giorgio/MachineSex
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Phase 4: PNAS research-article draft (main.md + composed figures + SI skeleton)

Browse source 
paper/pnas/main.md — the manuscript restructured as a research article
(~5.6k words main text): significance statement, abstract, introduction
(diagnosis conceded; the management thesis; the interpretation/
explanation/prediction ladder with the prediction rung stated as a
bounded controlled test), the minimal model with its exactness boundary
(learning kernel cited against ourselves), Table 1 dictionary with
per-row support levels, a five-step results ladder (grounding floor;
conservation law + operator boundaries + Fisher-Muller + directed sex +
mating structure; the jointly-necessary society; speciation across three
tiers with the emergent null; the controlled predictive test at
second-review calibration), discussion (design rules, borrowed-vs-ours
ledger, limits with the reviewer's generalisation-before-scale ordering,
what biology gets back), brief methods, 30 references.

build.py composes 6 figures by stacking committed vector PDFs (bespoke
unified re-plots deferred to submission polish); builds clean under
tectonic (15 pp incl. 6 full-page figures). si.md: SI skeleton
(propositions, claims ledger, per-tier methods, statistics, figure
list). Manifesto sections of v6 (institutions, timescales, re-minting)
compressed into Discussion per the plan; v6 remains the long-form
perspective document.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BkRLcc18rwT2Lysu6PbG7v
This commit is contained in:
Giorgio Gilestro 2026-09-06 18:24:58 +01:00
parent a40ace1821
commit bf4b1c077c
21 changed files with 928 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

192
paper/pnas/build.py Normal file
View file

@ -0,0 +1,192 @@
r"""Build the PNAS-draft PDF from main.md (Markdown stays the source of truth).
Adapted from paper/arxiv/md2tex.py (same Markdown subset + pipe tables), with one addition: standalone
`*(FIG:name)*` markers compose multi-panel figures by stacking existing per-experiment vector PDFs
(LaTeX-level consolidation; bespoke unified figures are a submission-time polish, tracked in the work
order). Captions define the panel letters positionally (A = top, ...) because the sub-figures carry
their own internal panel labels.
Usage: python paper/pnas/build.py && (cd paper/pnas && tectonic main.tex)
"""
from __future__ import annotations
import re
import shutil
from pathlib import Path
ROOT = Path(__file__).resolve().parents[2]
HERE = Path(__file__).resolve().parent
SRC = HERE / "main.md"
OUT = HERE / "body.tex"
# figure name -> (list of source PDFs (stacked top->bottom), caption)
FIGURES: dict[str, tuple[list[str], str]] = {
"fig1": (["results/E2/E2.pdf", "results/mnist_collapse/mnist_montage.pdf"],
"Collapse is drift; grounding is immigration. (A, top) The grounding phase response in the "
"minimal model: a critical real-data fraction $g^*\\!\\approx\\!0.05$ retains most diversity "
"indefinitely, while tail survival obeys the per-item floor $m\\,p \\gtrsim 1$. (B, bottom) "
"The same signs on real images: a convolutional VAE retrained each generation on its own "
"output collapses to a single blurred mode (rows: generations), while $\\sim$10\\% grounding "
"holds all thirty class$\\times$style modes."),
"fig2": (["results/E4/E4.pdf", "results/E8/E8.pdf"],
"Recombination: the conservation law and the Fisher--Muller effect. (A, top) Refitting a child "
"to the mean of its parents' output distributions conserves rare-item mass at single-parent "
