Upload README.md with huggingface_hub

README.md

@@ -16,12 +16,12 @@ metrics:
   - accuracy
 ---
 
-# sourcetrace — the fitted head of CORE (open-set audio deepfake attribution)
+# sourcetrace — the fitted head of CoRA (open-set audio deepfake attribution)
 
 The fitted head of [`sourcetrace`](https://github.com/pujariaditya/sourcetrace),
 which names **which synthesis model produced a synthetic speech clip** — or reports
-that the model is not one it has seen. It is the artifact behind the paper *CORE:
-Enhancing Open-Set Audio Deepfake Attribution with Neural Codec Residuals*.
+that the model is not one it has seen. It is the artifact behind the paper *CoRA:
+Robust Open-Set Audio Deepfake Attribution with Neural Codec Residuals*.
 
 **This is not a standalone model.** `mlaad_v5.pt` is a `torch.save` dict with
 `format: "sourcetrace-method-checkpoint"`, loaded by `sourcetrace.method.Method.load`.
@@ -139,7 +139,7 @@ redistributed here.
 
 ## Citation
 
-See [`CITATION.cff`](https://github.com/pujariaditya/sourcetrace/blob/main/CITATION.cff)
+See [`CITATION.cff`](https://github.com/pujariaditya/sourcetrace/blob/master/CITATION.cff)
 in the code repository, which is the single source for how to cite this.
 
 Please also cite the benchmarks (MLAAD, STOPA) and the baselines this is compared