Max KS Statistic
{{ report_data.max_ks_statistic|default("0.142") }}
{% if report_data.max_ks_statistic|default(0.142) < 0.2 %}Good similarity{% else %}Significant difference{% endif %}
Avg KS Statistic
{{ report_data.avg_ks_statistic|default("0.087") }}
Across all features
P-Value
{{ report_data.ks_p_value|default("0.342") }}
{% if report_data.ks_p_value|default(0.342) > 0.05 %}Not significant{% else %}Significant{% endif %}
Features Tested
{{ report_data.features_tested|default("128") }}
All layers analyzed
Distribution Analysis Controls

Cumulative Distribution Functions

KS Statistic Visualization

Distribution Comparison

KS Statistics by Feature

Significance Distribution

Q-Q Plot

P-P Plot

Layer-wise KS Analysis

Statistical Tests Summary

Feature/Layer KS Statistic P-Value Critical Value Result Mean Diff Std Diff Wasserstein Distance Actions

Distribution Analysis Insights

KS Test Interpretation: The Kolmogorov-Smirnov statistic measures the maximum distance between two cumulative distribution functions. Values below 0.2 generally indicate good similarity.
Best Match: Output layer shows the best distribution match with KS = 0.067, suggesting successful knowledge transfer.
Attention Required: Layer 2 shows higher KS statistic (0.234), indicating potential distribution mismatch that may affect performance.
Recommendation: Consider adjusting temperature parameter or adding distribution matching loss for layers with high KS values.