README: add arXiv link + citation

README.md

@@ -1,12 +1,28 @@
 # SE-Probe model artefacts
 
-Companion model checkpoints for [SE-Probe](https://github.com/YairAmar/SE-Probe).
+Companion model checkpoints for [SE-Probe](https://github.com/YairAmar/SE-Probe), the public code release for *"Where Does Speech Enhancement Adapt? Probing Study Under Controlled Degradation"* (Amar, Ivry, Cohen, 2026).
+
+📄 Paper: <https://arxiv.org/abs/2512.00482>
 
 ## Files
 
-- `muse_reverb_e48.pt` (2.3 MB): Reverb-fine-tuned MUSE checkpoint (epoch 48). PESQ 3.02 / STOI 0.944 on the 824x5 RIR test set; corresponds to the FT model probed in Section 4.2 of the paper. Trained from the upstream noise-only MUSE g_best, fine-tuned on RIR-Mega convolutive mixtures.
+- `muse_reverb_e48.pt` (2.3 MB): Reverb fine-tuned MUSE checkpoint (epoch 48). PESQ 3.02 / STOI 0.944 on the 824x5 RIR test set; this is the model probed in Section 4.2 of the paper. Trained from the upstream noise-only MUSE g_best, fine-tuned on RIR-Mega convolutive mixtures.
+
+The training pipeline that produced this checkpoint is vendored in the SE-Probe repository under `training/` (originally <https://github.com/YairAmar/muse-dereverb-ft>).
+
+## Citation
 
-Training pipeline that produced this checkpoint: <https://github.com/YairAmar/muse-dereverb-ft>.
+```bibtex
+@article{amar2026seprobe,
+  title         = {Where Does Speech Enhancement Adapt? Probing Study Under Controlled Degradation},
+  author        = {Amar, Yair and Ivry, Amir and Cohen, Israel},
+  year          = {2026},
+  eprint        = {2512.00482},
+  archivePrefix = {arXiv},
+  primaryClass  = {eess.AS},
+  url           = {https://arxiv.org/abs/2512.00482}
+}
+```
 
 ## License