Score breakdown

Risks from Learned Optimization in Advanced Machine Learning Systems

paper-0112 · paper · 2019

Evan Hubinger et al.

Mesa-optimization and deceptive alignment; core inner-alignment concepts.

Academic, score -0.2035

MetricStatusValueNorm.WeightContributionSourceConfidenceProvenance
citation_countpresent25.00.0001080.55.4e-05OpenAlexhighlink
library_holdingsmissingrecorded as missing, penalized by rule, never imputed−0.1recorded as missing; penalized by rule, never imputed
readership_persistencepresent7.00.4285710.050.021429OpenAlexmediumlink
syllabus_adoptionsmissingrecorded as missing, penalized by rule, never imputed−0.125recorded as missing; penalized by rule, never imputed

Broad Influence, score -0.0285

MetricStatusValueNorm.WeightContributionSourceConfidenceProvenance
citation_countpresent25.00.0001080.22.2e-05OpenAlexhighlink
library_holdingsmissingrecorded as missing, penalized by rule, never imputed−0.125recorded as missing; penalized by rule, never imputed
readership_persistencepresent7.00.4285710.40.171429OpenAlexmediumlink
syllabus_adoptionsmissingrecorded as missing, penalized by rule, never imputed−0.075recorded as missing; penalized by rule, never imputed

Governance Practitioner, score -0.2821

MetricStatusValueNorm.WeightContributionSourceConfidenceProvenance
citation_countpresent25.00.0001080.252.7e-05OpenAlexhighlink
library_holdingsmissingrecorded as missing, penalized by rule, never imputed−0.15recorded as missing; penalized by rule, never imputed
readership_persistencepresent7.00.4285710.10.042857OpenAlexmediumlink
syllabus_adoptionsmissingrecorded as missing, penalized by rule, never imputed−0.175recorded as missing; penalized by rule, never imputed

A rank is not a verdict on intrinsic worth. It is a transparent output of declared evidence, weights, and missing-data rules at a specific release date.

Disagree with this rank or a number? Challenge it with your evidence. Every challenge gets a public identifier and a published resolution.