card: rename to Hybrid-Averse

README.md

@@ -14,19 +14,21 @@ tags:
 library_name: peft
 ---
 
-# VericodingEBM — Per-Line Fault Localizer for Verus
+# VericodingEBM — Hybrid-Averse checkpoint
 
-LoRA + per-line scalar head trained on top of [Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct) to score every line of a Verus implementation with an energy proxy for *"this line is the bug."*
+A LoRA + per-line scalar head trained on top of [Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct) to score every line of a Verus implementation with an energy proxy for *"this line is the bug."*
 
-Submitted to the **Apart × Atlas Computing Secure Program Synthesis Hackathon, Track 3 (Vericoding)**.
+This is the canonical **Hybrid-Averse** checkpoint reported in the paper — the post-fix model that learned to anti-correlate with the `// FAILS` debug marker rather than rely on it.
+
+Submitted to the Apart × Atlas Computing **Secure Program Synthesis Hackathon, Track 3 (Vericoding)**.
 
 📄 **Paper:** see [`paper/main.pdf`](https://github.com/ozlabsai/VericodingEBM/blob/main/paper/main.pdf)
 💾 **Code + reproducibility:** https://github.com/ozlabsai/VericodingEBM
 📊 **Training data:** [`OzLabs/VericodingEBM-data`](https://huggingface.co/datasets/OzLabs/VericodingEBM-data)
 
-## Headline results (run #10, this checkpoint)
+## Headline results (Hybrid-Averse)
 
-| Measurement | This model | Best frontier LLM |
+| Measurement | Hybrid-Averse (this model) | Best frontier LLM |
 |---|---|---|
 | Per-line top-3 recall on Verus dev-test (n=609 FAILs) | **0.84** | 0.74 (Claude Opus 4.7) |
 | Whole-impl discrimination AUROC | 0.78 | **0.91** (GPT-5.5) |
@@ -42,7 +44,7 @@ To run inference you need all three files plus the training code at https://gith
 
 ## Marker-leak audit (paper §4.6)
 
-This checkpoint is **marker-AVERSE**: its per-line top-1 recall jumps from 4% to 56% when the `// FAILS` debug markers are stripped from the input (delta = −52pp). This is the result of the counterfactual-marker augmentation described in paper §B; pre-fix checkpoints (run #7) are marker-RELIANT (signal collapses without markers).
+This checkpoint is **marker-AVERSE**: per-line top-1 recall jumps from 4% → 56% when the `// FAILS` debug markers are stripped from the input (delta = −52pp). This is the result of the counterfactual-marker augmentation described in paper §B. The pre-audit **Sentinel-Reliant** checkpoint (not released here) shows the opposite regime — signal collapses without markers, exposing the leak that motivated this work.
 
 ## License