Giorgio Gilestro
ab3dc10587
- paper/pnas -> paper/manuscript (venue-neutral)
- configs/layer1 -> configs/inheritance, src/knowledge -> src/inheritance
(imported as `inheritance`), make layer1 -> make inheritance; layer2 alias dropped
- inheritance and trained-network bundles named after the manuscript figure
they feed (fig2_grounding_sweep, figS3_rebaselining, ...), or descriptively
where they feed none; configs keep their `experiment:` value so parquet
hashes are unchanged, only output.dir moves
- figure scripts, SI figure sources, notebooks, REPRODUCING.md, README and the
SI Methods/tables updated; make clean no longer deletes tracked manifests;
reproduce.sh hashes the s{seed}/ layouts too
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Y64o8FKP7rCuXzC48pxpMm
100 lines
5.5 KiB
Makefile
100 lines
5.5 KiB
Makefile
# Repository automation (inheritance, neural and language-model tiers). The uv venv (built from the committed uv.lock) is the
|
|
# reproducibility source of truth; every target runs inside it via `uv run`.
|
|
|
|
.PHONY: env env-neural env-mnist env-llm env-notebooks test inheritance neural mnist llm \
|
|
llm-epistasis llm-society llm-society-calib llm-society-calib-b llm-society-v2-smoke \
|
|
figures paper-figures paper notebooks clean
|
|
|
|
env: ## build .venv from the committed lockfile
|
|
uv sync --extra dev
|
|
|
|
env-neural: ## add the torch stack for the trained-network tier (GPU)
|
|
uv sync --extra dev --extra neural
|
|
|
|
env-mnist: ## add torchvision for the real-MNIST confirmation tier
|
|
uv sync --extra dev --extra neural --extra mnist
|
|
|
|
test: ## correctness tests + scientific-validation tests (the spine of trust)
|
|
uv run pytest
|
|
|
|
inheritance: ## run every inheritance-model experiment (analytic; bitwise reproducible)
|
|
for c in configs/inheritance/*.yaml; do uv run python -m inheritance.experiment "$$c"; done
|
|
|
|
neural: ## run the synthetic trained-network experiments (excludes the MNIST/torchvision tiers)
|
|
for c in configs/neural/*.yaml; do case "$$c" in *mnist*|*speciation_real*) ;; \
|
|
*) uv run python -m neural.experiment "$$c" ;; esac; done
|
|
|
|
mnist: ## run the torchvision tiers: MNIST collapse + real-weight speciation (needs env-mnist)
|
|
uv run python -m neural.experiment configs/neural/fig2_mnist_collapse.yaml
|
|
uv run python -m neural.experiment configs/neural/speciation_real.yaml
|
|
uv run python -m neural.experiment configs/neural/speciation_real_cliff.yaml
|
|
uv run python -m neural.experiment configs/neural/speciation_real_emergent.yaml
|
|
MPLBACKEND=Agg uv run python figures/mnist_montage.py # the asset paper Fig. 2A embeds
|
|
|
|
env-llm: ## add the LLM stack for the Layer-2 prototype (GPU; transformers/peft)
|
|
uv sync --extra dev --extra neural --extra llm
|
|
|
|
llm: ## run the LLM prototypes: merge (fusion) + moe (union) + directed (offspring select)
|
|
uv run python -m llm.experiment configs/llm/merge.yaml
|
|
uv run python -m llm.experiment configs/llm/moe.yaml
|
|
uv run python -m llm.experiment configs/llm/directed.yaml
|
|
|
|
llm-speciation: ## LLM-tier speciation: conflict cliff (replace + de-confounded add) and duration null
|
|
uv run python -m llm.experiment configs/llm/speciation.yaml
|
|
