Deploy Space: update src

src/about.py

@@ -10,27 +10,35 @@ ranks**. Use the **Overall** tab for aggregate scores; each subsequent tab is on
 """
 
 LLM_BENCHMARKS_TEXT = """
-## How to participate
-
-1. Clone [TSFM_Bench](https://github.com/zhouziyu02/TSFM_Bench)
-2. Implement your model against the streaming data interface (`tsfm_bench.data`)
-3. Run evaluation and write `results/<MODEL_NAME>/all_results.csv`
-4. Open a pull request; results sync to this leaderboard
+## How to participate (Submit a New Model)
+
+To evaluate your model on this leaderboard (run securely on our servers to prevent test data leakage while we absorb the compute costs), you can submit a Pull Request to our repository. Please prepare and submit the following files:
+
+1. **Model Source Code Wrapper**:
+   - Create a Python file under `space/user_models/<your_model_id>.py` implementing a predictor class that inherits from `RepresentablePredictor`.
+   - Implement the `predict(dataset: GluonDataset) -> Iterator[Forecast]` method conforming to our evaluation input-output interface.
+2. **Model Weights / Checkpoint**:
+   - Provide your pre-trained model weights by either specifying a public Hugging Face model ID, or adding a checkpoint file under `space/user_models/<your_model_id>_checkpoint.pt`.
+3. **Dependency Environment**:
+   - Add any custom libraries your model depends on to the optional packages list in `pyproject.toml` or `space/requirements.txt`.
+4. **Model Configuration**:
+   - Register your model specification in [configs/models/online_tsfm.yaml](file:///Users/bytedance/Desktop/TSFM_Bench/configs/models/online_tsfm.yaml):
+     ```yaml
+       - model_id: local/<your_model_id>
+         display_name: My-Custom-TSFM
+         model_type: local
+         org: My Organization
+         model_class: user_models.<your_model_id>.<ModelClass>
+         model_path: space/user_models/<your_model_id>_checkpoint.pt
+     ```
+
+Once your Pull Request is opened, our automated sandbox pipeline will load your model, run zero-shot evaluations on the live test streams under the exact same conditions, compute the metrics fairly, and update the leaderboard automatically.
 
 ## Metrics
 
 - **MASE** — Mean Absolute Scaled Error (absolute)
 - **CRPS** — Mean Weighted Sum Quantile Loss (probabilistic forecast quality)
 - **MASE_Rank** / **CRPS_Rank** — per-dataset rank (lower is better)
-
-## Automated evaluation
-
-```bash
-export TSFM_API_KEY=your_key
-export HF_TOKEN=your_hf_token
-python scripts/run_online_daemon.py --once
-python scripts/run_online_daemon.py   # every 5 min by default
-```
 """
 
 CITATION_BUTTON_LABEL = "Copy citation"

src/utils.py

@@ -752,9 +752,10 @@ def make_domain_pie_chart(root_dir: str = "results") -> object | None:
         marker=dict(colors=colors),
         hole=0.25,
     )])
+    date_str = today_start.strftime("%Y-%m-%d")
     fig.update_layout(
         title=dict(
-            text="Evaluated timestamps by domain (today, UTC+8)",
+            text=f"Evaluated timestamps by domain ({date_str}, UTC+8)",
             font=dict(size=16, weight="bold"),
         ),
         margin=dict(l=20, r=20, t=60, b=20),