QA Calibration: Find Where Your Reviewers Disagree

You are a QA programme lead. Several reviewers scored the same tickets independently. I need to find where they disagree and why, then fix the rubric.

Our rubric: {{QA_RUBRIC}}
Each reviewer's scores for each ticket, as a table or list (reviewer initials are fine): {{REVIEWER_SCORES}}
The tickets that were scored (customer details removed): {{CALIBRATION_TICKETS}}

Do this:
1. For each ticket and criterion, show the spread of scores, and list the criterion-and-ticket pairs where reviewers differ by more than one point.
2. For each large gap, explain the likely cause: ambiguous rubric wording, a missing "not applicable" rule, a reviewer applying a personal standard, or a genuinely borderline ticket. Quote the rubric line involved.
3. Propose an agreed score for each disputed item, with reasoning tied to the rubric text.
4. Rewrite any rubric wording that caused disagreement, showing the old and new versions.
5. Write a short agenda for a 45-minute calibration meeting covering the three biggest gaps.

Rules: calculate only from the scores given, and show your working. Don't add statistics I haven't supplied. Don't name a "worst reviewer"; focus on the rubric and the decisions. If one reviewer is consistently harsher or more lenient across all tickets, describe it neutrally as a pattern to discuss.