Manuscript revision and pending experiment work, snapshot before restructuring

Clarity pass over the main text (36-item audit), Discussion rewrite and cut,
acknowledgements, Souly et al. as ref 62, lettered SI panels, model section
moved under Results; plus the untracked curriculum/society/compose/smol
configs, runners, figures, stats and tests that the SI already cites.

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 16:54:09 +01:00
parent e4804adabc
commit 84124de143
450 changed files with 52813 additions and 1202 deletions

View file

@ -19,18 +19,18 @@ import matplotlib.pyplot as plt
import numpy as np
sys.path.insert(0, str(Path(__file__).parent))
from _figlib import load_bundle, savefig # noqa: E402
from _figlib import load_seed_bundles, savefig # noqa: E402
_FAMS = ["lists", "strings", "arith"]
def _acc(df, model, metric):
r = df[(df["model"] == model) & (df["metric"] == metric)]["accuracy"]
return float(r.iloc[0]) if len(r) else float("nan")
return float(r.mean()) if len(r) else float("nan")
def main(results_dir: str = "results/llm_merge") -> None:
df, cfg = load_bundle(results_dir)
df, cfg = load_seed_bundles(results_dir) # seed-mean when the bundle has s{seed}/ sub-bundles
specialists = sorted(m for m in df["model"].unique() if m.startswith("spec_"))
merges = sorted(m for m in df["model"].unique() if m.startswith("merge_"))
models = ["base"] + specialists + merges