Deploy Space: update src

src/about.py

@@ -15,27 +15,22 @@ subsequent domain tab retains the original absolute per-dataset results.
 LLM_BENCHMARKS_TEXT = """
 ## 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.
+Community models are evaluated through owner-operated HTTPS endpoints. Copy the
+portable FastAPI template in `examples/community_endpoint/`, replace its
+`forecast_one` function, and deploy it on your own inference server or existing
+cloud service. A paid Hugging Face Space is optional and a Static Space cannot
+run the forecasting API.
+
+The endpoint receives only causal history, prediction length, frequency, and
+requested quantiles. It never receives future labels. Servers behind NAT can use
+a stable named HTTPS tunnel; temporary Quick Tunnel URLs are not accepted.
+
+Before submitting, run `scripts/validate_external_model_endpoint.py` against the
+public `/forecast` URL and generate `community_model.yaml` with
+`scripts/generate_community_model_metadata.py`. Submit the public model card,
+endpoint-code URL, endpoint URL, metadata, and successful validator receipt
+through the community model request form. Accepted entries are evaluated only
+on future live releases.
 
 ## Metrics
 

src/utils.py

@@ -1005,6 +1005,24 @@ def load_baseline_rank_history_monthly(root_dir: str = "results") -> pd.DataFram
     present = [c for c in _MONTHLY_DISPLAY_COLS if c in monthly.columns]
     return monthly[present].sort_values(["month", "model"]).reset_index(drop=True)
 
+
+def load_fixed_window_rank(root_dir: str = "results", window: str = "1d") -> pd.DataFrame:
+    """Load a wall-clock 1d/7d/30d leaderboard generated from canonical releases."""
+
+    if window not in {"1d", "7d", "30d"}:
+        raise ValueError(f"Unsupported fixed leaderboard window: {window}")
+    path = Path(root_dir) / "aggregates" / f"live_rank_{window}.csv"
+    if not path.exists():
+        return pd.DataFrame()
+    try:
+        frame = pd.read_csv(path)
+    except Exception:
+        return pd.DataFrame()
+    for column in ("Rank", "AverageRank", "WinRate", "Elo"):
+        if column in frame.columns:
+            frame[column] = pd.to_numeric(frame[column], errors="coerce").map(format_rank_number)
+    return frame
+
 # ---------------------------------------------------------------------------
 # Forecast snapshot utilities
 # ---------------------------------------------------------------------------