diff --git a/.gitignore b/.gitignore
index 84e7f06..5381ab2 100644
--- a/.gitignore
+++ b/.gitignore
@@ -5,3 +5,5 @@ data-stress
 *.zst
 *.zst.meta
 *.pb
+*.json
+*.bin
diff --git a/debug.log b/debug.log
new file mode 100644
index 0000000..4244ba5
--- /dev/null
+++ b/debug.log
@@ -0,0 +1,275 @@
+[2m2026-04-27T20:36:04.208955Z[0m [32m INFO[0m [2mobikmer::cmd::partition[0m[2m:[0m dereplicating...
+[2m2026-04-27T20:36:11.471489Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 0/256
+[2m2026-04-27T20:36:11.471521Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 128/256
+[2m2026-04-27T20:36:11.471530Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 32/256
+[2m2026-04-27T20:36:11.471535Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 12/256
+[2m2026-04-27T20:36:11.471551Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 76/256
+[2m2026-04-27T20:36:11.471522Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 2/256
+[2m2026-04-27T20:36:11.471525Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 4/256
+[2m2026-04-27T20:36:11.471535Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 96/256
+[2m2026-04-27T20:36:11.471535Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 80/256
+[2m2026-04-27T20:36:11.471535Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 10/256
+[2m2026-04-27T20:36:11.471538Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 16/256
+[2m2026-04-27T20:36:11.471543Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 224/256
+[2m2026-04-27T20:36:11.471537Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 192/256
+[2m2026-04-27T20:36:11.471536Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 64/256
+[2m2026-04-27T20:36:11.471537Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 72/256
+[2m2026-04-27T20:36:11.471530Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 8/256
+[2m2026-04-27T20:36:12.831739Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 129/256
+[2m2026-04-27T20:36:13.555104Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 9/256
+[2m2026-04-27T20:36:14.077082Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 17/256
+[2m2026-04-27T20:36:14.203310Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 77/256
+[2m2026-04-27T20:36:14.316403Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 3/256
+[2m2026-04-27T20:36:14.415177Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 33/256
+[2m2026-04-27T20:36:14.467689Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 97/256
+[2m2026-04-27T20:36:14.559650Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 5/256
+[2m2026-04-27T20:36:14.591431Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 81/256
+[2m2026-04-27T20:36:14.606508Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 193/256
+[2m2026-04-27T20:36:14.611406Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 73/256
+[2m2026-04-27T20:36:14.623813Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 11/256
+[2m2026-04-27T20:36:14.665058Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 65/256
+[2m2026-04-27T20:36:14.666877Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 1/256
+[2m2026-04-27T20:36:14.667569Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 13/256
+[2m2026-04-27T20:36:14.697486Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 225/256
+[2m2026-04-27T20:36:14.698441Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 130/256
+[2m2026-04-27T20:36:14.998749Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 14/256
+[2m2026-04-27T20:36:15.485303Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 18/256
+[2m2026-04-27T20:36:15.637613Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 78/256
+[2m2026-04-27T20:36:15.722825Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 98/256
+[2m2026-04-27T20:36:15.831703Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 112/256
+[2m2026-04-27T20:36:16.161408Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 66/256
+[2m2026-04-27T20:36:16.340113Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 226/256
+[2m2026-04-27T20:36:16.506407Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 82/256
+[2m2026-04-27T20:36:16.542430Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 74/256
+[2m2026-04-27T20:36:16.550654Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 34/256
+[2m2026-04-27T20:36:16.634719Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 6/256
+[2m2026-04-27T20:36:16.763833Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 194/256
+[2m2026-04-27T20:36:16.813285Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 131/256
+[2m2026-04-27T20:36:16.913975Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 208/256
+[2m2026-04-27T20:36:16.993526Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 15/256
+[2m2026-04-27T20:36:17.092998Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 160/256
+[2m2026-04-27T20:36:17.114964Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 88/256
+[2m2026-04-27T20:36:17.148685Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 79/256
+[2m2026-04-27T20:36:17.161989Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 19/256
+[2m2026-04-27T20:36:17.180022Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 113/256
+[2m2026-04-27T20:36:17.397037Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 67/256
+[2m2026-04-27T20:36:17.484519Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 99/256
+[2m2026-04-27T20:36:17.906842Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 35/256
+[2m2026-04-27T20:36:18.146262Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 75/256
+[2m2026-04-27T20:36:18.247130Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 7/256
+[2m2026-04-27T20:36:18.303872Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 227/256
+[2m2026-04-27T20:36:18.374448Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 195/256
+[2m2026-04-27T20:36:18.382279Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 83/256
+[2m2026-04-27T20:36:18.428092Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 104/256
+[2m2026-04-27T20:36:18.442213Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 132/256
+[2m2026-04-27T20:36:18.621883Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 209/256
+[2m2026-04-27T20:36:18.784307Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 161/256
+[2m2026-04-27T20:36:18.796465Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 114/256
+[2m2026-04-27T20:36:18.877587Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 120/256
+[2m2026-04-27T20:36:18.888423Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 89/256
+[2m2026-04-27T20:36:18.918340Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 20/256
+[2m2026-04-27T20:36:18.985341Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 100/256
+[2m2026-04-27T20:36:19.080092Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 68/256
+[2m2026-04-27T20:36:19.282760Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 36/256
+[2m2026-04-27T20:36:19.485079Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 92/256
+[2m2026-04-27T20:36:19.692354Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 24/256
+[2m2026-04-27T20:36:19.746458Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 228/256
+[2m2026-04-27T20:36:20.004054Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 84/256
+[2m2026-04-27T20:36:20.164510Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 196/256
+[2m2026-04-27T20:36:20.277288Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 105/256
+[2m2026-04-27T20:36:20.349391Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 133/256
+[2m2026-04-27T20:36:20.511981Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 210/256
+[2m2026-04-27T20:36:20.709583Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 101/256
+[2m2026-04-27T20:36:20.715870Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 69/256
+[2m2026-04-27T20:36:20.728029Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 115/256
+[2m2026-04-27T20:36:20.822257Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 162/256
+[2m2026-04-27T20:36:20.982131Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 90/256
+[2m2026-04-27T20:36:20.990122Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 21/256
+[2m2026-04-27T20:36:21.030814Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 121/256
+[2m2026-04-27T20:36:21.088309Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 93/256
+[2m2026-04-27T20:36:21.134904Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 37/256
+[2m2026-04-27T20:36:21.196814Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 25/256
+[2m2026-04-27T20:36:21.444384Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 85/256
+[2m2026-04-27T20:36:21.605343Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 197/256
+[2m2026-04-27T20:36:21.954010Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 106/256
+[2m2026-04-27T20:36:22.026167Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 229/256
+[2m2026-04-27T20:36:22.194676Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 134/256
+[2m2026-04-27T20:36:22.209911Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 211/256
+[2m2026-04-27T20:36:22.281984Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 70/256
+[2m2026-04-27T20:36:22.440637Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 163/256
+[2m2026-04-27T20:36:22.481750Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 91/256
+[2m2026-04-27T20:36:22.522458Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 116/256
+[2m2026-04-27T20:36:22.775669Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 22/256
+[2m2026-04-27T20:36:23.095766Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 102/256
+[2m2026-04-27T20:36:23.119802Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 94/256
+[2m2026-04-27T20:36:23.183138Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 122/256
+[2m2026-04-27T20:36:23.186904Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 38/256
+[2m2026-04-27T20:36:23.196250Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 86/256
+[2m2026-04-27T20:36:23.206118Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 26/256
+[2m2026-04-27T20:36:23.314520Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 198/256
+[2m2026-04-27T20:36:23.355959Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 107/256
+[2m2026-04-27T20:36:23.526146Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 230/256
+[2m2026-04-27T20:36:23.723572Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 212/256
+[2m2026-04-27T20:36:23.856569Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 71/256
+[2m2026-04-27T20:36:23.910613Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 164/256
+[2m2026-04-27T20:36:23.945560Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 135/256
+[2m2026-04-27T20:36:24.085073Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 117/256
+[2m2026-04-27T20:36:24.111144Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 144/256
+[2m2026-04-27T20:36:24.188547Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 23/256
+[2m2026-04-27T20:36:24.573867Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 103/256
+[2m2026-04-27T20:36:24.604461Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 27/256
+[2m2026-04-27T20:36:24.670189Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 95/256
+[2m2026-04-27T20:36:24.935767Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 123/256
+[2m2026-04-27T20:36:25.031507Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 39/256
+[2m2026-04-27T20:36:25.039809Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 108/256
+[2m2026-04-27T20:36:25.067950Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 199/256
+[2m2026-04-27T20:36:25.149100Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 231/256
+[2m2026-04-27T20:36:25.272346Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 213/256
+[2m2026-04-27T20:36:25.400111Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 165/256
+[2m2026-04-27T20:36:25.607381Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 136/256
+[2m2026-04-27T20:36:25.902415Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 152/256
+[2m2026-04-27T20:36:26.055400Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 118/256
+[2m2026-04-27T20:36:26.138877Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 119/256
+[2m2026-04-27T20:36:26.255235Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 87/256
