Update README, metadata, and aggregated tables

README.md

@@ -26,18 +26,24 @@ Models are trained on the human genome (**GRCh38 / hg38**) against the observed
 
 ## Repository layout
 
-Files are organized one directory per experiment, `<encid>/`:
+Each experiment's five fold checkpoints live under `<encid>/`:
 
 | file | description |
 |---|---|
-| `cherimoya.fold_<i>.torch` | the model checkpoint (EMA shadow weights) |
-| `cherimoya.fold_<i>.performance.tsv` | validation metrics for that fold |
-| `cherimoya.fold_<i>.log` | training log |
-| `cherimoya.fold_<i>.fit.json` / `.evaluate.json` | training / evaluation settings |
+| `<encid>/cherimoya.fold_<i>.torch` | checkpoint for fold `i` (EMA shadow weights) |
 
-`performance.tsv` has one row with columns (fixed order): `profile_mnll profile_jsd profile_pearson profile_spearman count_pearson count_spearman count_mse`; the headline metrics are `profile_pearson` (profile shape) and `count_pearson` (total accessibility).
+Repository-level files:
 
-Experiment-level metadata is in `CATv1-metadata.tsv` (keyed by `experiment_accession`), and `manifest.csv` lists exactly which experiments and folds are included. Each `experiment_accession` is the source ENCODE experiment the models were trained on (`https://www.encodeproject.org/experiments/<experiment_accession>/`), and the paired `annotation_accession` points to the ENCODE ChromBPNet model annotation for that same experiment (`https://www.encodeproject.org/annotations/<annotation_accession>/`).
+| file | description |
+|---|---|
+| `performance.tsv` | validation metrics for every experiment and fold |
+| `CATv1-metadata.tsv` | experiment metadata, keyed by `experiment_accession` |
+| `manifest.csv` | the full list of experiments and folds included |
+| `fit.json` / `evaluate.json` | a representative example of the per-fold training / evaluation settings |
+
+`performance.tsv` has one row per experiment-fold: the first two columns are `experiment_accession` and `fold`, followed by `profile_mnll profile_jsd profile_pearson profile_spearman count_pearson count_spearman count_mse`. The headline metrics are `profile_pearson` (profile shape) and `count_pearson` (total accessibility).
+
+Each `experiment_accession` is the source ENCODE experiment the models were trained on (`https://www.encodeproject.org/experiments/<experiment_accession>/`), and the paired `annotation_accession` points to the ENCODE ChromBPNet model annotation for that same experiment (`https://www.encodeproject.org/annotations/<annotation_accession>/`).
 
 ## Which model should I use?