/sota/symptom-status-recognition-on-cmdd-1-0-test.md?metric=Window-Level%20Precision>): Higher is better; unit: PERCENT.

- [Window-Level Recall](<https://www.sota2.com/research/sota/symptom-status-recognition-on-cmdd-1-0-test.md?metric=Window-Level%20Recall>): Higher is better; unit: PERCENT.

- [Window-Level F1](<https://www.sota2.com/research/sota/symptom-status-recognition-on-cmdd-1-0-test.md?metric=Window-Level%20F1>): Higher is better; unit: PERCENT.

- [Dialogue-Level Precision](<https://www.sota2.com/research/sota/symptom-status-recognition-on-cmdd-1-0-test.md?metric=Dialogue-Level%20Precision>): Higher is better; unit: PERCENT.

- [Dialogue-Level Recall](<https://www.sota2.com/research/sota/symptom-status-recognition-on-cmdd-1-0-test.md?metric=Dialogue-Level%20Recall>): Higher is better; unit: PERCENT.

- [Dialogue-Level F1](<https://www.sota2.com/research/sota/symptom-status-recognition-on-cmdd-1-0-test.md?metric=Dialogue-Level%20F1>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Window-Level Precision | Result date | Report paper |
| --- | --- | --- | --- |
| KNSE | 84.17 | Not recorded | 68fa6f801e209131cea46098 |
| KNSE | 83.78 | Not recorded | 68fa6f801e209131cea46098 |
| KNSE | 83.05 | Not recorded | 68fa6f801e209131cea46098 |
| CANE | 82.54 | Not recorded | 68fa6f801e209131cea46098 |
| KNSE | 82.12 | Not recorded | 68fa6f801e209131cea46098 |
| MIE-multi | 81.63 | Not recorded | 68fa6f801e209131cea46098 |
| BERT-MTL | 80.2 | Not recorded | 68fa6f801e209131cea46098 |
| MRC | 80.05 | Not recorded | 68fa6f801e209131cea46098 |
| Plain-Classifier | 79.8 | Not recorded | 68fa6f801e209131cea46098 |

### KNSE

Window-Level Precision: 84.17. Result ID: 6990c77a3a6c314849033bab.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f801e209131cea46098.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f801e209131cea46098.md>)

Recorded evaluation configuration: {"status":"full model"}. This record does not assert independent reproduction.

### KNSE

Window-Level Precision: 83.78. Result ID: 6990c77a3a6c314849033bad.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f801e209131cea46098.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f801e209131cea46098.md>)

Recorded evaluation configuration: {"Ablation":"hard prompt"}. This record does not assert independent reproduction.

### KNSE

Window-Level Precision: 83.05. Result ID: 6990c77a3a6c314849033bae.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f801e209131cea46098.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f801e209131cea46098.md>)

Recorded evaluation configuration: {"Ablation":"w/o. knowledge"}. This record does not assert independent reproduction.

### CANE

Window-Level Precision: 82.54. Result ID: 6990c77a3a6c314849033baa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f801e209131cea46098.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### KNSE

Window-Level Precision: 82.12. Result ID: 6990c77a3a6c314849033bac.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f801e209131cea46098.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f801e209131cea46098.md>)

Recorded evaluation configuration: {"Ablation":"encoder only"}. This record does not assert independent reproduction.

### MIE-multi

Window-Level Precision: 81.63. Result ID: 6990c77a3a6c314849033ba8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f801e209131cea46098.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### BERT-MTL

Window-Level Precision: 80.2. Result ID: 6990c77a3a6c314849033ba7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f801e209131cea46098.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65c31e209131cea0c4ed.md>)

[Implementation](<https://github.com/google-research/bert>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MRC

Window-Level Precision: 80.05. Result ID: 6990c77a3a6c314849033ba9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f801e209131cea46098.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Plain-Classifier

Window-Level Precision: 79.8. Result ID: 6990c77a3a6c314849033ba6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f801e209131cea46098.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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