Probability calibration is the systematic adjustment of predicted probabilities so they align with observed frequencies. Parameters: a set of raw probabilistic predictions, corresponding observed outcomes, and a calibration function (isotonic regression, Platt scaling, or histogram binning) that maps uncalibrated outputs to calibrated probabilities that satisfy the law of large numbers. Persistence mechanism: institutionalized in forecasting communities, machine learning pipelines, and decision-analytic practice where miscalibrated probabilities produce systematically suboptimal decisions. [formal: calibratio | substrate: behavior | horizon: hours | explicit: yes | epoch: 0.95]
Accepted ontology entry
probability-calibration
Probability calibration is the systematic adjustment of predicted probabilities so they align with observed frequencies. Parameters: a set of raw probabilistic predictions, corresponding observed outcomes, and a calibration function (isoto…
Definition
Why it is in scope
The systematic adjustment of probabilistic predictions so they match observed frequencies — a practice used in forecasting, machine learning, and decision analysis to make probabilistic judgments reliable
Names and aliases
- probability-calibrationen · CANONICAL
Relations from this entry
- cmroy9bjn05vbd1nla5rlzxdnDEPENDS_ON →
Probability-calibration is a specific type of calibration practice applied to probabilistic predictions. Remove calibration as a general concept and probability-calibration has no framework to extend. The specific practice depends on the general concept it instantiates. Removal test passes.
- cmroy9bjn05vbd1nla5rlzxdnDERIVED_FROM →
Probability-calibration is a newer, specialized practice derived from the older, more general practice of calibration. Which-came-first test: calibration (epoch 0.19) predates probability-calibration (epoch 0.95). The specific practice extends the general framework.
Relations to this entry
No accepted relations in this direction.
Record identity
- Created
- Aug 5, 2026, 2:37 PM UTC
- Content hash
- e5ff25bf41bd224a737e68e43a619d73081df22a5904bfb451b1fad19420779f