Unverified50% confidenceDecision RuleExact time
In time-series direction forecasting, the correct baseline should be the majority class proportion rather than 50%, because if 51% of movements are upward, 'always guess up' achieves 51% accuracy.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedPapers that were randomly boosted with initial selections saw their probability of subsequent selection increase by 45.55 percentage points (95% confidence interval: 41.20 to 49.90).70% similarUnverifiedUnder the condition of n=100 with an even split of positive and negative samples, the 95% confidence interval for 55% accuracy is roughly 45%–65%, which covers the 50% baseline, so the 5 percentage point gap may be random fluctuation.70% similarUnverified研究表明人类评估者在判断LLM输出的事实准确性时，正确率往往只有50%-70%67% similarUnverifiedIncorporating calibration numbers into performance reviews turns them into strategic statements, where everyone learns to report "fifty-fifty"—a claim that is never wrong—thereby corrupting the data.67% similarUnverifiedWhen evaluating a binary classification model, the majority-class baseline when positive and negative samples are evenly split means a model that always predicts 'normal' can also achieve 50% accuracy.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1016941API
curl https://kongchang.com/api/v1/knowledge/claims/1016941MCP
get_claim(id=1016941)