uv run python -m llm.experiment configs/llm/speciation_add.yaml
|
|
|
|
llm-epistasis: ## the controlled predictive test (feeds paper Fig. 3C-D) + its robust statistics
|
|
uv run python -m llm.experiment configs/llm/epistasis.yaml
|
|
uv run python -m llm.experiment configs/llm/epistasis_compat.yaml
|
|
uv run python figures/stats_llm_epistasis.py
|
|
|
|
llm-society: ## the composed society at LLM scale (C3): pilot; the campaign runs on HPC
|
|
uv run python -m llm.experiment configs/llm/society.yaml
|
|
|
|
llm-society-calib: ## v2 society calibration gates (prereg §4): stage A (families), then B (C2/C3/C5)
|
|
uv run python -m llm.experiment configs/llm/society_v2_calib_a.yaml
|
|
@echo "Review the C1 table, fix the 12 families in society_v2_calib_b.yaml, then: make llm-society-calib-b"
|
|
|
|
llm-society-calib-b: ## v2 calibration stage B over the chosen 12 families: transmission, cross, consensus
|
|
uv run python -m llm.experiment configs/llm/society_v2_calib_b.yaml
|
|
mkdir -p configs/llm/_gen
|
|
uv run python - <<'EOF'
|
|
import yaml; c = yaml.safe_load(open("configs/llm/society_v2_calib_b.yaml"))
|
|
for st in ("cross", "consensus"):
|
|
c["stage"] = st; c["output"] = {"dir": f"results/llm_society_v2_calib_b_{st}"}
|
|
yaml.safe_dump(c, open(f"configs/llm/_gen/calib_{st}.yaml", "w"), sort_keys=False)
|
|
EOF
|
|
uv run python -m llm.experiment configs/llm/_gen/calib_cross.yaml
|
|
uv run python -m llm.experiment configs/llm/_gen/calib_consensus.yaml
|
|
|
|
llm-society-v2-smoke: ## v2 society loop smoke (4 families, 4 agents, 2 generations, all arms)
|
|
uv run python -m llm.experiment configs/llm/society_v2_smoke.yaml
|
|
uv run python figures/plot_llm_society.py results/llm_society_v2_smoke
|
|
|
|
llm-seeds: ## multi-seed firm-up (heavy): merge x5, moe-hard x3, directed-hard x3
|
|
uv run python -m llm.experiment configs/llm/merge_seeds.yaml
|
|
uv run python -m llm.experiment configs/llm/moe_hard_seeds.yaml
|
|
uv run python -m llm.experiment configs/llm/directed_hard_seeds.yaml
|
|
|
|
figures: ## regenerate per-experiment figures from committed results (pure; no re-simulation)
|
|
for p in figures/plot_*.py; do MPLBACKEND=Agg uv run python "$$p"; done
|
|
|
|
paper-figures: ## regenerate the manuscript figures (Fig. 1-5) and rebuild the PDF bodies
|
|
MPLBACKEND=Agg uv run python paper/manuscript/make_figs.py
|
|
uv run python paper/manuscript/build.py
|
|
uv run python paper/manuscript/build.py si
|
|
|
|
paper: paper-figures ## figures + compile both PDFs (needs tectonic)
|
|
cd paper/manuscript && tectonic main.tex && tectonic si.tex
|
|
uv run python paper/manuscript/build_lay_legends.py && cd paper/manuscript && tectonic figure_legends_for_students.tex
|
|
|
|
env-notebooks: ## add Jupyter for the walkthrough notebooks
|
|
uv sync --extra dev --extra notebooks
|
|
|
|
notebooks: ## execute every notebook end-to-end (a reproduction check in itself)
|
|
for nb in notebooks/*.ipynb; do uv run jupyter nbconvert --to notebook --execute \
|
|
--inplace --ExecutePreprocessor.timeout=1800 "$$nb"; done
|
|
|
|
clean: ## remove caches and regenerable parquets (keeps committed manifests and figures)
|
|
rm -rf .pytest_cache **/__pycache__
|
|
find results -name 'results.parquet' -delete 2>/dev/null || true # tracked manifests/figures stay
|