Record the matching battery: fifteen solvers, one amplifier

Adds MATCHING_RESULTS.md. Entropic GW annealed and PATH both reach 0.961
on the reference field, above the 0.958 the project's own pipeline
reached after months, and neither had been run. GW reaches 0.881 on the
rank-8 field where GRAMPA reaches 0.076 -- which retires the morning's
rank-ladder conclusion, since that ladder was run entirely with GRAMPA
and GRAMPA degrades on clustered eigenvalues.

The hard instance yields to amplification rather than a better solver:
descent multiplies a partial answer by about four, so the job is to feed
it a start that is 10-20% correct rather than to replace it.

Co-Authored-By: Claude <noreply@anthropic.com>

1 files changed, 59 insertions, 0 deletions

diff --git a/logs/verify.py b/logs/verify.py
new file mode 100644
index 0000000..17fd643
--- /dev/null
+++ b/logs/verify.py
@@ -0,0 +1,59 @@
+import sys, numpy as np, ot, torch
+sys.path.insert(0,'/home/yurenh2/emm')
+from scipy.optimize import linear_sum_assignment
+from worldalign.synth_fast_gate import ClosedFormEnergy, fast_pair_descent
+from worldalign.synth_triangle_gate import standardized
+DEV=torch.device("cuda:1")
+def standardise(m):
+    mask=~np.eye(len(m),dtype=bool); v=m[mask]
+    o=(m-v.mean())/v.std(); np.fill_diagonal(o,0.0); return o
+def tlb(V,S):
+    n=len(V); a=np.sort(V,1); b=np.sort(S,1)
+    return (a*a).sum(1)[:,None]/n+(b*b).sum(1)[None,:]/n-2*(a@b.T)/n
+st=torch.load("/home/yurenh2/emm/artifacts/synth_v1/omit_size.pt",map_location='cpu',weights_only=False)
+V=standardise(st["visual_field"].double().numpy()); T=standardise(st["text_field"].double().numpy())
+n=len(V); w=ot.unif(n)
+rng=np.random.default_rng(0); hid=rng.permutation(n); S=T[np.ix_(hid,hid)]
+Vg=standardized(torch.from_numpy(V).to(DEV)).double(); Sg=standardized(torch.from_numpy(S).to(DEV)).double()
+en=ClosedFormEnergy(Sg,Vg,1.0,0.0,64)
+M=tlb(V,S); M=M/M.max()
+G=np.outer(w,w)
+for a in (0.0,0.2):
+    G=ot.gromov.fused_gromov_wasserstein(M,V,S,w,w,"square_loss",alpha=a,G0=G,max_iter=200,tol_rel=1e-9)
+_,cols=linear_sum_assignment(-G)
+fin=fast_pair_descent(Sg,Vg,torch.from_numpy(np.ascontiguousarray(cols)).to(DEV),2000).cpu().numpy()
+truth=np.argsort(hid)
+Ef=float(en.energy(torch.from_numpy(np.ascontiguousarray(fin)).to(DEV)[None])[0])
+Et=float(en.energy(torch.from_numpy(np.ascontiguousarray(truth)).to(DEV)[None])[0])
+acc=float((hid[fin]==np.arange(n)).mean())
+print("accuracy=%.4f  E_found=%.10f  E_truth=%.10f  diff=%.3e"%(acc,Ef,Et,Ef-Et))
+wrong=np.where(hid[fin]!=np.arange(n))[0]
+print("n_wrong=%d"%len(wrong))
+# for each wrong scene i: correlation between S-row of assigned node and S-row of true node
+Sal=S  # in shuffled index space
+corr=[]
+vcorr=[]
+for i in wrong:
+    a_idx=fin[i]; t_idx=truth[i]
+    x=np.delete(Sal[a_idx],[a_idx,t_idx]); y=np.delete(Sal[t_idx],[a_idx,t_idx])
+    corr.append(np.corrcoef(x,y)[0,1])
+    u=np.delete(V[i],[i]); 
+    # visual side: is the visually-assigned scene similar to i? compare V rows of i and of the scene truly at a_idx
+    j=hid[a_idx]
+    v1=np.delete(V[i],[i,j]); v2=np.delete(V[j],[i,j])
+    vcorr.append(np.corrcoef(v1,v2)[0,1])
+rng2=np.random.default_rng(7); pairs=rng2.integers(0,n,(len(wrong),2))
+base=[np.corrcoef(np.delete(Sal[p],[p,q]),np.delete(Sal[q],[p,q]))[0,1] for p,q in pairs if p!=q]
+print("text-row corr of confused partners: median=%.3f mean=%.3f  | random pair baseline median=%.3f"%(np.median(corr),np.mean(corr),np.median(base)))
+print("visual-row corr of confused partners: median=%.3f"%np.median(vcorr))
+# cycle structure of the error
+perm=hid[fin]
+seen=set(); cyc=[]
+for i in range(n):
+    if i in seen or perm[i]==i: continue
+    c=0; j=i
+    while j not in seen:
+        seen.add(j); j=perm[j]; c+=1
+    cyc.append(c)
+import collections
+print("error cycle lengths:", dict(collections.Counter(cyc)))