Add exp uncertainties

app.py

@@ -137,8 +137,8 @@ with gr.Blocks(title="OpenADMET ADMET Challenge", fill_height=False,
                 Go to the **Leaderboard** to check out how the challenge is going. 
                 To participate, head out to the **Submit** tab and upload your results as a `CSV` file.
                     
-                We are releasing an intermediate leaderboard on December 2nd so stay tuned!
-                        The submission cutoff for this leaderboard will be **Dec 1st at 11:59PM GMT.**
+                We released an intermediate leaderboard on December 2nd, with submissions evaluated against the full blinded test set.
+                    Check it out on the OpenADMET [blog](https://openadmet.ghost.io/openadmet-expansionrx-blind-challenge-2/)!
                         
                 """
                 )
@@ -227,6 +227,28 @@ with gr.Blocks(title="OpenADMET ADMET Challenge", fill_height=False,
     The training and blinded test set will also be made available on the [CDD Vault](https://www.collaborativedrug.com/). An account to access the CDD Vault can be requested by filling out this [form](https://forms.gle/KiviZ7AaGcuqtrwH8).
     Note that by joining the Vault, your account will be visible to other participants, so this option is **not recommended for those wishing to remain anonymous.**
 
+    ### Experiment uncertainties
+    For each endpoint, we present the experimental error statistics, measured with different control compounds. Special thanks Jon Ainsley for providing this data!
+
+    | Property | Compound | Count | Min | Max | SD | Mean abs. dev. | Median abs. dev. | Mean | Median |
+    | :---- | :---- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- |
+    | LogD | Progesterone | 456 | 3.7 | 4.02 | 0.07 | 0.06 | 0.05 | 3.85 | 3.85 |
+    | KSOL | Progesterone | 336 | 12.33 | 25.69 | 2.28 | 1.79 | 1.48 | 16.88 | 16.8 |
+    | MLM CLint | Verapamil | 276 | 237.67 | 514.78 | 76.03 | 69.34 | 36.78 | 334.41 | 292.73 |
+    | HLM CLint | Verapamil | 359 | 104.68 | 304.07 | 61.28 | 57.58 | 61.9 | 197.84 | 210.25 |
+    | Caco-2 Permeability Efflux | Atenolol | 113 | 0.85 | 1.71 | 0.2 | 0.17 | 0.16 | 1.28 | 1.27 |
+    |  | Digoxin | 383 | 25.08 | 69.71 | 10.8 | 8.77 | 6.17 | 37.76 | 34.22 |
+    |  | Minoxidil | 383 | 0.74 | 1.39 | 0.12 | 0.1 | 0.08 | 1.06 | 1.05 |
+    |  | Propranolol | 270 | 0.66 | 1.29 | 0.13 | 0.11 | 0.09 | 0.96 | 0.94 |
+    | Caco-2 Permeability Papp A\>B | Atenolol | 113 | 0.23 | 0.96 | 0.17 | 0.14 | 0.13 | 0.57 | 0.56 |
+    |  | Digoxin | 383 | 0.22 | 0.82 | 0.13 | 0.11 | 0.1 | 0.54 | 0.55 |
+    |  | Minoxidil | 383 | 4.99 | 9.98 | 1.17 | 0.98 | 0.87 | 7.8 | 7.81 |
+    |  | Propranolol | 270 | 16.16 | 33.93 | 3.57 | 2.88 | 2.35 | 25.34 | 25.52 |
+    | MPPB % Unbound | Ketoconazole | 265 | 98.96 | 99.62 | 0.13 | 0.1 | 0.08 | 99.35 | 99.35 |
+    | MBPB % Unbound | Propranolol | 260 | 96.55 | 97.88 | 0.26 | 0.21 | 0.18 | 97.3 | 97.33 |
+    | MGPB % Unbound | Propranolol | 95 | 92.28 | 98.53 | 1.06 | 0.76 | 0.54 | 94.18 | 93.94 |
+
+
     ## 📝 Evaluation
     The challenge will be judged based on the following criteria:
     - We welcome submissions of any kind, including machine learning and physics-based approaches. You can also employ pre-training approaches as you see fit, 
@@ -247,6 +269,7 @@ with gr.Blocks(title="OpenADMET ADMET Challenge", fill_height=False,
     - **December 1st:** Intermediate leaderboard release
     - **January 19, 2026:** Submission closes
     - **January 26, 2026:** Winners announced
+
     ## Acknowledgements
     We gratefully acknowledge Jon Ainsley, Andrew Good, Elyse Bourque, Lakshminarayana Vogeti, Renato Skerlj, Tiansheng Wang, and Mark Ledeboer for generously
     providing the Expansion Therapeutics dataset used in this challenge as an in-kind contribution.
@@ -262,7 +285,7 @@ with gr.Blocks(title="OpenADMET ADMET Challenge", fill_height=False,
             </style>
             <style>
             #welcome-md table {
-                width: 60%;
+                width: 80%;
                 border-collapse: collapse;
                 font-size: 0.95rem;     
                 line-height: 1.2;