+[2m2026-04-27T20:36:26.350364Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 148/256
+[2m2026-04-27T20:36:26.465089Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 145/256
+[2m2026-04-27T20:36:26.682375Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 40/256
+[2m2026-04-27T20:36:26.694729Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 216/256
+[2m2026-04-27T20:36:26.777197Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 28/256
+[2m2026-04-27T20:36:26.802996Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 124/256
+[2m2026-04-27T20:36:26.972099Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 200/256
+[2m2026-04-27T20:36:27.066713Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 232/256
+[2m2026-04-27T20:36:27.112569Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 166/256
+[2m2026-04-27T20:36:27.156124Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 214/256
+[2m2026-04-27T20:36:27.231214Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 137/256
+[2m2026-04-27T20:36:27.359784Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 109/256
+[2m2026-04-27T20:36:27.369743Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 153/256
+[2m2026-04-27T20:36:27.668409Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 204/256
+[2m2026-04-27T20:36:27.701887Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 202/256
+[2m2026-04-27T20:36:27.794402Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 215/256
+[2m2026-04-27T20:36:28.058391Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 149/256
+[2m2026-04-27T20:36:28.192195Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 217/256
+[2m2026-04-27T20:36:28.369717Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 125/256
+[2m2026-04-27T20:36:28.412339Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 41/256
+[2m2026-04-27T20:36:28.496068Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 29/256
+[2m2026-04-27T20:36:28.693510Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 167/256
+[2m2026-04-27T20:36:28.808495Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 201/256
+[2m2026-04-27T20:36:28.843564Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 233/256
+[2m2026-04-27T20:36:28.917920Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 140/256
+[2m2026-04-27T20:36:28.940416Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 138/256
+[2m2026-04-27T20:36:29.125956Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 110/256
+[2m2026-04-27T20:36:29.197246Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 154/256
+[2m2026-04-27T20:36:29.376894Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 203/256
+[2m2026-04-27T20:36:29.491887Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 176/256
+[2m2026-04-27T20:36:29.501763Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 205/256
+[2m2026-04-27T20:36:29.538499Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 150/256
+[2m2026-04-27T20:36:29.685646Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 218/256
+[2m2026-04-27T20:36:29.874786Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 126/256
+[2m2026-04-27T20:36:30.021059Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 42/256
+[2m2026-04-27T20:36:30.255780Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 240/256
+[2m2026-04-27T20:36:30.602468Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 141/256
+[2m2026-04-27T20:36:30.696718Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 234/256
+[2m2026-04-27T20:36:30.784522Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 139/256
+[2m2026-04-27T20:36:31.027016Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 155/256
+[2m2026-04-27T20:36:31.073326Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 30/256
+[2m2026-04-27T20:36:31.137264Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 111/256
+[2m2026-04-27T20:36:31.143413Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 168/256
+[2m2026-04-27T20:36:31.237329Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 206/256
+[2m2026-04-27T20:36:31.252908Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 236/256
+[2m2026-04-27T20:36:31.306110Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 177/256
+[2m2026-04-27T20:36:31.431064Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 151/256
+[2m2026-04-27T20:36:31.490837Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 127/256
+[2m2026-04-27T20:36:31.528815Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 43/256
+[2m2026-04-27T20:36:31.790858Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 219/256
+[2m2026-04-27T20:36:31.803934Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 241/256
+[2m2026-04-27T20:36:32.131051Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 156/256
+[2m2026-04-27T20:36:32.433342Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 235/256
+[2m2026-04-27T20:36:32.459699Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 142/256
+[2m2026-04-27T20:36:32.532717Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 31/256
+[2m2026-04-27T20:36:32.814909Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 184/256
+[2m2026-04-27T20:36:32.967090Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 169/256
+[2m2026-04-27T20:36:33.062660Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 178/256
+[2m2026-04-27T20:36:33.076014Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 237/256
+[2m2026-04-27T20:36:33.128961Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 207/256
+[2m2026-04-27T20:36:33.228734Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 180/256
+[2m2026-04-27T20:36:33.228905Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 143/256
+[2m2026-04-27T20:36:33.266931Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 44/256
+[2m2026-04-27T20:36:33.280333Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 158/256
+[2m2026-04-27T20:36:33.368740Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 220/256
+[2m2026-04-27T20:36:33.373469Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 179/256
+[2m2026-04-27T20:36:33.409455Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 157/256
+[2m2026-04-27T20:36:33.685036Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 242/256
+[2m2026-04-27T20:36:34.174714Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 182/256
+[2m2026-04-27T20:36:34.255362Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 146/256
+[2m2026-04-27T20:36:34.284053Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 170/256
+[2m2026-04-27T20:36:34.340602Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 185/256
+[2m2026-04-27T20:36:34.748830Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 45/256
+[2m2026-04-27T20:36:34.894515Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 172/256
+[2m2026-04-27T20:36:35.342815Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 238/256
+[2m2026-04-27T20:36:35.549647Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 159/256
+[2m2026-04-27T20:36:35.556431Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 181/256
+[2m2026-04-27T20:36:35.579877Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 188/256
+[2m2026-04-27T20:36:35.619438Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 221/256
+[2m2026-04-27T20:36:35.704344Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 174/256
+[2m2026-04-27T20:36:35.891634Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 190/256
+[2m2026-04-27T20:36:35.893065Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 239/256
+[2m2026-04-27T20:36:35.978053Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 183/256
+[2m2026-04-27T20:36:35.980835Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 186/256
+[2m2026-04-27T20:36:36.010364Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 243/256
+[2m2026-04-27T20:36:36.084972Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 171/256
+[2m2026-04-27T20:36:36.085806Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 147/256
+[2m2026-04-27T20:36:36.129893Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 48/256
+[2m2026-04-27T20:36:36.188339Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 46/256
+[2m2026-04-27T20:36:36.281975Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 173/256
+[2m2026-04-27T20:36:37.004395Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 187/256
+[2m2026-04-27T20:36:37.080479Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 222/256
+[2m2026-04-27T20:36:37.100573Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 189/256
+[2m2026-04-27T20:36:37.422152Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 248/256
+[2m2026-04-27T20:36:37.446786Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 175/256
+[2m2026-04-27T20:36:37.951518Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 244/256
+[2m2026-04-27T20:36:38.235613Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 191/256
+[2m2026-04-27T20:36:38.259288Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 47/256
+[2m2026-04-27T20:36:38.379966Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 252/256
+[2m2026-04-27T20:36:38.380690Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 223/256
+[2m2026-04-27T20:36:38.520398Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 56/256
+[2m2026-04-27T20:36:38.598256Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 49/256
+[2m2026-04-27T20:36:38.680704Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 254/256
+[2m2026-04-27T20:36:38.681038Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 246/256
+[2m2026-04-27T20:36:38.813533Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 247/256
+[2m2026-04-27T20:36:38.820199Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 60/256
+[2m2026-04-27T20:36:38.961240Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 52/256
+[2m2026-04-27T20:36:39.001585Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 58/256
+[2m2026-04-27T20:36:39.050047Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 249/256
+[2m2026-04-27T20:36:39.076449Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 57/256
+[2m2026-04-27T20:36:39.078254Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 250/256
+[2m2026-04-27T20:36:39.082390Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 251/256
+[2m2026-04-27T20:36:39.082697Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 245/256
+[2m2026-04-27T20:36:39.250465Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 50/256
+[2m2026-04-27T20:36:39.448799Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 54/256
+[2m2026-04-27T20:36:39.449166Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 62/256
+[2m2026-04-27T20:36:39.450954Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 63/256
+[2m2026-04-27T20:36:39.766480Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 253/256
+[2m2026-04-27T20:36:39.838346Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 59/256
+[2m2026-04-27T20:36:39.875987Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 255/256
+[2m2026-04-27T20:36:39.876798Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 55/256
+[2m2026-04-27T20:36:39.877292Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 51/256
+[2m2026-04-27T20:36:40.244598Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 61/256
+[2m2026-04-27T20:36:40.245589Z[0m [32m INFO[0m [2mobikpartitionner::partition[0m[2m:[0m counting kmers in partition 53/256
+      266.84 real      3776.35 user       115.80 sys
+          2423504896  maximum resident set size
+                   0  average shared memory size
+                   0  average unshared data size
+                   0  average unshared stack size
+              292303  page reclaims
+              132311  page faults
+                   0  swaps
+                   0  block input operations
+                   0  block output operations
+                   0  messages sent
+                   0  messages received
+                   0  signals received
+                4462  voluntary context switches
+             1991864  involuntary context switches
+      54933227607056  instructions retired
+      11271230983971  cycles elapsed
+          2210777320  peak memory footprint
diff --git a/docmd/implementation/mphf.md b/docmd/implementation/mphf.md
index 316308f..b7a6b05 100644
--- a/docmd/implementation/mphf.md
+++ b/docmd/implementation/mphf.md
@@ -1,6 +1,29 @@
-# MPHF selection — analysis in progress
+# MPHF selection — two-phase indexing architecture
 
