Score breakdown

Unsolved Problems in ML Safety

paper-0132 · paper · 2021

Dan Hendrycks et al.

The mainstream-ML framing of robustness, monitoring, alignment, systemic safety.

Academic, score -0.2069

MetricStatusValueNorm.WeightContributionSourceConfidenceProvenance
citation_countpresent88.00.0003920.50.000196OpenAlexhighlink
library_holdingsmissingrecorded as missing, penalized by rule, never imputed−0.1recorded as missing; penalized by rule, never imputed
readership_persistencepresent6.00.3571430.050.017857OpenAlexmediumlink
syllabus_adoptionsmissingrecorded as missing, penalized by rule, never imputed−0.125recorded as missing; penalized by rule, never imputed

Broad Influence, score -0.0571

MetricStatusValueNorm.WeightContributionSourceConfidenceProvenance
citation_countpresent88.00.0003920.27.8e-05OpenAlexhighlink
library_holdingsmissingrecorded as missing, penalized by rule, never imputed−0.125recorded as missing; penalized by rule, never imputed
readership_persistencepresent6.00.3571430.40.142857OpenAlexmediumlink
syllabus_adoptionsmissingrecorded as missing, penalized by rule, never imputed−0.075recorded as missing; penalized by rule, never imputed

Governance Practitioner, score -0.2892

MetricStatusValueNorm.WeightContributionSourceConfidenceProvenance
citation_countpresent88.00.0003920.259.8e-05OpenAlexhighlink
library_holdingsmissingrecorded as missing, penalized by rule, never imputed−0.15recorded as missing; penalized by rule, never imputed
readership_persistencepresent6.00.3571430.10.035714OpenAlexmediumlink
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.