"level regardless of parent count (blending inheritance); a strongest-source (union) operator "
"realises the multi-parent gain. (B, bottom) Multi-locus recombination of decorrelated "
"specialists assembles a genotype fitter than any parent, climbing to the optimum as parents "
"are added, while the best single parent and the blended average plateau below."),
"fig3": (["results/E9/E9.pdf", "results/E10/E10.pdf", "results/E14/E14.pdf"],
"Rugged (epistatic) landscapes: risk, remedy, and structure. (A, top) Outbreeding depression: "
"blind recombination of specialists drops offspring below their parents, worsening with "
"ruggedness; the optimal recombination rate shrinks as skills entangle. (B, middle) Directed "
"sex --- unbounded parents, chosen mates, verifier-screened offspring --- converts the "
"catastrophe into a reliable gain at every ruggedness. (C, bottom) Mating structure: wide "
"(promiscuous) mixing maximises the population mean but monotonically destroys diversity; the "
"champion-optimal mate-pool breadth narrows as the landscape roughens."),
"fig4": (["results/E11/E11.pdf"],
"The society: grounding, sex, and diversity are jointly necessary. A finite agent population "
"on a rugged NK landscape under a grounded selection score. Four-arm ablation: the full system "
"climbs to near the global optimum; removing grounding collapses the population onto a "
"confident, unfit consensus (self-consumption); removing recombination strands it on local "
"optima; removing diversity converges it prematurely. Each ablation fails differently."),
"fig5": (["results/E12/E12.pdf", "results/speciation_real/speciation_real.pdf",
"results/llm_speciation/llm_speciation.pdf"],
"Model speciation across three tiers. (A, top) Analytic: hybrid fitness traces compatible "
"$\\rightarrow$ outbreeding depression $\\rightarrow$ inviability; the cliff arrives earlier "
"the denser the incompatibilities; incompatibility count snowballs with divergence. (B, "
"middle) Trained MLPs: the merge barrier decomposed under the complete unit symmetry group --- "
"same-task/different-init barriers are coordinate artefacts (removed by alignment); "
"conflicting-task barriers survive in full, with hybrid fitness falling 0.97 $\\rightarrow$ "
"0.03; divergence without conflict produced no isolation, the merge instead rescuing the "
"forgetting specialists. (C, bottom) Language models: conflicting conventions produce "
"function-specific hybrid breakdown; over-training disjoint specialists produces none --- at "
"every tier tested, isolation had to be provoked by functional conflict."),
"fig6": (["results/llm_merge_seeds/llm_seeds.pdf", "results/llm_moe_hard_hpc/llm_moe.pdf",
"results/llm_epistasis/llm_epistasis.pdf"],
"The language-model tier. (A, top) Seed-replicated recombination claims (fixed test sets, "
"training seed varied, 95\\% CI): merges beat every specialist; union-preserving routing and "
"directed offspring selection beat the blend in every seed on headroom tasks, including one "
"catastrophic blend failure they avoided. (B, middle) The headroom rule at 7B on hard "
"(unsaturated) tasks: the weight-average dilutes a fragile specialist below the best single "
"parent; routing preserves it. (C, bottom) The controlled predictive test: across a task grid "
"with conflict, compatible-overlap, and duration axes decorrelated by construction, pre-merge "
"functional disagreement predicts merge penalty (held-out $\\rho \\approx 0.4$) while "
"weight-geometry baselines show no detectable association; paired predictor differences are "
"not individually significant."),
}