-The choice of Minimal Perfect Hash Function for phase 6 is not yet settled. Three candidates were evaluated.
+## Indexing architecture
+
+Kmer indexing per partition proceeds in two phases. The separation is necessary because the exact number of unique kmers in a partition is not known until after counting and filtering.
+
+### Superkmer vs kmer counts
+
+The `SKFileMeta` sidecar written by `SKFileWriter` records `instances` (unique superkmers) and `length_sum` (total nucleotides). A superkmer of length L contains L − k + 1 kmers, so the kmer count per partition can be estimated as `length_sum − instances × (k − 1)`. This is an **overestimate** of unique kmers: two distinct superkmers (different flanking contexts, same minimizer) can share kmers. The exact count of unique kmers is only known after enumerating and deduplicating them.
+
+Note: two superkmers sharing a kmer necessarily share the same minimizer and therefore always land in the same partition — no kmer can appear in two different partitions.
+
+### Phase 1 — provisional index and spectrum
+
+1. Enumerate all kmers from the dereplicated superkmers of the partition.
+2. Build a provisional MPHF over this key set; capacity is pre-allocated from the sidecar estimate (slight overestimate, harmless).
+3. Accumulate counts: for each kmer in each superkmer, `count[MPHF(kmer)] += sk.count()`.
+4. Compute the kmer frequency spectrum (histogram: occurrences → number of kmers).
+5. Apply count filter (e.g. discard singletons). After filtering, the exact number of surviving kmers is known.
+6. Discard the provisional MPHF.
+
+### Phase 2 — definitive index
+
+Build a new MPHF over the filtered kmer set only, with the exact key count available. This is the persistent per-partition index used for all downstream operations (queries, set operations).
+
+---
 
