Development

A model disproves a statistical procedure cited 130,000 times

development2026-07-15

Claim

Wharton's Edgar Dobriban used GPT-5.6 to prove that the Benjamini-Hochberg procedure, cited 130,000 times, does not actually control the false discovery rate for correlated tests, a problem its predecessor could not crack in 20 hours and that the new model solved in 90 minutes.

Reported metric: 20 hours to 90 minutes

Reporting date: 2026-07-15 (not necessarily the event date)

Sources

Attribution and reporting linked by this record; links do not imply independent verification.

Welcome to July 15, 2026 (theinnermostloop.substack.com)

Knowledge graphopen in browser →

Reported in

Welcome to July 15, 2026

Actor

Evidence for

Supersedes

A fifty-year-old conjecture falls to 64 subagents in under an hour

Referenced by

Cite or correct this record

Citation formatCitation text

A model disproves a statistical procedure cited 130,000 times
Innermost Loop KB — secondary record
Reporting date: 2026-07-15
KB permalink: https://nicholsn.github.io/innermost-loop-kb/developments/2026-07-15-a-model-corrects-a-textbook-cited-130000-times
Claim: Wharton's Edgar Dobriban used GPT-5.6 to prove that the Benjamini-Hochberg procedure, cited 130,000 times, does not actually control the false discovery rate for correlated tests, a problem its predecessor could not crack in 20 hours and that the new model solved in 90 minutes.
Attributed sources:
- Welcome to July 15, 2026 — https://theinnermostloop.substack.com/p/welcome-to-july-15-2026
This citation does not imply independent verification of linked-source claims.

Suggest a correction — opens a GitHub draft for you to review and submit.