false-negative

A false-negative is a diagnostic or classification error in which a test or signal wrongly indicates the absence of a condition, property, or threat when it is actually present. The test output is negative (indicating absence) while the ground truth is positive (presence). False-negatives arise in any system that makes binary or categorical decisions based on imperfect signals — medical screening tests, machine learning classifiers, security scanners, and statistical hypothesis tests. They are quantified as the false-negative rate (β in hypothesis testing, related to statistical power = 1−β) and represent the risk of missing what is actually there. A false-negative in medical diagnosis or security screening carries real-world consequences proportional to the condition's severity. [formal: falsum negativum | substrate: behavior | horizon: a moment | explicit: yes | epoch: 0.01]