 ## Candidates
 
@@ -8,31 +31,41 @@ The choice of Minimal Perfect Hash Function for phase 6 is not yet settled. Thre
 
 - ~3.7 bits/key; mature crate, used in production bioinformatics (Pufferfish, Piscem)
 - Parallel construction; well-tested with DNA kmer data at scale
-- Drawback: largest space footprint of the three
+- Drawback: largest space footprint; streaming construction (no exact count needed) was its main differentiator — irrelevant here since exact count is available at phase 2
 
 **ptr_hash** (PtrHash algorithm, Groot Koerkamp, SEA 2025):
 
 - ~2.4 bits/key; fastest queries (≥2.1× over alternatives, 8–12 ns/key for u64 in tight loops) and fastest construction (≥3.1×)
-- Theoretical foundation solid; paper and Rust crate from the same author
+- Requires exact key count at construction — available at phase 2
 - Drawback: published February 2025 — very young, no production track record
 
 **FMPHGO** (`ph` crate, Beling, ACM JEA 2023):
 
 - ~2.1 bits/key — most compact of the three; good query speed; parallelisable construction
 - More established than ptr_hash; actively maintained
-- Currently preferred candidate
+- Works well with overestimated capacity → natural fit for phase 1
+
+## MPHF choice per phase
+
+**Phase 1** (provisional, discarded after spectrum computation): FMPHGO. Tolerates overestimated capacity, compact, no need to optimise for query speed on a temporary structure.
+
+**Phase 2** (persistent, queried repeatedly): open between FMPHGO and ptr_hash. Exact key count is available, so both operate optimally. ptr_hash's query speed advantage (2.1–3.3×) is meaningful for the persistent index but carries the risk of a very young crate. FMPHGO is the conservative default; ptr_hash is worth revisiting once it has broader production use.
+
+boomphf is effectively eliminated: its space overhead is the largest and its streaming-construction advantage does not apply here.
+
+---
 
 ## Space at scale
 
-For 1 024 partitions × 100 M kmers/partition:
+For 1 024 partitions × 100 M kmers/partition (phase 2 index, after filtering):
 
-| MPHF    | bits/key | Total MPHF size |
-|---------|----------|-----------------|
-| boomphf | 3.7      | ~47 GB          |
-| ptr_hash | 2.4     | ~31 GB          |
-| FMPHGO  | 2.1      | ~27 GB          |
+| MPHF     | bits/key | Total MPHF size |
+|----------|----------|-----------------|
+| boomphf  | 3.7      | ~47 GB          |
+| ptr_hash | 2.4      | ~31 GB          |
+| FMPHGO   | 2.1      | ~27 GB          |
 
-In practice, partition sizes depend on the dataset. For a human genome at 30× coverage with p=10 (1 024 partitions), realistic partition sizes are 3–30 M kmers → 1–8 MB per MPHF, well within RAM.
+For a human genome at 30× coverage with 1 024 partitions, realistic partition sizes are 3–30 M unique kmers → 1–8 MB per phase-2 MPHF, well within RAM.
 