UNICODE = {"—": "---", "–": "--", "→": r"\(\rightarrow\)", "≈": r"\(\approx\)", "≥": r"\(\geq\)",
"≳": r"\(\gtrsim\)", "×": r"\(\times\)", "·": r"\(\cdot\)", "μ": r"\(\mu\)",
"ρ": r"\(\rho\)", "≤": r"\(\leq\)", "≪": r"\(\ll\)", "∝": r"\(\propto\)"}
SPECIALS = {"&": r"\&", "%": r"\%", "#": r"\#", "_": r"\_", "$": r"\$",
"~": r"\textasciitilde{}", "^": r"\textasciicircum{}"}
def esc(s: str) -> str:
s = s.replace("\\", r"\textbackslash{}")
for k, v in SPECIALS.items():
s = s.replace(k, v)
for k, v in UNICODE.items():
s = s.replace(k, v)
return s
def inline(s: str) -> str:
parts = re.split(r"(`[^`]*`)", s)
out = []
for p in parts:
if p.startswith("`") and p.endswith("`") and len(p) >= 2:
out.append(r"\texttt{" + esc(p[1:-1]) + "}")
else:
p = esc(p)
p = re.sub(r"\[([^\]]+)\]\((https?://[^)]+)\)", r"\\href{\2}{\1}", p)
p = re.sub(r"\*\*([^*]+)\*\*", r"\\textbf{\1}", p)
p = re.sub(r"\*([^*]+)\*", r"\\emph{\1}", p)
p = re.sub(r'"([^"]+)"', r"``\1''", p)
out.append(p)
return "".join(out)
def figure_env(name: str) -> str:
pdfs, caption = FIGURES[name]
(HERE / "figs").mkdir(exist_ok=True)
lines = [f"\\begin{{figure*}}[p]\\centering % {name}"]
for src in pdfs:
dst = HERE / "figs" / (name + "_" + Path(src).name)
shutil.copyfile(ROOT / src, dst)
frac = min(0.98, 3.0 / len(pdfs) * 0.42)
lines.append(f"\\includegraphics[width=\\textwidth,height={frac:.2f}\\textheight,"
f"keepaspectratio]{{figs/{dst.name}}}\\par\\smallskip")
lines.append(f"\\caption{{{caption}}}\\label{{{name}}}")
lines.append("\\end{figure*}")
return "\n".join(lines)
def convert(text: str) -> str:
lines = text.split("\n")
i = 0
while i < len(lines) and lines[i].strip() != "---":
i += 1
i += 1
blocks: list[list[str]] = []
cur: list[str] = []
for line in lines[i:]:
if line.strip() == "":
if cur:
blocks.append(cur); cur = []
else:
cur.append(line)
if cur:
blocks.append(cur)
def emit_table(block, out):
rows = [[c.strip() for c in line.strip().strip("|").split("|")] for line in block]
header, body = rows[0], rows[2:]
n = len(header)
widths = " ".join([f"p{{{0.92 / n:.3f}\\textwidth}}"] * n)
out += ["\\medskip\\noindent\\begin{center}\\footnotesize",
f"\\begin{{tabular}}{{{widths}}}", "\\hline",
" & ".join(inline(c) for c in header) + " \\\\ \\hline"]
for r in body:
r = (r + [""] * n)[:n]
out.append(" & ".join(inline(c) for c in r) + " \\\\[3pt]")
out += ["\\hline\\end{tabular}\\end{center}\\medskip", ""]
out: list[str] = []
for block in blocks:
first = block[0].strip()
m = re.match(r"^\*?\(FIG:(\w+)\)\*?$", first)
if m:
out.append(figure_env(m.group(1))); out.append("")
elif first.startswith("|") and len(block) >= 2 and set(block[1].strip()) <= set("|-: "):
emit_table(block, out)
elif first == "---" and len(block) == 1:
out.append("\\medskip\\hrule\\medskip"); out.append("")
elif first.startswith("## "):
out.append(f"\\section*{{{inline(first[3:])}}}"); out.append("")
elif first.startswith("### "):
out.append(f"\\subsection*{{{inline(first[4:])}}}"); out.append("")
elif re.match(r"^(- |\d+\. )", first):
env = "itemize" if first.startswith("- ") else "enumerate"
out.append(f"\\begin{{{env}}}")
items: list[str] = []
for l in block:
s = l.strip()
if re.match(r"^(- |\d+\. )", s):
items.append(re.sub(r"^(- |\d+\. )", "", s))
else:
items[-1] += " " + s
for it in items:
out.append("\\item " + inline(it.strip()))
out.append(f"\\end{{{env}}}"); out.append("")
else:
joined = re.sub(r"\s{2,}", " ", " ".join(l.strip() for l in block)).strip()
out.append(inline(joined)); out.append("")
return "\n".join(out) + "\n"
if __name__ == "__main__":
OUT.write_text(convert(SRC.read_text()))
print(f"wrote {OUT}")