Unverified50% confidenceFactExact time
Surprisal is a fundamental concept in information theory, referring to how unexpected a word or string is in a given context, commonly measured by negative log probability: the lower the probability, the higher the surprisal.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedA common nonconformity score definition in classification tasks is 1 minus the probability value corresponding to the true class in the softmax output, where a higher score indicates a more anomalous sample.68% similarUnverifiedLikelihood is essentially a statistic that only reflects relative rarity under a probability distribution, and it cannot distinguish unique expressions written by humans after deliberate thought from meaningless strings randomly copied by machines.68% similarUnverifiedThe illusion of fluency refers to the tendency of learners to overestimate their degree of mastery when information is presented in a clear and organized manner, because the metacognitive monitoring system misinterprets processing fluency as a signal of having already learned the material.67% similarUnverifiedThe base rate fallacy points out that when targets are extremely rare, even a highly accurate system may produce a large proportion of false alarms among its alerts.66% similarUnverifiedThe frequentist school treats probability as the long-term frequency of event occurrence, while the Bayesian school understands probability as a subjective measure of belief about uncertainty.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1038108API
curl https://kongchang.com/api/v1/knowledge/claims/1038108MCP
get_claim(id=1038108)