 ## On-disk and mmap considerations
 
@@ -42,7 +75,7 @@ No established Rust crate provides a natively on-disk MPHF. **SSHash** (Sparse a
 
 ## Open questions
 
-- Confirm actual partition sizes on representative metagenomic datasets before fixing the choice.
-- Evaluate whether ptr_hash's query speed advantage (2.1–3.3×) justifies adopting a crate that is less than a year old.
-- Assess rkyv integration cost for FMPHGO if true zero-copy mmap becomes necessary.
+- Confirm actual partition sizes and overestimation factor on representative metagenomic datasets.
+- Revisit ptr_hash for phase 2 once the crate has broader production track record.
+- Assess rkyv integration cost for FMPHGO if true zero-copy mmap becomes necessary for the persistent index.
 - Keep SSHash in mind if the indexing architecture is reconsidered at a higher level.
diff --git a/scripts/plot_spectrum.py b/scripts/plot_spectrum.py
new file mode 100644
index 0000000..2c7a37e
--- /dev/null
+++ b/scripts/plot_spectrum.py
@@ -0,0 +1,64 @@
+#!/usr/bin/env python3
+"""Plot kmer frequency spectrum from kmer_spectrum_raw.json (log-log scale)."""
+
+import json
+import sys
+import argparse
+import matplotlib.pyplot as plt
+
+
+def load_spectrum(path: str):
+    with open(path) as f:
+        data = json.load(f)
+    spectrum = data["spectrum"]
+    pairs = sorted((int(k), v) for k, v in spectrum.items() if v > 0)
+    counts = [x for x, _ in pairs]
+    freqs  = [y for _, y in pairs]
+    return counts, freqs, data.get("f0"), data.get("f1")
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Log-log kmer spectrum plot")
+    parser.add_argument("spectrum", nargs="?", default="kmer_spectrum_raw.json",
+                        help="Path to kmer_spectrum_raw.json")
+    parser.add_argument("-o", "--output", default=None,
+                        help="Save figure to file (PNG/SVG/PDF). Omit to display interactively.")
+    parser.add_argument("--max-count", type=int, default=None,
+                        help="Truncate x-axis at this count value")
+    args = parser.parse_args()
+
+    counts, freqs, f0, f1 = load_spectrum(args.spectrum)
+
+    if args.max_count:
+        pairs = [(c, f) for c, f in zip(counts, freqs) if c <= args.max_count]
+        counts, freqs = zip(*pairs) if pairs else ([], [])
+
+    fig, ax = plt.subplots(figsize=(9, 5))
+    ax.plot(counts, freqs, ".", markersize=2, linewidth=0.6, color="steelblue")
+    ax.set_xscale("log")
+    ax.set_yscale("log")
+    ax.set_xlabel("Repetition degree (count)", fontsize=12)
+    ax.set_ylabel("Number of distinct k-mers", fontsize=12)
+    ax.set_title("K-mer frequency spectrum", fontsize=13)
+
+    info = []
+    if f0 is not None:
+        info.append(f"F₀ = {f0:,}")
+    if f1 is not None:
+        info.append(f"F₁ = {f1:,}")
+    if info:
+        ax.text(0.98, 0.97, "  ".join(info), transform=ax.transAxes,
+                ha="right", va="top", fontsize=9, color="gray")
+
+    ax.grid(True, which="both", linestyle="--", linewidth=0.4, alpha=0.6)
+    fig.tight_layout()
+
+    if args.output:
+        fig.savefig(args.output, dpi=150)
+        print(f"Saved to {args.output}", file=sys.stderr)
+    else:
+        plt.show()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/src/Cargo.lock b/src/Cargo.lock
index db5c270..9e4a003 100644
--- a/src/Cargo.lock
+++ b/src/Cargo.lock
@@ -35,12 +35,39 @@ dependencies = [
  "as-slice",
 ]
 
+[[package]]
+name = "aligned-vec"
+version = "0.6.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dc890384c8602f339876ded803c97ad529f3842aba97f6392b3dba0dd171769b"
+dependencies = [
+ "equator",
+]
+
 [[package]]
 name = "allocator-api2"
 version = "0.2.21"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "683d7910e743518b0e34f1186f92494becacb047c7b6bf616c96772180fef923"
 
+[[package]]
+name = "ambassador"
+version = "0.4.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e68de4cdc6006162265d0957edb4a860fe4e711b1dc17a5746fd95f952f08285"
+dependencies = [
+ "itertools 0.10.5",
+ "proc-macro2",
+ "quote",
+ "syn 1.0.109",
+]
+
+[[package]]
+name = "anes"
+version = "0.1.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4b46cbb362ab8752921c97e041f5e366ee6297bd428a31275b9fcf1e380f7299"
+
 [[package]]
 name = "anes"
 version = "0.2.1"
@@ -103,6 +130,18 @@ version = "1.0.102"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7f202df86484c868dbad7eaa557ef785d5c66295e41b460ef922eca0723b842c"
 
+[[package]]
+name = "arbitrary-chunks"
+version = "0.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2ad8689a486416c401ea15715a4694de30054248ec627edbf31f49cb64ee4086"
+
+[[package]]
+name = "arrayvec"
+version = "0.7.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7c02d123df017efcdfbd739ef81735b36c5ba83ec3c59c80a9d7ecc718f92e50"
+
 [[package]]
 name = "as-slice"
 version = "0.2.1"
@@ -130,7 +169,7 @@ dependencies = [
  "miniz_oxide",
  "object",
  "rustc-demangle",
- "windows-link",
+ "windows-link 0.2.1",
 ]
 
 [[package]]
@@ -151,6 +190,12 @@ dependencies = [
  "thiserror 1.0.69",
 ]
 
