Model card: DeBERTa-ConPara naming, conpara API, links

README.md

@@ -11,9 +11,9 @@ tags:
 pipeline_tag: text-classification
 ---
 
-# RawGuard (DeBERTa-ConPara)
+# DeBERTa-ConPara
 
-RawGuard detects machine-generated English text and stays accurate under the
+DeBERTa-ConPara detects machine-generated English text and stays accurate under the
 adversarial edits that defeat most detectors: homoglyph substitution, zero-width
 character insertion, whitespace and typographic attacks.
 
@@ -21,11 +21,11 @@ It is the system reported in our AACL-IJCNLP 2026 main-conference paper. The
 finding behind it: normalising the **training** corpus deduplicates it — 35.4% of
 RAID rows collapse into byte-identical copies of their clean siblings, deleting
 the adversarial supervision — while normalising at **inference** is an effective
-defence. RawGuard trains on raw text and normalises only at inference.
+defence. DeBERTa-ConPara trains on raw text and normalises only at inference.
 
 - **Architecture:** DeBERTa-v3-large → CLS token → Linear(1024, 512) → GELU →
   Dropout(0.1) → Linear(512, 2). No feature branch.
-- **Training data:** 1.56M documents, leakage-free stratified splits over RAID,
+- **Training data:** 1.55M documents, leakage-free stratified splits over RAID,
   HC3 Plus, MAGE and M4, grouped by source id.
 - **Output:** logit margin, `logit[AI] − logit[human]`. Higher is more
   machine-like. Not a probability.
@@ -40,9 +40,9 @@ validation split and held fixed: HC3-QA 99.69, HC3-SI 83.50, MAGE 96.23,
 M4 98.27.
 
 The README of the [GitHub repository](https://github.com/MohamedMady19/deberta-conpara)
-compares RawGuard with every RAID leaderboard system that publishes a checkpoint,
-and states the two caveats those numbers need: MELD scores higher than RawGuard
-on RAID itself, and HC3/MAGE/M4 are training sources for RawGuard while being
+compares DeBERTa-ConPara with every RAID leaderboard system that publishes a checkpoint,
+and states the two caveats those numbers need: MELD scores higher than DeBERTa-ConPara
+on RAID itself, and HC3/MAGE/M4 are training sources for DeBERTa-ConPara while being
 external data for the other systems.
 
 ## Usage
@@ -52,9 +52,9 @@ not load through `AutoModelForSequenceClassification`. Use the loader from the
 repository:
 
 ```python
-from src.rawguard import RawGuard          # pip install -r requirements.txt
+from src.conpara import ConPara          # pip install -r requirements.txt
 
-det = RawGuard.from_pretrained()           # pulls rawguard.pt from this repo
+det = ConPara.from_pretrained()           # pulls rawguard.pt from this repo
 det.score(["a document to check"])         # logit margin
 det.predict(["a document to check"])       # bool at the stored threshold
 ```
@@ -91,7 +91,7 @@ reproducible from `evaluation/`.
 ## Citation
 
 ```bibtex
-@inproceedings{mady2026rawguard,
+@inproceedings{mady2026conpara,
   title     = {Where You Normalise Matters: Unicode Preprocessing and the
                Robustness of AI-Generated Text Detection},
   author    = {Mady, Mohamed and Li, Yupei and Reschke, Johannes and Schuller, Bj\"orn W.},
@@ -102,3 +102,9 @@ reproducible from `evaluation/`.
 ```
 
 License: MIT, matching the DeBERTa-v3-large backbone.
+
+## Links
+
+- Code and evaluation scripts: https://github.com/MohamedMady19/deberta-conpara
+- Live demo: https://huggingface.co/spaces/mohamedmady/deberta-conpara
+- Paper: "DeBERTa-ConPara: Attack-Aware and Deployment-Realistic Detection of AI-Generated Text", AACL-IJCNLP 2026 (arXiv link to follow)