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

main: keep only what reproduces the manuscript; everything else lives on dev

Browse source 
Removed from main (all preserved on the dev branch): the arXiv build and
its sources, design documents (blueprint, results summary, review responses,
essay drafts), tasks/ and CLAUDE.md, the cover letter and reference tooling,
two unused manuscript figures, and every experiment that feeds no figure or
number in the paper: the collapse null, the sexual-vs-asexual lineage, the
NK speciation variant, the 0.5B single-seed LLM prototypes, the compose and
society experiments with their calibration and pilot runs, and their
configs, runners, tests, figure scripts and PBS jobs. Their result bundles
are moved to results/_archive/ (ignored) so the parquets stay on disk.

Also: plot_llm_speciation reads the s{seed}/ layout; the mating-breadth
plot writes under its bundle name; Makefile targets reduced to the kept
experiments; REPRODUCING.md and README point to dev for the rest.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Y64o8FKP7rCuXzC48pxpMm
This commit is contained in:
Giorgio Gilestro 2026-09-13 17:07:23 +01:00
parent ab3dc10587
commit 6f8cef1ac5
292 changed files with 26 additions and 15590 deletions
Download patch file Download diff file Expand all files Collapse all files

59
tests/test_llm.py
View file

@ -138,62 +138,3 @@ def test_lora_delta_inner_matches_brute_force():
A2, B2 = torch.randn(4, 20, generator=g), torch.randn(12, 4, generator=g)
brute = float(((B1 @ A1) * (B2 @ A2)).sum())
assert abs(lora_delta_inner(A1, B1, A2, B2) - brute) < 1e-3
# ---------------------------------------------------------------------- society (pure operators)
def test_society_consensus_is_modal_and_deterministic():
from llm.society import consensus_answers
outs = [["5", "cat", "[1, 2]"],
["5", "dog", "[1, 2]"],
["7", "dog", "[2, 1]"]]
cons = consensus_answers(outs)
assert cons[0] == "5" and cons[1] == "dog" and cons[2] == "[1, 2]"
# a full three-way tie breaks lexicographically (deterministic)
tie = consensus_answers([["a"], ["b"], ["c"]])
assert tie == ["a"]
def test_society_conformity_and_distance():
from llm.society import behavioural_distance, conformity_scores, consensus_answers
outs = [["5", "dog"], ["5", "dog"], ["7", "cat"]]
cons = consensus_answers(outs)
conf = conformity_scores(outs, cons)
assert conf[0] == conf[1] == 1.0 and conf[2] == 0.0 # majority conforms, dissenter does not
d = behavioural_distance(outs)
assert d[0, 1] == 0.0 and d[0, 2] == 1.0 and np.allclose(d, d.T)
def test_society_selection_greedy_vs_quality_diversity():
from llm.society import select_parents
scores = np.array([1.0, 0.95, 0.94, 0.1])
# agents 0 and 1 are behavioural clones; agent 2 is distant from both
d = np.zeros((4, 4))
d[0, 2] = d[2, 0] = d[1, 2] = d[2, 1] = 1.0
d[0, 3] = d[3, 0] = d[1, 3] = d[3, 1] = d[2, 3] = d[3, 2] = 1.0
greedy = select_parents(scores, d, 2, diversity=False)
assert greedy == [0, 1] # pure score: takes the clones
qd = select_parents(scores, d, 2, diversity=True, lam=0.3)
assert qd == [0, 2] # QD: prefers the distant near-peer
def test_society_pairs_and_arms():
import pytest
from llm.society import arm_settings, complementary_pairs
d = np.zeros((4, 4))
d[0, 1] = d[1, 0] = 0.9
d[0, 2] = d[2, 0] = 0.2
d[1, 2] = d[2, 1] = 0.5
pairs = complementary_pairs([0, 1, 2], d, 4)
assert pairs[0] == (0, 1) and pairs[1] == (1, 2) # most-complementary pair breeds first
assert len(pairs) == 4 and pairs[3] == pairs[0] # cycles to fill the slots
assert arm_settings("no_grounding", 0.5)["g"] == 0.0
assert arm_settings("no_sex", 0.5) == {"g": 0.5, "sex": False, "diversity": True}
with pytest.raises(ValueError):
arm_settings("bogus", 0.5)