Submissions are evaluated on [Cohen’s kappa score](https://en.wikipedia.org/wiki/Cohen%27s_kappa) between the predicted label and the true label.

## Submission File
For each ID in the test set, you must predict a cell type for the TARGET variable. The file should contain a header and have the following format:

```python
    ID,TARGET
    0, IT-L23
    1, IT-L23
    2, ODC
```
    etc, where ID is the obs_names of single-cell data.

## Notes
- Maximum daily submission: 5 times
- If there is any question or concern, you may discuss with us on Feishu.