+[[package]]
+name = "binout"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "222fb4925a15bea6a68075021910e03d6aa2d04951d71ff1d956190a551d738f"
+
 [[package]]
 name = "bitflags"
 version = "1.3.2"
@@ -163,6 +208,15 @@ version = "2.11.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c4512299f36f043ab09a583e57bceb5a5aab7a73db1805848e8fef3c9e8c78b3"
 
+[[package]]
+name = "bitm"
+version = "0.5.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "31468ea4a856000d83cb61960dfdc2980ecd96b15b61321c8c76cc96aea6e688"
+dependencies = [
+ "dyn_size_of",
+]
+
 [[package]]
 name = "bitvec"
 version = "1.0.1"
@@ -184,6 +238,16 @@ dependencies = [
  "generic-array",
 ]
 
+[[package]]
+name = "block-pseudorand"
+version = "0.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2097358495d244a0643746f4d13eedba4608137008cf9dec54e53a3b700115a6"
+dependencies = [
+ "chiapos-chacha8",
+ "nanorand",
+]
+
 [[package]]
 name = "bpaf"
 version = "0.9.25"
@@ -278,6 +342,15 @@ version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "613afe47fcd5fac7ccf1db93babcb082c5994d996f20b8b159f2ad1658eb5724"
 
+[[package]]
+name = "chiapos-chacha8"
+version = "0.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "33f8be573a85f6c2bc1b8e43834c07e32f95e489b914bf856c0549c3c269cd0a"
+dependencies = [
+ "rayon",
+]
+
 [[package]]
 name = "ciborium"
 version = "0.2.2"
@@ -336,7 +409,7 @@ dependencies = [
  "heck",
  "proc-macro2",
  "quote",
- "syn",
+ "syn 2.0.117",
 ]
 
 [[package]]
@@ -351,6 +424,27 @@ version = "1.0.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1d07550c9036bf2ae0c684c4297d503f838287c83c53686d05370d0e139ae570"
 
+[[package]]
+name = "combine"
+version = "4.6.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ba5a308b75df32fe02788e748662718f03fde005016435c444eea572398219fd"
+dependencies = [
+ "bytes",
+ "memchr",
+]
+
+[[package]]
+name = "common_traits"
+version = "0.12.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "65d0a1296e8d359cb197a8f8289f3d3f77cdb67f1a83d0aeb0820a5b7aea4058"
+dependencies = [
+ "anyhow",
+ "half",
+ "impl-tools",
+]
+
 [[package]]
 name = "core-foundation-sys"
 version = "0.8.7"
@@ -384,13 +478,49 @@ dependencies = [
  "cfg-if",
 ]
 
+[[package]]
+name = "criterion"
+version = "0.5.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f2b12d017a929603d80db1831cd3a24082f8137ce19c69e6447f54f5fc8d692f"
+dependencies = [
+ "anes 0.1.6",
+ "cast",
+ "ciborium",
+ "clap",
+ "criterion-plot",
+ "is-terminal",
+ "itertools 0.10.5",
+ "num-traits",
+ "once_cell",
+ "oorandom",
+ "plotters",
+ "rayon",
+ "regex",
+ "serde",
+ "serde_derive",
+ "serde_json",
+ "tinytemplate",
+ "walkdir",
+]
+
+[[package]]
+name = "criterion-plot"
+version = "0.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6b50826342786a51a89e2da3a28f1c32b06e387201bc2d19791f622c673706b1"
+dependencies = [
+ "cast",
+ "itertools 0.10.5",
+]
+
 [[package]]
 name = "criterion2"
 version = "3.0.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "861a56bb48e3ba7a2a38580a91577e17d90db946649f5c342fd74ba864180def"
 dependencies = [
- "anes",
+ "anes 0.2.1",
  "bpaf",
  "cast",
  "ciborium",
@@ -461,6 +591,41 @@ dependencies = [
  "cfg-if",
 ]
 
+[[package]]
+name = "darling"
+version = "0.21.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9cdf337090841a411e2a7f3deb9187445851f91b309c0c0a29e05f74a00a48c0"
+dependencies = [
+ "darling_core",
+ "darling_macro",
+]
+
+[[package]]
+name = "darling_core"
+version = "0.21.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1247195ecd7e3c85f83c8d2a366e4210d588e802133e1e355180a9870b517ea4"
+dependencies = [
+ "fnv",
+ "ident_case",
+ "proc-macro2",
+ "quote",
+ "strsim",
+ "syn 2.0.117",
+]
+
+[[package]]
+name = "darling_macro"
+version = "0.21.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d38308df82d1080de0afee5d069fa14b0326a88c14f15c5ccda35b4a6c414c81"
+dependencies = [
+ "darling_core",
+ "quote",
+ "syn 2.0.117",
+]
+
 [[package]]
 name = "debugid"
 version = "0.8.0"
@@ -470,6 +635,29 @@ dependencies = [
  "uuid",
 ]
 
+[[package]]
+name = "derivative"
+version = "2.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fcc3dd5e9e9c0b295d6e1e4d811fb6f157d5ffd784b8d202fc62eac8035a770b"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 1.0.109",
+]
+
+[[package]]
+name = "derive_setters"
+version = "0.1.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b7e6f6fa1f03c14ae082120b84b3c7fbd7b8588d924cf2d7c3daf9afd49df8b9"
+dependencies = [
+ "darling",
+ "proc-macro2",
+ "quote",
+ "syn 2.0.117",
+]
+
 [[package]]
 name = "digest"
 version = "0.10.7"
@@ -488,15 +676,117 @@ checksum = "97369cbbc041bc366949bc74d34658d6cda5621039731c6310521892a3a20ae0"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn",
+ "syn 2.0.117",
 ]
 
