models: new hg38_wg decoder, footprint lites, routing trees withdrawn

hg38_wg.updecx is retrained on a Loyfer-67 reference pooled from training
cells only plus the bank's 100 resolvers, to the step cap at patience 400.
It fixes the hepatocyte ELF3/MIR200C undercall (dip MAE 0.309 -> 0.047 at
29k input) and is better than the previous model at both loci at every
coverage.

hg38_celltype_lite.clfx and mm10_brain_lite.clfx are the footprint-picked
lites: resolver pairs chosen by hard-block footprint rather than the
retired gate, a fifth the size of the full banks.

hg38_celltype.clfx and mm10_celltype_brain.clfx are withdrawn, superseded
by the bank classifiers published at v9. They stay in the history and in
every earlier tag.

mm10_wg.updecx is unchanged: its tissue-reference pilot was inconclusive,
so the mouse decoder is carried forward and revisited later.

hg38_celltype.clfx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:16c4e9ccc7fd5997a4676f50926f0257fffecb97424c9c4efc393984ef7170c3
-size 13998591

hg38_celltype_lite.clfx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ca47d7af07f07f5d9dc7dd415bbfa7931da13d6c3ca88f90deeb306f1643ffc
-size 53848077
+oid sha256:a89214fe1a9a3a562eefeb2044eceac0509146df93296db3663abd5ca337b988
+size 22205304

hg38_wg.updecx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60c786aa383c27461e7a5de37d6b17d2e01b33c5f8a6553f3df7083035fac65a
-size 2835749302
+oid sha256:a1aeaf7d62ec8546bd40963f2fe18dcb0bdb54360b64748c10fbd304816442d8
+size 2866632834

mm10_brain_lite.clfx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76c5de9ebff41a0ec82484668b4c62d5c0ace6e3beb208cea6c69c7a972eb1ee
-size 28222345
+oid sha256:58df24503facfdb7a65d8862918b4f553e359ceb4191b4e2fd395c719c125047
+size 13917982

mm10_celltype_brain.clfx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c754eb20c03758678d7da861080b68461b636aded7be1544b38f23e0d6b04902
-size 105823329