Unverified50% confidenceFactExact time
Semantic Entropy was originally proposed by Kuhn et al. in 2023 at NeurIPS.
1
Sources
50%
Confidence
Long-term
Relevance
9/21/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe concept of information entropy originates from information theory, proposed by Claude Shannon in 1948 to measure uncertainty and disorder in information systems.66% similarUnverifiedSAC was proposed by Haarnoja et al. at UC Berkeley, introducing a maximum entropy framework that simultaneously maximizes the entropy of the policy while optimizing the expected cumulative reward65% similarVerifiedCross-entropy = entropy of the true distribution + KL divergence.64% similarUnverifiedIn 1951, Shannon published the paper "Prediction and Entropy of Printed English," estimating the entropy of English to be approximately 1.0–1.5 bits per character through experiments in which human subjects predicted the next character.61% similarVerifiedClaude Shannon published 'A Mathematical Theory of Communication' in 1948, proposing the concept of information entropy, whereby low-probability events carry higher information content, with the formula I(x) = -log₂P(x).61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/938054API
curl https://kongchang.com/api/v1/knowledge/claims/938054MCP
get_claim(id=938054)