1 files changed, 130 insertions, 0 deletions
diff --git a/worldalign/degeneracy_gate.py b/worldalign/degeneracy_gate.py
new file mode 100644
index 0000000..4ba3dc1
--- /dev/null
+++ b/worldalign/degeneracy_gate.py
@@ -0,0 +1,130 @@
+"""Is the truth the optimum, tied with it, or beaten? Three descents, not seven hundred.
+
+The question that decides the next move is narrow, and the first attempt at it
+was not. Suppressing a caption factor leaves the information intact -- the
+anchor bound is 0.997 -- while blind matching returns 5.6%, and there are three
+possible reasons with three different responses:
+
+    E(truth) <  E(best found)   the searcher simply missed it   -> better optimiser
+    E(truth) == E(best found)   the truth is one of many minima  -> quotient the symmetry
+    E(truth) >  E(best found)   the truth is not the optimum     -> information is gone
+
+Answering it does not need a strong searcher. It needs the energy of the truth
+and the energy of whatever the standard pipeline actually converges to, which
+is one descent per trial rather than the sixty-one the first version ran -- at
+N=256 a single descent over all 32,640 transpositions costs minutes, so the
+difference is hours against seconds.
+"""
+
+from __future__ import annotations
+
+import argparse
+import json
+
+import numpy as np
+import torch
+
+from .common import write_json
+from .spectral_match import grampa
+from .synth_fast_gate import ClosedFormEnergy, fast_pair_descent
+from .synth_triangle_gate import standardized
+
+
+def parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--fields", nargs="+", required=True)
+    parser.add_argument("--labels", nargs="+", default=None)
+    parser.add_argument("--trials", type=int, default=3)
+    parser.add_argument("--iterations", type=int, default=600)
+    parser.add_argument("--device", default="cuda:3")
+    parser.add_argument("--tolerance", type=float, default=1e-3)
+    parser.add_argument("--output", default="artifacts/synth_v1/degeneracy_gate.json")
+    return parser.parse_args()
+
+
+def standardise(matrix: np.ndarray) -> np.ndarray:
+    mask = ~np.eye(len(matrix), dtype=bool)
+    values = matrix[mask]
+    out = (matrix - values.mean()) / values.std()
+    np.fill_diagonal(out, 0.0)
+    return out
+
+
+def analyse(path: str, label: str, args: argparse.Namespace) -> dict:
+    state = torch.load(path, map_location="cpu", weights_only=False)
+    visual = standardise(state["visual_field"].double().numpy())
+    text = standardise(state["text_field"].double().numpy())
+    size = len(visual)
+    device = torch.device(args.device)
+
+    gaps, accuracies, truths = [], [], []
+    for trial in range(args.trials):
+        generator = np.random.default_rng(trial)
+        hidden = generator.permutation(size)
+        shuffled = text[np.ix_(hidden, hidden)]
+        shuffled_gpu = standardized(torch.from_numpy(shuffled).to(device)).double()
+        visual_gpu = standardized(torch.from_numpy(visual).to(device)).double()
+        energy = ClosedFormEnergy(shuffled_gpu, visual_gpu, 1.0, 0.0, 256)
+        truth = torch.from_numpy(np.argsort(hidden).copy()).to(device)
+        truth_energy = float(energy.energy(truth[None])[0])
+
+        start = torch.from_numpy(grampa(visual, shuffled, 1.0).copy()).to(device)
+        final = fast_pair_descent(shuffled_gpu, visual_gpu, start, args.iterations)
+        found_energy = float(energy.energy(final[None])[0])
+        # descent from the truth itself: if it moves, the truth is not a local
+        # minimum either, which separates "not optimal" from "merely not found"
+        from_truth = fast_pair_descent(
+            shuffled_gpu, visual_gpu, truth.clone(), args.iterations
+        )
+        truth_local = float(energy.energy(from_truth[None])[0])
+
+        gaps.append(found_energy - truth_energy)
+        truths.append(truth_energy - truth_local)
+        accuracies.append(float((hidden[final.cpu().numpy()] == np.arange(size)).mean()))
+
+    gap = float(np.mean(gaps))
+    scale = abs(float(np.mean([g for g in gaps]))) + 1.0
+    if gap < -args.tolerance:
+        verdict = "truth is NOT the optimum -- information deficit"
+    elif abs(gap) <= args.tolerance:
+        verdict = "truth is TIED with what is found -- degenerate, quotient the symmetry"
+    else:
+        verdict = "truth is DEEPER than what is found -- optimiser failure"
+    return {
+        "label": label,
+        "size": size,
+        "energy_gap_found_minus_truth": gap,
+        "truth_descends_further_by": float(np.mean(truths)),
+        "blind_accuracy": float(np.mean(accuracies)),
+        "verdict": verdict,
+    }
+
+
+def main() -> None:
+    args = parse_args()
+    labels = args.labels or [p.split("/")[-1] for p in args.fields]
+    rows = []
+    for path, label in zip(args.fields, labels):
+        row = analyse(path, label, args)
+        rows.append(row)
+        print(
+            f"{row['label']:<20} gap(found-truth)={row['energy_gap_found_minus_truth']:+.4f}  "
+            f"truth-descends={row['truth_descends_further_by']:+.4f}  "
+            f"acc={row['blind_accuracy']:.3f}\n"
+            f"{'':<20} -> {row['verdict']}",
+            flush=True,
+        )
+    write_json(args.output, {
+        "protocol": (
+            "One spectral-start descent per trial, plus one descent started at "
+            "the truth. A positive gap means the searcher stopped above the "
+            "truth; zero means it found something the energy cannot "
+            "distinguish from the truth; negative means the truth is beaten."
+        ),
+        "rows": rows,
+    })
+    print(json.dumps({"done": True}))
+
+
+if __name__ == "__main__":
+    main()