Update model card: accurate TempoPFN attribution + Apache-2.0 license

README.md

@@ -19,8 +19,9 @@ indicators in a **single forward pass** (no autoregressive windowing) and return
 
 It is trained in two stages:
 
-1. Base model: A ~1.2M-parameter linear-RNN backbone (architecture inspired by
-   TempoPFN), trained from scratch **entirely on synthetic data** (no real macro data).
+1. Base model: A ~1.2M-parameter linear-RNN backbone (built on
+   [TempoPFN](https://github.com/automl/TempoPFN), Apache-2.0), trained from
+   scratch **entirely on synthetic data** (no real macro data).
 2. **MacroCast** — Base model **fine-tuned** on FRED-MD via an expanding-window,
    real-time-vintage procedure, using a mixture of macro-calibrated synthetic
    panels (block-bootstrap, per-variable AR, Dynamic Factor Model, and BVAR).
@@ -75,6 +76,8 @@ point, quantiles = f.predict(history, horizon=12, freq="M")
 - Built for **monthly macroeconomic** panels. Feed transformed/stationary inputs.
 - Forecasts are statistical outputs, **not financial or policy advice**.
 
-## Acknowledgements
-Architecture inspired by [TempoPFN](https://huggingface.co/AutoML-org/TempoPFN)
-(Apache-2.0); the vendored model code under `tempopfn/` derives from that project.
+## Acknowledgements & license
+Built on [TempoPFN](https://github.com/automl/TempoPFN) (Apache-2.0): the model
+backbone, trainer, and synthetic-data generators are vendored from that project
+and modified for macroeconomic forecasting. Released under Apache-2.0. Please
+cite TempoPFN (Moroshan et al., 2025; [arXiv:2510.25502](https://arxiv.org/abs/2510.25502)).