Update README.md

README.md

@@ -5,15 +5,15 @@ tags:
   - distilbert
   - text-classification
   - security
-  - oracle-shield
+  - arbiter
 pipeline_tag: text-classification
 ---
 
-# Oracle Shield — Log threat classifier
+# Arbiter — Log threat classifier
 
 ## What this is
 
-A **DistilBERT** sequence-classification checkpoint fine-tuned for Oracle Shield.
+A **DistilBERT** sequence-classification checkpoint fine-tuned for **[Arbiter](https://github.com/SentinelSage/arbiter)**.
 
 Given a short security-log style string, it predicts one of four actions:
 
@@ -24,39 +24,58 @@ Given a short security-log style string, it predicts one of four actions:
 | 2 | warn |
 | 3 | none |
 
-The Oracle Shield app then scales a threat score from the predicted class / probabilities and may adjust the final recommendation with a separate rule-based layer.
+The Arbiter app then scales a threat score from the predicted class / probabilities and may adjust the final recommendation with a separate rule-based layer (`refine_action`).
 
 ## Project
 
-Part of **Oracle Shield** (Django + React): paste a security log or ask a cybersecurity question.
+Part of **Arbiter** (Django + React): paste a security log or ask a cybersecurity question.
 
-This repository holds **weights only**. Application code is in the public Oracle Shield GitHub repository.
+This repository holds **weights only**. Application code: [github.com/SentinelSage/arbiter](https://github.com/SentinelSage/arbiter).
 
 ## Training note
 
 This is a **custom fine-tune**, not an unmodified public DistilBERT base checkpoint. Do not treat Hub `distilbert-base-uncased` (or similar) as a drop-in substitute for this artifact.
 
+**Training data:** custom-curated, **unpublished** project data. There is no public labelled cybersecurity corpus linked as a training set for this demo.
+
 ## Intended use
 
-- Running the Oracle Shield full-ML path locally
+- Running the Arbiter full-ML path locally
 - Experimentation and educational use with the companion application
 
 **Not** a production SOC product. No warranty. Outputs can be wrong; do not use for live blocking, compliance, or incident response without your own validation.
 
-## How Oracle Shield loads it
+## How Arbiter loads it
 
-Local path after download:
+Local path after download (`scripts/download_models.py` or equivalent):
 
 ```text
 backend/models/log_based_model/
 ```
 
-Loaded with Hugging Face `DistilBertForSequenceClassification.from_pretrained(<local_or_hub_id>)` when `ORACLE_DEMO_MODE=false`.
+Loaded with Hugging Face `DistilBertForSequenceClassification.from_pretrained(<local_or_hub_id>)` when `ARBITER_DEMO_MODE=false`.
 
 ## Files
 
 Expect a standard Transformers export, e.g. `model.safetensors`, `config.json`, tokenizer files (`vocab.txt`, `tokenizer_config.json`, …).
 
+## Method / citations
+
+If you reference this work:
+
+- **DistilBERT:** Sanh, V., Debut, L., Chaumond, J., & Wolf, T. (2019). *DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter.*  
+  Base: [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased)
+- **Transformers:** Wolf, T., et al. (2020). *Transformers: State-of-the-Art Natural Language Processing.* EMNLP.  
+  [huggingface/transformers](https://github.com/huggingface/transformers)
+- **PyTorch:** Paszke, A., et al. (2019). *PyTorch: An Imperative Style, High-Performance Deep Learning Library.* NeurIPS.  
+  [pytorch/pytorch](https://github.com/pytorch/pytorch)
+
+## Safety
+
+Research / portfolio demo only. Classifier confidence is **not calibrated**. Do not paste production logs, PII, or credentials into demos that use these weights on a shared host.
+
 ## License
 
 Apache License 2.0. Demo only — provided as-is, without warranty of any kind.
+
+Copyright 2026 Ryan Vong / Sentinel Sage