+[[package]]
+name = "dsi-progress-logger"
+version = "0.8.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ac3969f942da74913b951e19784a2c0b61a2b0d11c2887f6eb3b9b34775b31bf"
+dependencies = [
+ "log",
+ "num-format",
+ "pluralizer",
+ "sysinfo 0.36.1",
+]
+
+[[package]]
+name = "dyn_size_of"
+version = "0.4.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4a742b95783b1f45b900129082cbc47717b6a77ee8d17eea70a8ea62462f5de3"
+
 [[package]]
 name = "either"
 version = "1.15.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "48c757948c5ede0e46177b7add2e67155f70e33c07fea8284df6576da70b3719"
 
+[[package]]
+name = "enum-as-inner"
+version = "0.6.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a1e6a265c649f3f5979b601d26f1d05ada116434c87741c9493cb56218f76cbc"
+dependencies = [
+ "heck",
+ "proc-macro2",
+ "quote",
+ "syn 2.0.117",
+]
+
+[[package]]
+name = "env_filter"
+version = "1.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "32e90c2accc4b07a8456ea0debdc2e7587bdd890680d71173a15d4ae604f6eef"
+dependencies = [
+ "log",
+ "regex",
+]
+
+[[package]]
+name = "env_logger"
+version = "0.11.10"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0621c04f2196ac3f488dd583365b9c09be011a4ab8b9f37248ffcc8f6198b56a"
+dependencies = [
+ "anstream",
+ "anstyle",
+ "env_filter",
+ "jiff",
+ "log",
+]
+
+[[package]]
+name = "epserde"
+version = "0.11.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d8dffc01a379703ad5178f47a22aa532f5811b3ef45979ccd66b79da9856770b"
+dependencies = [
+ "anyhow",
+ "bitflags 2.11.1",
+ "common_traits",
+ "epserde-derive",
+ "mem_dbg",
+ "mmap-rs",
+ "sealed",
+ "thiserror 2.0.18",
+ "xxhash-rust",
+]
+
+[[package]]
+name = "epserde-derive"
+version = "0.11.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6fc2ceb99084df049085a5bdd15e3b2f7275111e2b9029f95fb01a3a06cf1b13"
+dependencies = [
+ "proc-macro-error",
+ "proc-macro2",
+ "quote",
+ "syn 2.0.117",
+]
+
+[[package]]
+name = "equator"
+version = "0.4.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4711b213838dfee0117e3be6ac926007d7f433d7bbe33595975d4190cb07e6fc"
+dependencies = [
+ "equator-macro",
+]
+
+[[package]]
+name = "equator-macro"
+version = "0.4.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "44f23cf4b44bfce11a86ace86f8a73ffdec849c9fd00a386a53d278bd9e81fb3"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.117",
+]
+
 [[package]]
 name = "equivalent"
 version = "1.0.2"
@@ -513,6 +803,12 @@ dependencies = [
  "windows-sys 0.61.2",
 ]
 
+[[package]]
+name = "fallible-iterator"
+version = "0.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2acce4a10f12dc2fb14a218589d4f1f62ef011b2d0cc4b3cb1bba8e94da14649"
+
 [[package]]
 name = "fastrand"
 version = "2.4.1"
@@ -667,6 +963,12 @@ version = "0.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea"
 
+[[package]]
+name = "hermit-abi"
+version = "0.5.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fc0fef456e4baa96da950455cd02c081ca953b141298e41db3fc7e36b1da849c"
+
 [[package]]
 name = "icu_collections"
 version = "2.2.0"
@@ -749,6 +1051,12 @@ dependencies = [
  "zerovec",
 ]
 
+[[package]]
+name = "ident_case"
+version = "1.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b9e0384b61958566e926dc50660321d12159025e767c18e043daf26b70104c39"
+
 [[package]]
 name = "idna"
 version = "1.1.0"
@@ -770,6 +1078,30 @@ dependencies = [
  "icu_properties",
 ]
 
+[[package]]
+name = "impl-tools"
+version = "0.11.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0ae314a99afb5821e2fda288387546d4a04aace674551e854e6216b892ec3208"
+dependencies = [
+ "autocfg",
+ "impl-tools-lib",
+ "proc-macro-error2",
+ "syn 2.0.117",
+]
+
+[[package]]
+name = "impl-tools-lib"
+version = "0.11.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ab699036df31c1f7d3561bfa6e9cb9bc3bb0fd2e2cd9bf121c31cb961d049ddf"
+dependencies = [
+ "proc-macro-error2",
+ "proc-macro2",
+ "quote",
+ "syn 2.0.117",
+]
+
 [[package]]
 name = "indexmap"
 version = "2.14.0"
@@ -789,12 +1121,32 @@ dependencies = [
  "cfb",
 ]
 
+[[package]]
+name = "is-terminal"
+version = "0.4.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3640c1c38b8e4e43584d8df18be5fc6b0aa314ce6ebf51b53313d4306cca8e46"
+dependencies = [
+ "hermit-abi",
+ "libc",
+ "windows-sys 0.61.2",
+]
+
 [[package]]
 name = "is_terminal_polyfill"
 version = "1.70.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a6cb138bb79a146c1bd460005623e142ef0181e3d0219cb493e02f7d08a35695"
 
+[[package]]
+name = "itertools"
+version = "0.10.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b0fd2260e829bddf4cb6ea802289de2f86d6a7a690192fbe91b3f46e0f2c8473"
+dependencies = [
+ "either",
+]
+
 [[package]]
 name = "itertools"
 version = "0.12.1"
@@ -804,12 +1156,62 @@ dependencies = [
  "either",
 ]
 
