datasets for tissue and tool named entity recognition, annotation files for biological workflow extraction, and disambiguation files
How fast can a coding agent p-hack? Measured: on known-zero data, realistic searches manufacture p<.05 on 33-97% of null draws, in ~1 second each. Instrumented specification-search engine + 11 Claude Code skills for econometric designs; every search leaves a verifiable ledger and an honest p-value. Research and teaching use only.
Blazing-fast multiverse data exploration 💨 — based on our Nature Energy 2025 publication
Topological Hyperparameter Evaluation Mapping Algorithm (Nature Energy 2025).
R and Stata package for reproducibility, replicability and robustness analysis using multiverse and specification-curve results.
Multiverse analysis of SNR and phase synchronization as predictors of sensorimotor BCI performance
Simple multiverse analysis simulations, visualizations and inference techniques.
Circuit-level interpretability evidence does not survive defensible analytic variation. Pre-registered multiverse over 15,840 specifications; the derived EU AI Act Annex IV claim flips across 73.2% of specification pairs. arXiv:2608.13754
How far does a conclusion about educational attainment move across modelling choices that are all individually defensible? A 48-specification sensitivity study of PISA 2022 UK mathematics outcomes.
Should they have passed? Evaluating shooting decisions from StatsBomb 360 freeze frames, and testing which analytical choices actually change the answer.
Garden of forking paths simulator. Hunt for p<0.05 in a null dataset, then see the whole multiverse of 1920 specifications
This essay presents a clear and intuitive overview of the full Siamese Universe framework. It explains how a shared quantum vacuum, a minimal phase desynchronization, and CPT symmetry together generate matter, structure, and cosmic complexity. A causal narrative linking physical principles and observable signatures.
Causally disciplined multiverse analysis in R: candidate DAGs, valid-specification multiverses, within/between-DAG variance decomposition
A preregistered, algorithm-agnostic matched-null test for cluster-count claims ("N types"), tried out on personality.
221 dengue outbreaks × 144 analysis choices = 33,152 model fits. Three-quarters of the variation in whether climate forcing is endorsed is analytical, not geographic — and most of that is an outbreak × analysis interaction no convention can remove.
Repo for the code and data used to perform our mini-multiverse analysis
To associate your repository with the multiverse-analysis topic, visit your repo's landing page and select "manage topics."