Fewer than 10% of preregistered studies include multiple-hypothesis corrections
RexDouglass · x · 2026-09-26
An empirical audit of preregistration in academic articles finds preregistrations generally strong on basics (hypotheses, outcomes, models, sample size) but thin on control variables, data cleaning, and robustness checks; multiple-hypothesis corrections appeared in fewer than 10% of cases.
Related event: Study Finds Most Preregistered Studies Deviate From Their Plans(2 posts)→
More from Research
- Biopharma Bench: agents complete only 8 of 71 real biopharma tasks, GPT-6 Astra leads — AllThingsApx · 2026-09-26
- Matryoshka Attribution finds neural network circuits via gradient descent, tops interpretability benchmark by 2.9x — stanfordnlp · 2026-09-26
- Anthropic's science blog shows Claude pulling off 'Nine Loops' particle physics calculations — rohanpaul_ai · 2026-09-26
- UniReps workshop invites NeurIPS rejects, deadline Oct 4 for Paris event — Pseudomanifold · 2026-09-26
- Creative Destruction Lab opens 15-year tech startup panel dataset to researchers — avicgoldfarb · 2026-09-26
- Building the next OCR benchmark: skalskip92 seeks hard samples from handwriting to technical drawings — BLUECOW009 · 2026-09-26