Unverified50% confidenceFactExact time
The experiments designed control groups for persistence and dominance results, keeping the accuracy of random guessing at around 0.27.
1
Sources
50%
Confidence
Long-term
Relevance
11/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedRandom accuracy is about 0.33 for three-class classification and about 0.25 for four-class classification; only the magnitude of improvement relative to the random level can reflect whether the model has truly learned anything.77% similarUnverifiedOpportunity-normalized accuracy is computed as (model accuracy − random-guess accuracy) / (1 − random-guess accuracy).77% similarUnverifiedResearchers have proposed having models explicitly output probabilities, or estimating reliability by sampling multiple times and measuring answer consistency (self-consistency).75% similarUnverifiedThe researchers drew 60 decisions from the late stage of each model's matches and, when the records were sufficient, compared the changes in probability distributions under three conditions: the original question, a repeated question, and removing the records.73% similarUnverifiedFor a randomly ranking classifier, the expected Average Precision is approximately equal to the positive-class prevalence; at a prevalence of 1%, the random baseline AP is about 0.01.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1138975API
curl https://kongchang.com/api/v1/knowledge/claims/1138975MCP
get_claim(id=1138975)