Restructure: descriptive tier and experiment names, paper/manuscript

- 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

figures/plot_grounding.py

@@ -1,140 +0,0 @@
-"""`grounding` figure — the neural grounding response in REAL weights (↔ Layer-1 E2).
-
-Honest reframing (see the progress log): the RNN's smoothing inductive bias makes H and
-tail-SURVIVAL the *wrong* neural collapse metrics — the model keeps spurious tail support
-alive even while its distribution drifts far from truth, so tail_truth_mass_alive is flat /
-non-monotone in g. The operative neural collapse metric is FORWARD-KL, on which grounding's
-effect is monotone and significant. The sharp Layer-1 threshold (g*=0.048) is an *exact-
-operator* feature reproduced quantitatively by the histogram bridge (g*=0.047); the trained
-RNN confirms it in SIGN and softens it in sharpness.
-
-Four panels: (A) forward-KL trajectories (dry climbs, grounded suppressed); (B) the phase
-boundary — stationary forward-KL vs g, monotone down; (C) recovery fraction with the median-
-recovery grounding (≈Layer-1's 0.048) and the note that full recovery needs much more g in a
-smoothing model; (D) the metric-choice panel — H and tail-survival are flat/non-monotone
-while forward-KL responds. Reads only the committed bundle.
-
-Usage:  python figures/plot_grounding.py [results/grounding]
-"""
-
-from __future__ import annotations
-
-import sys
-from pathlib import Path
-
-import matplotlib.pyplot as plt
-import numpy as np
-
-sys.path.insert(0, str(Path(__file__).parent))
-from _figlib import load_bundle, mean_ci, savefig, letter_axes  # noqa: E402
-
-sys.path.insert(0, str(Path(__file__).parents[1] / "src"))
-from knowledge.analysis import reduce_to_stationary  # noqa: E402
-from knowledge.metrics import heterozygosity  # noqa: E402
-from neural.config import SyntheticCfg  # noqa: E402
-from neural.synthetic import make_mode_truth  # noqa: E402
-
-_LAYER1_GSTAR = 0.048   # the analytic / histogram-bridge critical grounding fraction
-
-
-def _recovery_gstar(piv: np.ndarray, gs: np.ndarray, frac: float, seed: int = 7):
-    """Grounding at which forward-KL closes ``frac`` of its achievable reduction, + CI.
-
-    recovery(g) = (KL(0) - KL(g)) / (KL(0) - KL(g_max)); returns the first upward crossing of
-    ``frac`` with a percentile-bootstrap CI over replicates. This is a *descriptive* recovery
-    point, not a pre-registered sharp threshold (the RNN has no sharp g*).
-    """
-    def crossing(mat):
-        mk = mat.mean(axis=0)
-        rec = (mk[0] - mk) / (mk[0] - mk[-1])
-        idx = np.where(rec >= frac)[0]
-        if idx.size == 0 or idx[0] == 0:
-            return np.nan
-        i = idx[0]
-        r0, r1 = rec[i - 1], rec[i]
-        return gs[i - 1] + (frac - r0) * (gs[i] - gs[i - 1]) / (r1 - r0) if r1 > r0 else gs[i]
-
-    pt = crossing(piv)
-    rng = np.random.default_rng(seed)
-    boots = np.array([crossing(piv[rng.integers(0, piv.shape[0], piv.shape[0])])
-                      for _ in range(4000)])
-    boots = boots[~np.isnan(boots)]
-    lo, hi = (np.percentile(boots, [2.5, 97.5]) if boots.size else (np.nan, np.nan))
-    return float(pt), float(lo), float(hi)
-
-
-def main(results_dir: str = "results/grounding") -> None:
-    df, cfg = load_bundle(results_dir)
-    syn = SyntheticCfg(**cfg["synthetic"])
-    H_star = heterozygosity(make_mode_truth(syn).p_star)
-
-    g_values = np.array(sorted(df["g"].unique()))
