White by Default? The viral posts were right. We scraped 5.5 million criminal records and 1.5 million mugshots from 39…

11 tweets1 min read♥ 26.8Koriginal

Summary

Researchers analyzed 5.5 million criminal records and 1.5 million mugshots from 39 states, finding that approximately 29% of Hispanics are systematically misclassified as White in official Department of Corrections databases, even when Hispanic classification is explicitly available. Using machine learning trained on facial recognition and name demographics, they achieved 92.76% accuracy in racial classification and confirmed the misclassification bias is real, not anecdotal—correcting for it increases reported Hispanic criminal rates by 20-31% while decreasing White rates by 4-6%.

Summarized by ThreadOut AI from the full thread. May miss nuance — read the thread below.

#1
White by Default? The viral posts were right. We scraped 5.5 million criminal records and 1.5 million mugshots from 39 states. 29% of Hispanics are being misclassified as White in official Department of Corrections databases. Even when Hispanic is explicitly classified 🧵
#2
Everyone's seen these collages claiming non-whites get classified as White in criminal databases. The problem? Anecdotal. Cherry-picked. No way to verify. We had 1.5 million mugshots, names, and official racial classifications. Time to test it systematically:
#3
We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name demographics • First and last name racial statistics 92.76% accuracy distinguishing Black, White and Hispanic.
#4
The key insight: A sufficiently accurate linear model trained on biased data learns the TRUE signal, not the bias. Systematic deviations between predictions and official labels indicate mislabeling by authorities, not model error. Here's what we found....
#5
29% of predicted Hispanics were officially classified as White. Even at 95-100% model confidence, 22.4% of predicted Hispanics were still assigned White. Median confidence for these cases? 91.7%.
#6
Visual inspection confirmed it. These are people classified as "White" in official records. Look at those names!
#7
Furthermore, PC mapping revealed that many "Whites" were in Hispanic variable zones, but not the other way around. Measuring the euclidean distance from the centroids, Whites were just as distinguishable from Hispanics as Blacks were from Whites.
#8
To further confirm the validity of our method through visual inspection, we contrasted low and high confidence classifications. High confidence misclassifications almost always were the predicted race instead of the assigned race.
#9
We corrected for misclassification: Hispanic criminal record rates increase 20-31% White rates decrease 4-6% Black rates decrease 1% The lowerbound being only high confidence reassignments (>90% confidence), the upperbound assuming all predicted = actual race.
#10
State-level analysis showed massive variation. Florida: 60%+ of Hispanics misclassified as White (Cubans tend to self-id as White?) But no correlation with political ideology (r = 0.21, p = 0.472).
#11
For the analysis, FULL REPLICATION, code, data, github check out my blog post on it: White by Default: Systematic Bias in U.S. Criminal Racial Assignment uncorrelated.xyz/p/white-by-def…