# Replication guide — UQO WP 35

# Environment

macOS or Linux, Python 3.12 (managed with uv), TeX Live with latexmk and the aer bibliography style, make.
Pinned dependencies in pyproject.toml (numpy 2.3.4, pandas 2.3.3, scipy 1.16.2, statsmodels 0.14.5, lifelines 0.30.0, scikit-learn 1.7.2, networkx 3.5, matplotlib 3.10.7, pyreadr 0.5.3, openpyxl 3.1.5, pyarrow 21.0.0, pytest 8.4.2, …).

bash

uv venv -p 3.12 .venv && uv pip install -p .venv/bin/python -e .

# One-command reproduction

bash

make all      # fetch → data → measure → econ → sim → figures → paper
make test     # 11 tests

Individual targets, in dependency order:

target	command	outputs	time (M5 Max laptop)
fetch	`python -m wp35.acquisition.fetch`	`data/raw/*`, `data/metadata/source_registry.json`	~1 min (65 MB)
data	`python -m wp35.harmonization.build_panels`	`data/processed/.parquet`, `results/diagnostics/`, coverage figures	~1 min
measure	`python -m wp35.measurement.build_indices`	`data/processed/_indices.parquet`, `results/empirical/measurement_`, `power_h2a_*`	~10 s
econ	`python -m wp35.econometrics.run_all` (= h1, h2_seshat, h2_modern)	`results/empirical/h1_`, `h2_`, `h4_`, `h5_`	~15 min (modern panel dominates)
sim	`python -m wp35.simulations.run_experiments && python -m wp35.simulations.analyze`	`results/simulated/` and `fig_sim_`	~1 min on 12 cores
figures	`python -m wp35.visualization.make_all`	`paper/tables/.tex`, `paper/figures/.pdf`	~10 s
paper	`python -m wp35.validation.build_bib && cd paper && latexmk -pdf main.tex`	`paper/references.bib`, `paper/main.pdf`	~1 min

# Determinism

Estimation seed 20261101 (cross-validation folds, power simulations); simulation seeds 0–7; IRT is deterministic (EM).
python -m wp35.validation.verify_bib re-queries Crossref and may differ if Crossref metadata changes; the verified list used for the paper is research/prior_art.csv + research/bib_overrides.csv.

# Provenance of every number

Each table fragment in paper/tables/ is written by src/wp35/visualization/make_all.py from a file in results/; each figure likewise. The execution log results/logs/execution_log.md records every command and every correction made during the study; results/logs/final_research_audit.md lists completed, failed and blocked tasks.

# Pre-registration

research/preregistration.md was frozen before any predictor–outcome association was computed; SHA-256 ecda8804e17f931789be8e274ba1ff989000de356700a85b638b043928182e3a (recorded in research/decisions.md, D-003). Verify with shasum -a 256 research/preregistration.md.

spb/wp35_uqo