Update Tasks table: real row counts, Kaggle backend, ibm-aml F1 metric

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

README.md

@@ -51,12 +51,17 @@ You provide the `ground_truth/<task>.csv` files yourself (one row per test entit
 
 ## Tasks
 
-| Task | Type | Metric | Test rows |
-| --- | --- | --- | --- |
-| `ieee-fraud-detection` | binary classification | AUC-ROC | ~118k |
-| `arxiv-citation` | binary classification | AUC-ROC | 19,394 |
-| `figraph` | binary anomaly detection | AUC-ROC | 3,596 |
-| `ibm-aml` | binary anomaly detection (preview) | AUC-PR | TBD |
+| Task | Type | Metric | Test rows | Backend |
+| --- | --- | --- | --- | --- |
+| `ieee-fraud-detection` | binary classification | AUC-ROC | 506,691 | Kaggle |
+| `arxiv-citation` | binary classification | AUC-ROC | 193,696 | local GT |
+| `figraph` | binary anomaly detection | AUC-ROC | 3,596 | local GT |
+| `ibm-aml` | binary anomaly detection | F1 (minority) | 863,900 | local GT |
+
+`ieee-fraud-detection` forwards your CSV to the Kaggle competition and
+returns the official private-leaderboard score. The hosted server uses its
+own Kaggle credentials for that — no setup needed on your side just to
+submit. (You only need `KAGGLE_USERNAME`/`KAGGLE_KEY` if you self-host.)
 
 ## How it works