Update links to github.com/LakoreAI/sev

README.md

@@ -44,7 +44,7 @@ model-index:
 
 A ModernBERT-large decision model fine-tuned on `LocalLLaMA/typed-decisions` with **plain cross-entropy** against the teacher's soft targets, at the documented 1024-token context / 256-token option budget.
 
-It is the best-performing checkpoint from the reproduction study *Dissecting RLCD*, where I took apart the training method behind TypeSafe's Jev and its open reproduction, Laya. The short version of that study: Laya's RL term is a noise-smoothed cross-entropy gradient, and on this benchmark plain CE matches or beats it on every proper score.
+It is the best-performing checkpoint from the **Sev** study (*Dissecting RLCD*), where I took apart the training method behind TypeSafe's Jev and its open reproduction, Laya. The short version of that study: Laya's RL term is a noise-smoothed cross-entropy gradient, and on this benchmark plain CE matches or beats it on every proper score.
 
 **Test-set results (2,000 decisions, 400 cases):**
 
@@ -98,7 +98,7 @@ Structured, closed-set probabilistic decisions over short English text: routing,
 This is a custom architecture, not a `transformers` `AutoModel`. Load it with the code from the reproduction repo:
 
 ```bash
-git clone https://github.com/LakoreAI/rlcd-reverse-engineering
+git clone https://github.com/LakoreAI/sev
 cd rlcd-reverse-engineering && uv sync
 ```
 
@@ -166,7 +166,7 @@ This checkpoint is deliberately RL-free. In the accompanying study, adding Laya'
 
 ## Links
 
-- Code, configs, and per-run results: [LakoreAI/rlcd-reverse-engineering](https://github.com/LakoreAI/rlcd-reverse-engineering)
+- Code, configs, and per-run results: [LakoreAI/sev](https://github.com/LakoreAI/sev)
 - All ablation checkpoints and metrics: [minhleduc/rlcd-e2-checkpoints](https://huggingface.co/minhleduc/rlcd-e2-checkpoints)
 - Base model: [convaiinnovations/laya](https://huggingface.co/convaiinnovations/laya)
 - Dataset: [LocalLLaMA/typed-decisions](https://huggingface.co/datasets/LocalLLaMA/typed-decisions)
@@ -178,6 +178,6 @@ This checkpoint is deliberately RL-free. In the accompanying study, adding Laya'
   title  = {Dissecting RLCD: What Reinforcement Learning Does (and Doesn't) Do for Calibrated Typed Decisions},
   author = {Le Duc Minh},
   year   = {2026},
-  url    = {https://github.com/LakoreAI/rlcd-reverse-engineering}
+  url    = {https://github.com/LakoreAI/sev}
 }
 ```