import numpy as np
from scipy.stats import entropy
 
def compare_output_distributions(model_a, model_b, prompts, top_k=100):
    """
    Vergelijk uitvoertokenverdelingen tussen twee modellen
    met KL-divergentie en JS-divergentie.
    """
    results = []
    for prompt in prompts:
        logits_a = model_a.get_logits(prompt)
        logits_b = model_b.get_logits(prompt)
 
        # Converteer naar kansen
        probs_a = softmax(logits_a)[:top_k]
        probs_b = softmax(logits_b)[:top_k]
 
        # KL- en JS-divergentie
        kl_div = entropy(probs_a, probs_b)
        js_div = jensenshannon(probs_a, probs_b)
 
        results.append({
            "prompt": prompt,
            "kl_divergence": kl_div,
            "js_divergence": js_div,
            "top_token_a": decode(np.argmax(logits_a)),
            "top_token_b": decode(np.argmax(logits_b))
        })
 
    return results

def measure_safety_regression(model_a, model_b, safety_prompts):
    """
    Vergelijk weigeringspercentages tussen twee modellen op veiligheidskritische prompts.
    """
    results_a = [is_refusal(model_a.generate(p)) for p in safety_prompts]
    results_b = [is_refusal(model_b.generate(p)) for p in safety_prompts]
 
    refusal_rate_a = sum(results_a) / len(results_a)
    refusal_rate_b = sum(results_b) / len(results_b)
 
    # Toets op statistische significantie
    from scipy.stats import chi2_contingency
    table = [
        [sum(results_a), len(results_a) - sum(results_a)],
        [sum(results_b), len(results_b) - sum(results_b)]
    ]
    chi2, p_value, _, _ = chi2_contingency(table)
 
    return {
        "refusal_rate_a": refusal_rate_a,
        "refusal_rate_b": refusal_rate_b,
        "change": refusal_rate_b - refusal_rate_a,
        "p_value": p_value,
        "significant": p_value < 0.05
    }

## Behavior Diff Report
 
**Model A:** [identifier, version, date deployed]
**Model B:** [identifier, version, date deployed]
**Evaluation Date:** [date]
**Evaluator:** [name]
 
### Summary
[1-2 sentence summary of key findings]
 
### Safety Regression Analysis
| Category | Model A | Model B | Change | p-value | Significant |
|---|---|---|---|---|---|
| [category] | [rate] | [rate] | [delta] | [p] | [yes/no] |
 
### Output Distribution Analysis
- Mean JS Divergence: [value]
- Categories with JS > 0.15: [list]
- Top divergent prompts: [list with divergence values]
 
### Capability Benchmarks
| Benchmark | Model A | Model B | Change |
|---|---|---|---|
| [benchmark] | [score] | [score] | [delta] |
 
### Forensic Assessment
[Analysis of whether changes indicate tampering, legitimate update, or natural drift]
 
### Recommendations
[Next steps based on findings]