[TechDebt] Meaning of fold in the results parquet file

Hi! I was trying to match some of my run results with the ones reported in tabarena and had a question about folds and repeats reporting in the provided results dataframe. I am using the following dataframe:

```python
df = pd.read_parquet("https://tabarena.s3.us-west-2.amazonaws.com/results/df_results_leaderboard.parquet")
```

It has the following columns:

```python

# df.columns -> returns
Index(['dataset', 'fold', 'method', 'metric_error', 'time_train_s',
'time_infer_s', 'metric_error_val', 'config_selected', 'seed',
'method_metadata', 'ensemble_weight', 'problem_type', 'metric',
'method_type', 'method_subtype', 'config_type'],
dtype='object')
```

There are up to 30 "folds" – I get that the paper used 3-fold outer validation for scoring with up to 10 repeats. Can you please help me understand how do dataset fold indexes and repeat indexes are converted to these 30 folds.

Basically, which of the two options is correct (do we first iterate over fold and then over repeat or is it the other way around):

```python
# just an example
df_fold = 13

# option 1:
openml_fold = df_fold // 10
openml_repeat = df_fold % 10

# or option 2:
openml_fold = df_fold % 3
openml_repeat = df_fold // 3
```

---

To help you better understand where my question is coming from. I wanted to quickly check some results on a few different small dataset splits (e.g. fold=0, repeat in range(0,5) -- in openml terms when loading the data). And now I want to match results that I have to the dataframe.

Start with the generation or documentation for df_results_leaderboard.parquet and trace how its fold column is derived from the OpenML fold and repeat indexes. Confirm the mapping against the stated three outer folds and up to ten repeats, then document the conversion so users can reproduce selected dataset splits and match their results.

Written by the indexing model from the issue text.