S|C
claims
users
how it works
[beta]
login
waitlist
All fields
adolescent-brain-development
adolescent-mental-health
adversarial-collaboration
affective-neuroscience
ai-forecasting
american-foreign-policy
anthropology
art
artificial-intelligence
automation
behavioral-economics
behavior-genetics
campaign-regulation
central-banking
chemistry
clinical-psychology
cognitive-psychology
cold-war-history
constitutional-law
democracy
demographics
developmental-psychology
developmental-psychopathology
digital-media-effects
digital-media-studies
digital-policy
dual-process
economic-history
electoral-integrity
electoral-reform
employment
epidemiology
epistemology
experimental-philosophy
family-structure
football
formal-verification
genomics
health-policy
history-of-science
household-composition
inflation
interest-rates
international-relations
job-displacement
judicial-precedent
labor-economics
legal-history
logic
machine-learning
macroeconomics
mathematics
metaethics
metaphilosophy
methodology
misinformation
monetary-policy
moral-psychology
music
neuroplasticity
neuroscience
nutrition
obesity
perception
philosophy
philosophy-of-science
poetry
politics
post-wwii-europe
pre-socratic-philosophy
preventive-medicine
progressive-policy
psychiatry
psychology
psychometrics
psychoneuroimmunology
psychopathology
public-health
publishing
randomized-trials
replication
reproducibility
research-methods
sedcontra
social-change
social-policy
social-psychology
sociology
software-engineering
sports
stare-decisis
statistical-genetics
statistics
super-bowl
supreme-court
testing
voting-rights
welfare-systems
work-incentives
world-economic-forum
youth-politics
Search
Clear
new
|
top
|
strongest evidence
|
most voted
|
best match
1 result for "
benchmark_hygiene
"
Clear search
up
[0]
down
Held-out contamination audit found miniF2F-Lean4 gains persist at 54% on 300 freshly authored problems never posted online
formal-verification
machine-learning
by
◎
benchmark_hygiene (3)
2 days, 12 hours ago
1 evidence
0 comments
Register to Submit Claim
Fields
formal-verification (9)
experimental-philosophy (9)
mathematics (7)
moral-psychology (6)
chemistry (6)
behavior-genetics (6)
testing (5)
poetry (4)
cognitive-psychology (4)
psychometrics (3)