Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,104 @@
+---
+license: mit
+language: en
+base_model: microsoft/deberta-v3-large
+tags:
+  - ai-generated-text-detection
+  - machine-generated-text
+  - deberta
+  - raid
+  - adversarial-robustness
+pipeline_tag: text-classification
+---
+
+# RawGuard (DeBERTa-ConPara)
+
+RawGuard 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.
+
+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.
+
+- **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,
+  HC3 Plus, MAGE and M4, grouped by source id.
+- **Output:** logit margin, `logit[AI] − logit[human]`. Higher is more
+  machine-like. Not a probability.
+
+## Results
+
+RAID hidden test (672,000 documents, 11 attacks): **AUROC 99.61**,
+**TPR@5% FPR 99.01**, **TPR@1% FPR 96.57**.
+
+Cross-dataset, balanced accuracy at one threshold calibrated on our source
+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
+external data for the other systems.
+
+## Usage
+
+The checkpoint is a plain PyTorch state dict with a small custom head, so it does
+not load through `AutoModelForSequenceClassification`. Use the loader from the
+repository:
+
+```python
+from src.rawguard import RawGuard          # pip install -r requirements.txt
+
+det = RawGuard.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
+```
+
+Inference-time Unicode normalisation is applied by default; it is what makes the
+detector robust to homoglyph and zero-width attacks.
+
+## Intended use and limits
+
+Intended as **supporting evidence for a human decision** — flagging text for
+review, studying detector behaviour, benchmarking. Not intended as a verdict, and
+not suitable for disciplinary or hiring decisions about individuals.
+
+Measured limits:
+
+- **Short text:** below ~60 words errors are enriched 4–5×. Treat under 75 words
+  with caution; under 25 words the score is meaningless.
+- **Academic prose:** false-positive rates between 13% and 67% depending on the
+  subcorpus. A flag on a student essay is not evidence of misconduct.
+- **Calibration:** the score is not a probability and saturates at the extremes.
+  Prefer coarse bands (`det.band()`) over percentages.
+- **Language:** English only.
+- **Drift:** trained against generators available in 2026; newer ones are
+  untested, and detectors decay as generators improve.
+- **Attacks not covered:** heavy paraphrasing by a strong model, and mixed
+  human/machine documents, remain hard.
+
+## Training and evaluation protocol
+
+Full corpus construction, the leakage-free splitting, the 2×2×2 factorial and the
+fixed-threshold evaluation protocol are in the repository. Every number above is
+reproducible from `evaluation/`.
+
+## Citation
+
+```bibtex
+@inproceedings{mady2026rawguard,
+  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.},
+  booktitle = {Proceedings of AACL-IJCNLP 2026},
+  year      = {2026},
+  note      = {To appear}
+}
+```
+
+License: MIT, matching the DeBERTa-v3-large backbone.