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

references: citation-order renumbering, PNAS style, full verification

Browse source 
All 66 references renumbered to first-appearance order (programmatically
verified: in-text sequence = 1..66 = list order; ranges expanded,
remapped, recompressed) and rewritten in PNAS style (initials-first
authors with the >5 -> et-al rule, sentence-case titles, abbreviated
italic venues, bold volumes, year-at-end, arXiv [Preprint] + 10.48550
DOIs). Correctness: 47 arXiv ids batch-verified against the arXiv API
(title/first-author/year); caught and fixed an authorless GENOME entry
(Y. Zhang et al.), "Sakana AI" -> J. Abrantes et al., a wrong Kotha id
(2310.05719, a different paper -> 2309.10105), Nemotron's corporate
author, and Liang's truncated title. Also: six load-bearing refs that
lost their in-text anchors during the restructure re-anchored (NK, QD,
Pari, LoRA, Sharma, Kozodoi), one real mis-citation fixed
(Self-Instruct credited to Multiagent-Finetuning; new ref added), and
four figure captions in build.py brought up to third-review calibration
(operational grounding threshold; first-order conservation;
complementary-contributions society; permutation-and-rescaling
alignment). 20-pp rebuild clean.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BkRLcc18rwT2Lysu6PbG7v
This commit is contained in:
Giorgio Gilestro 2026-09-07 09:00:56 +01:00
parent 543cbe3e45
commit 6f1f8bf172
5 changed files with 218 additions and 205 deletions
Download patch file Download diff file Expand all files Collapse all files

22
paper/pnas/build.py
View file

@ -23,17 +23,18 @@ 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) "
"Collapse is drift; grounding is immigration. (A, top) The grounding response in the minimal "
"model: an operational threshold $g\\!\\approx\\!0.05$ retained most equilibrium diversity in "
"the tested setting (the equilibrium is smooth in $g$), while per-item observation obeys "
"$1-e^{-m p}$. (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 "
"Recombination: blending inheritance and the Fisher--Muller effect. (A, top) Refitting a child "
"to the mean of its parents' output distributions conserves expected rare-item mass at the "
"single-parent level, cancelling the multi-parent gain to first order in the rare-item "
"regime; a strongest-source (union) operator, with renormalisation and an oracle, realises it. (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"],
@ -45,8 +46,9 @@ FIGURES: dict[str, tuple[list[str], str]] = {
"(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 "
"The society: grounded evaluation, recombination, and diversity preservation make complementary "
"contributions in the tested model. A finite agent population on a rugged NK landscape, with "
"selection weighting true fitness against conformity. 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."),
@ -55,7 +57,7 @@ FIGURES: dict[str, tuple[list[str], str]] = {
"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 --- "
"middle) Trained MLPs: the merge barrier decomposed under permutation-and-rescaling alignment --- "
"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 "