Added more details on October 13th test set results

about.py

@@ -8,6 +8,18 @@ from constants import (
     TUTORIAL_URL,
 )
 
+WEBSITE_HEADER = f"""
+    ## Welcome to the Ginkgo Antibody Developability Benchmark!
+
+    Participants can submit their model to the leaderboards by simply uploading a CSV file (see the "✉️ Submit" tab).
+
+    You can **predict any or all of the 5 properties**, and you can filter the main leaderboard by property.
+    See more details in the "{ABOUT_TAB_NAME}" tab.
+
+    🗓️ There will be a test set scoring on **October 13th** (which will score all the latest test set submissions at that point). 
+    Use this to refine your models before the final submission deadline on **1 November 2025**.
+"""
+
 ABOUT_INTRO = f"""
 ## About this challenge
 
@@ -52,7 +64,7 @@ ABOUT_TEXT = f"""
 
 Check out our introductory tutorial on training an antibody developability prediction model with cross-validation [here]({TUTORIAL_URL}).
 
-⏰ Submissions close on **1 November 2025**.
+⏰ Submissions close on **1 November 2025**, but there will be an early test set scoring on **October 13th** (which will score all the latest test set submissions at that point, and then you can refine your model and resubmit).
 
 ---
 
@@ -71,7 +83,7 @@ We're working on getting more public models added, so that participants have mor
 
 #### How to contribute?
 
-We'd like to add some more existing developability models to the leaderboard. Some examples of models we'd like to add:
+We'd like to add more existing developability models to the leaderboard. Some examples of models we'd like to add:
 - Absolute folding stability models (for Thermostability)
 - PROPERMAB
 - AbMelt (requires GROMACS for MD simulations)
@@ -165,9 +177,9 @@ You do **not** need to predict all 5 properties — each property has its own le
    - **Private Test Set predictions** (final test submission)
 2. Each CSV should contain `antibody_name` + one column per property you are predicting (e.g. `"antibody_name,Titer,PR_CHO"` if your model predicts Titer and Polyreactivity).
    - List of valid property names: `{', '.join(ASSAY_LIST)}`.
+3. Submit as many times as you like, and the latest submission will be used for the leaderboard (and test set scoring at the end of the competition).
 
-The GDPa1 results should appear on the leaderboard within a minute, and can also be calculated manually using Spearman rank correlation. The **private test set results will not appear on the leaderboards at first**, and will be used to determine the winners at the close of the competition.
-We may release private test set results at intermediate points during the competition.
+The GDPa1 results should appear on the leaderboard within a minute, and can also be calculated manually using average Spearman rank correlation across the 5 folds. 
 
 ## Cross-validation
 
@@ -175,5 +187,10 @@ For the GDPa1 cross-validation predictions, use the `"hierarchical_cluster_IgG_i
 Submit a CSV file in the same format but also containing the `"hierarchical_cluster_IgG_isotype_stratified_fold"` column.
 Check out our tutorial on training an antibody developability prediction model with cross-validation [here]({TUTORIAL_URL}).
 
+## Test set
+
+The **private test set results will not appear on the leaderboards at first**, and will be used to determine the winners at the close of the competition.
+🗓️ There will be a test set scoring on **October 13th** (which will score all the latest test set submissions at that point).
+
 Submissions close on **1 November 2025**.
 """

app.py

@@ -8,7 +8,7 @@ from dotenv import load_dotenv
 
 load_dotenv()  # Load environment variables from .env file (before imports)
 
-from about import ABOUT_INTRO, ABOUT_TEXT, FAQS, SUBMIT_INSTRUCTIONS
+from about import ABOUT_INTRO, ABOUT_TEXT, FAQS, SUBMIT_INSTRUCTIONS, WEBSITE_HEADER
 from constants import (
     ASSAY_RENAME,  # noqa: F401
     SEQUENCES_FILE_DICT,
@@ -88,15 +88,7 @@ with gr.Blocks(theme=gr.themes.Default(text_size=sizes.text_lg)) as demo:
     with gr.Row():
         with gr.Column(scale=6):  # bigger text area
             gr.Markdown(
-                f"""
-                ## Welcome to the Ginkgo Antibody Developability Benchmark!
-
-                Participants can submit their model to the leaderboards by simply uploading a CSV file (see the "✉️ Submit" tab).
-
-                You can **predict any or all of the 5 properties**, and you can filter the main leaderboard by property.
-                See more details in the "{ABOUT_TAB_NAME}" tab.
-                Submissions close on 1 November 2025.
-                """
+                WEBSITE_HEADER
             )
         with gr.Column(scale=2):  # smaller side column for logo
             gr.Image(