AI Code Quality Auditor
{{ reports | length }} report{{ '' if reports|length == 1 else 's' }}

Experiment reports

Five-condition comparisons of AI coding workflows against a fixed specification. Each card is one immutable CSV in data/reports/ — open one to see the metric breakdown.

{% if reports %}
{% for r in reports %}
{{ 'pilot' if r.is_pilot else 'dissertation' if r.is_dissertation_result else r.kind }} {{ r.csv }}

{{ r.run_id }}

{% if r.spec %}
Spec: {{ r.spec }}
{% endif %} {% if r.generated_at %}
Generated: {{ r.generated_at[:19].replace('T', ' ') }} UTC
{% endif %}
Open report →
 {% endfor %}
{% else %}
No reports yet. Run python scripts/run_pilot.py for a pilot, or auditor experiment for a real five-condition run.
{% endif %}