-    last = int(cfg["generations"] * 0.6)          # stationary window: final 40% of the run
-    stat = df[df["generation"] >= last]
-
-    st_kl = reduce_to_stationary(stat, value_col="forward_kl")
-    piv = st_kl.pivot(index="replicate", columns="g", values="forward_kl")[g_values].to_numpy()
-    g50, lo50, hi50 = _recovery_gstar(piv, g_values, 0.5)
-
-    fig, axes = plt.subplots(2, 2, figsize=(13, 9))
-    colors = plt.cm.viridis(np.linspace(0, 0.9, len(g_values)))
-
-    # Panel A: forward-KL trajectories (dry climbs, grounded suppressed).
-    ax = axes[0, 0]
-    for g, c in zip(g_values, colors):
-        s = df[df["g"] == g].groupby("generation")["forward_kl"].mean()
-        ax.plot(s.index, s.values, color=c, label=f"g={g:g}")
-    ax.set(xlabel="generation", ylabel=r"forward-KL $D(p^*\Vert\hat p)$",
-           title="Trajectories: grounding suppresses divergence")
-    ax.legend(frameon=False, fontsize=8, ncol=2)
-
-    # Panel B: the phase boundary — stationary forward-KL vs g (monotone down).
-    ax = axes[0, 1]
-    kg, Km, Kci = mean_ci(st_kl, "g", "forward_kl")
-    ax.errorbar(kg, Km, yerr=Kci, fmt="o-", color="#1f77b4", capsize=3, zorder=3)
-    ax.set(xlabel="grounding fraction $g=m/(n+m)$",
-           ylabel=r"stationary forward-KL $D(p^*\Vert\hat p)$",
-           title="Trained RNN: KL falls monotonically with grounding\n"
-                 "(paired $t$=3.3 at $g$=0.2)")
-
-    # Panel C: recovery fraction with the median-recovery grounding vs Layer-1's g*.
-    ax = axes[1, 0]
-    mk = piv.mean(axis=0)
-    rec = (mk[0] - mk) / (mk[0] - mk[-1])
-    ax.plot(g_values, rec, "o-", color="#2ca02c")
-    ax.axhline(0.5, ls=":", color="gray", lw=1)
-    ax.axvspan(lo50, hi50, color="#d62728", alpha=0.15)
-    ax.axvline(g50, color="#d62728", lw=1.2,
-               label=f"median-recovery $g$={g50:.3f}\n(95% CI [{lo50:.3f},{hi50:.3f}])")
-    ax.axvline(_LAYER1_GSTAR, ls="--", color="k", lw=1, label=f"analytic $g^*$={_LAYER1_GSTAR}")
-    ax.set(xlabel="grounding fraction $g$", ylabel="forward-KL recovery fraction",
-           title="Half the divergence gap closes by $g\\approx0.04$\n"
-                 "(full recovery needs more g: smoothing softens the threshold)")
-    ax.legend(frameon=False, fontsize=8)
-
-    # Panel D: why forward-KL — H and tail-survival are flat/non-monotone in a smoothing model.
-    ax = axes[1, 1]
-    for col, lab, style in [("heterozygosity", r"$H$ / $H^*$", "s-"),
-                            ("tail_truth_mass_alive", "tail survival", "^-"),
-                            ("forward_kl", "forward-KL recovery", "o-")]:
-        st = reduce_to_stationary(stat, value_col=col)
-        s = st.groupby("g")[col].mean().reindex(g_values)
-        if col == "heterozygosity":
-            y = s.to_numpy() / H_star
-        elif col == "forward_kl":
-            y = (s.iloc[0] - s.to_numpy()) / (s.iloc[0] - s.iloc[-1])   # recovery, 0..1
-        else:
-            y = s.to_numpy()
-        ax.plot(g_values, y, style, ms=4, label=lab)
-    ax.set(xlabel="grounding fraction $g$", ylabel="normalised response (0–1)",
-           title="Metric choice: $H$ & tail-survival are flat/non-monotone\n"
-                 "(smoothing keeps spurious support); forward-KL responds")
-    ax.legend(frameon=False, fontsize=8)
-
-    fig.tight_layout()
-    letter_axes(fig)
-    savefig(fig, results_dir, "grounding")
-
-
-if __name__ == "__main__":
-    main(*sys.argv[1:])