Calibration Curve
An evaluation chart with predicted probability on the horizontal axis and observed frequency on the vertical axis, ideally forming a diagonal line; it is used to measure the calibration of a model's probability outputs.
Timeline (last 90 days)
Common metrics for measuring a model's ability to express uncertainty include the calibration curve and ECE (Expected Calibration Error).
The core mechanism of Calibration Court is to write each AI prediction into a hash-chain ledger before the outcome is revealed, and to score it using the Brier score, log loss, and calibration curves.
The risk-coverage curve plots the proportion of cases automatically handled by the model on the x-axis and the error risk at that coverage level on the y-axis; a smaller area under the curve indicates more reliable judgments in high-confidence intervals.
All Facts (3)
Common metrics for measuring a model's ability to express uncertainty include the calibration curve and ECE (Expected Calibration Error).
50%UnverifiedThe core mechanism of Calibration Court is to write each AI prediction into a hash-chain ledger before the outcome is revealed, and to score it using the Brier score, log loss, and calibration curves.
50%UnverifiedThe risk-coverage curve plots the proportion of cases automatically handled by the model on the x-axis and the error risk at that coverage level on the y-axis; a smaller area under the curve indicates more reliable judgments in high-confidence intervals.
50%