diff --git a/.github/ISSUE_TEMPLATE/experiment.yml b/.github/ISSUE_TEMPLATE/experiment.yml
new file mode 100644
index 0000000..55d530d
--- /dev/null
+++ b/.github/ISSUE_TEMPLATE/experiment.yml
@@ -0,0 +1,124 @@
+# .github/ISSUE_TEMPLATE/experiment.yml
+name: Experiment
+description: Document a new ML experiment
+title: "[EXP] "
+labels: ["experiment"]
+assignees:
+  - ${{github.actor}}
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Use this template to document a new experiment for your thesis.
+        
+  - type: textarea
+    id: hypothesis
+    attributes:
+      label: Hypothesis
+      description: What is the hypothesis you're testing with this experiment?
+      placeholder: Using a deeper network with residual connections will improve accuracy on the imbalanced dataset without increasing overfitting
+    validations:
+      required: true
+      
+  - type: textarea
+    id: background
+    attributes:
+      label: Background & Motivation
+      description: Background context and why this experiment is important
+      placeholder: Previous experiments showed promising results but suffered from overfitting. Recent literature suggests that...
+    validations:
+      required: true
+      
+  - type: textarea
+    id: dataset
+    attributes:
+      label: Dataset
+      description: What data will you use for this experiment?
+      placeholder: |
+        - Dataset: MNIST with augmentation
+        - Preprocessing: Standardization + random rotation
+        - Train/Test Split: 80/20
+        - Validation strategy: 5-fold cross-validation
+    validations:
+      required: true
+      
+  - type: textarea
+    id: methodology
+    attributes:
+      label: Methodology
+      description: How will you conduct the experiment?
+      placeholder: |
+        1. Implement ResNet architecture with varying depths (18, 34, 50)
+        2. Train with early stopping (patience=10)
+        3. Compare against baseline CNN from experiment #23
+        4. Analyze learning curves and performance metrics
+    validations:
+      required: true
+      
+  - type: textarea
+    id: parameters
+    attributes:
+      label: Parameters & Hyperparameters
+      description: List the key parameters for this experiment
+      placeholder: |
+        - Learning rate: 0.001 with Adam optimizer
+        - Batch size: 64
+        - Epochs: Max 100 with early stopping
+        - Dropout rate: 0.3
+        - L2 regularization: 1e-4
+    validations:
+      required: true
+      
+  - type: textarea
+    id: metrics
+    attributes:
+      label: Evaluation Metrics
+      description: How will you evaluate the results?
+      placeholder: |
+        - Accuracy
+        - F1-score (macro-averaged)
+        - ROC-AUC
+        - Training vs. validation loss curves
+        - Inference time
+    validations:
+      required: true
+      
+  - type: input
+    id: notebook
+    attributes:
+      label: Notebook Location
+      description: Where will the experiment notebook be stored?
+      placeholder: notebooks/experiment_resnet_comparison.ipynb
+    validations:
+      required: false
+      
+  - type: textarea
+    id: dependencies
+    attributes:
+      label: Dependencies
+      description: What other issues or tasks does this experiment depend on?
+      placeholder: |
+        - Depends on issue #42 (Data preprocessing pipeline)
+        - Requires completion of issue #51 (Baseline model)
+    validations:
+      required: false
+      
+  - type: textarea
+    id: references
+    attributes:
+      label: References
+      description: Any papers, documentation or other materials relevant to this experiment
+      placeholder: |
+        - He et al. (2016). "Deep Residual Learning for Image Recognition"
+        - My previous experiment #23 (baseline CNN)
+    validations:
+      required: false
+      
+  - type: textarea
+    id: notes
+    attributes:
+      label: Additional Notes
+      description: Any other relevant information
+      placeholder: This experiment may require significant GPU resources. Expected runtime is ~3 hours on Tesla V100.
+    validations:
+      required: false