Updated the read me with demo commans, created a good first issue template, added demo commands examples, and sample report json format

.github/ISSUE_TEMPLATE/good_first_issue.md

@@ -0,0 +1,35 @@
+---
+name: Good first issue
+about: A simple, well-defined task that’s perfect for someone new to the project.
+title: "Good First Issue: [TASK]"
+labels: "good first issue"
+assignees: ""
+---
+
+## Description
+
+This is a simple task for first-time contributors! Please follow the steps below to implement the feature or fix the bug.
+
+### Steps to reproduce
+
+- Step 1
+- Step 2
+- Step 3
+
+### Expected behavior
+
+- What should happen after the task is completed
+
+### How to contribute
+
+1. Fork the repository.
+2. Create a new branch from `main` (`git checkout -b feature/new-feature`).
+3. Work on the task and commit your changes (`git commit -m "Implement new feature"`).
+4. Push the changes and create a pull request.
+5. Ensure that your code passes all tests and is documented.
+
+---
+
+### Additional Context
+
+- Link to relevant resources (e.g., issues, discussions, or other PRs).

README.md

@@ -20,3 +20,27 @@ This comes with risks:
 ---
 
 ## Other Functionaly will be updated as the project goes on
+
+## Quickstart
+
+```bash
+python -m venv .venv && source .venv/bin/activate
+pip install -e .
+pip install pytest pytest-cov
+
+# (A) Train demo models (fast settings)
+
+#Clean model on 5 epochs (Increase epochs for better accuracy, but it will take longer)
+python -m scripts.train_resnet18 --dataset clean  --epochs 5 --output_path models/resnet18_clean.pth
+
+#Poisoned model on 5 epochs (Increase epochs for better accuracy, but it will take longer)
+python -m scripts.train_resnet18 --dataset poison --train_poison_rate 0.1 --target_class 0 \
+  --epochs 5 --output_path models/resnet18_poison.pth
+
+# (B) Run detection
+mithridatium detect --model models/resnet18_poison.pth --defense mmbd --data cifar10 --out reports/mmbd.json
+
+# (C) See summary
+cat reports/mmbd.json
+
+```

examples/demo_commands.md

@@ -0,0 +1,28 @@
+# Demo Commands for Mithridatium
+
+## 1. Set up environment:
+
+```bash
+python -m venv .venv
+source .venv/bin/activate
+pip install -e .
+pip install pytest pytest-cov
+```
+
+## 2. Train Clean model:
+
+```bash
+python -m scripts.train_resnet18 --dataset clean --epochs 5 --output_path models/resnet18_clean.pth
+```
+
+## 3. Train Poisoned model:
+
+```bash
+python -m scripts.train_resnet18 --dataset poison --train_poison_rate 0.1 --target_class 0 --epochs 5 --output_path models/resnet18_poison.pth
+```
+
+## 4. Run detection:
+
+```bash
+mithridatium detect --model models/resnet18_poison.pth --defense mmbd --data cifar10 --out reports/mmbd.json
+```

examples/sample_report.json

@@ -0,0 +1,12 @@
+{
+  "mithridatium_version": "0.1.0",
+  "timestamp_utc": "2025-01-01T00:00:00Z",
+  "model_path": "models/resnet18_poison.pth",
+  "defense": "mmbd",
+  "dataset": "cifar10",
+  "results": {
+    "suspected_backdoor": true,
+    "num_flagged": 500,
+    "top_eigenvalue": 42.3
+  }
+}