+[[package]]
+name = "itertools"
+version = "0.14.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2b192c782037fadd9cfa75548310488aabdbf3d2da73885b31bd0abd03351285"
+dependencies = [
+ "either",
+]
+
 [[package]]
 name = "itoa"
 version = "1.0.18"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8f42a60cbdf9a97f5d2305f08a87dc4e09308d1276d28c869c684d7777685682"
 
+[[package]]
+name = "jiff"
+version = "0.2.24"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f00b5dbd620d61dfdcb6007c9c1f6054ebd75319f163d886a9055cec1155073d"
+dependencies = [
+ "jiff-static",
+ "jiff-tzdb-platform",
+ "log",
+ "portable-atomic",
+ "portable-atomic-util",
+ "serde_core",
+ "windows-sys 0.61.2",
+]
+
+[[package]]
+name = "jiff-static"
+version = "0.2.24"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e000de030ff8022ea1da3f466fbb0f3a809f5e51ed31f6dd931c35181ad8e6d7"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.117",
+]
+
+[[package]]
+name = "jiff-tzdb"
+version = "0.1.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c900ef84826f1338a557697dc8fc601df9ca9af4ac137c7fb61d4c6f2dfd3076"
+
+[[package]]
+name = "jiff-tzdb-platform"
+version = "0.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "875a5a69ac2bab1a891711cf5eccbec1ce0341ea805560dcd90b7a2e925132e8"
+dependencies = [
+ "jiff-tzdb",
+]
+
 [[package]]
 name = "jobserver"
 version = "0.1.34"
@@ -830,12 +1232,44 @@ dependencies = [
  "wasm-bindgen",
 ]
 
+[[package]]
+name = "lambert_w"
+version = "1.2.34"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f5f0846ee4f0299ca4c5b9ca06ff55cf88b3430a763bf591474cc734479c9b24"
+dependencies = [
+ "num-complex",
+ "num-traits",
+]
+
 [[package]]
 name = "lazy_static"
 version = "1.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "bbd2bcb4c963f2ddae06a2efc7e9f3591312473c50c6685e1f298068316e66fe"
 
+[[package]]
+name = "lender"
+version = "0.4.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c150e24afda8f769930a339cb5ad6e182101fdf1165c30c157b33ce5050fd7ad"
+dependencies = [
+ "fallible-iterator",
+ "lender-derive",
+ "stable_try_trait_v2",
+]
+
+[[package]]
+name = "lender-derive"
+version = "0.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d074a297c82222d442171bad4f392fef93d35fb31e24a115f605a0c907ce0af9"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.117",
+]
+
 [[package]]
 name = "libc"
 version = "0.2.185"
@@ -898,6 +1332,15 @@ dependencies = [
  "hashbrown 0.15.5",
 ]
 
+[[package]]
+name = "mach2"
+version = "0.4.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d640282b302c0bb0a2a8e0233ead9035e3bed871f0b7e81fe4a1ec829765db44"
+dependencies = [
+ "libc",
+]
+
 [[package]]
 name = "matchers"
 version = "0.2.0"
@@ -907,6 +1350,28 @@ dependencies = [
  "regex-automata",
 ]
 
+[[package]]
+name = "mem_dbg"
+version = "0.3.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "728cc9dc97593cd22f7bc81fbef70a2d391d7a9a855e7d658b653318124a6cf0"
+dependencies = [
+ "bitflags 2.11.1",
+ "mem_dbg-derive",
+ "mmap-rs",
+]
+
+[[package]]
+name = "mem_dbg-derive"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d84f40c93b0508d5565db79a814d02d5b2545967205ce44be211592aafa34d6c"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.117",
+]
+
 [[package]]
 name = "memchr"
 version = "2.8.0"
@@ -922,6 +1387,15 @@ dependencies = [
  "libc",
 ]
 
+[[package]]
+name = "memoffset"
+version = "0.7.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5de893c32cde5f383baa4c04c5d6dbdd735cfd4a794b0debdb2bb1b421da5ff4"
+dependencies = [
+ "autocfg",
+]
+
 [[package]]
 name = "miniz_oxide"
 version = "0.8.9"
@@ -932,12 +1406,35 @@ dependencies = [
  "simd-adler32",
 ]
 
+[[package]]
+name = "mmap-rs"
+version = "0.6.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "86968d85441db75203c34deefd0c88032f275aaa85cee19a1dcfff6ae9df56da"
+dependencies = [
+ "bitflags 1.3.2",
+ "combine",
+ "libc",
+ "mach2",
+ "nix 0.26.4",
+ "sysctl",
+ "thiserror 1.0.69",
+ "widestring",
+ "windows 0.48.0",
+]
+
 [[package]]
 name = "multimap"
 version = "0.10.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1d87ecb2933e8aeadb3e3a02b828fed80a7528047e68b4f424523a0981a3a084"
 
+[[package]]
+name = "nanorand"
+version = "0.6.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "729eb334247daa1803e0a094d0a5c55711b85571179f5ec6e53eccfdf7008958"
+
 [[package]]
 name = "niffler"
 version = "2.7.0"
@@ -976,6 +1473,8 @@ dependencies = [
  "bitflags 1.3.2",
  "cfg-if",
  "libc",
+ "memoffset",
+ "pin-utils",
 ]
 
 [[package]]
@@ -1017,6 +1516,25 @@ dependencies = [
  "windows-sys 0.61.2",
 ]
 
+[[package]]
+name = "num-complex"
+version = "0.4.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "73f88a1307638156682bada9d7604135552957b7818057dcef22705b4d509495"
+dependencies = [
+ "num-traits",
+]
+
+[[package]]
+name = "num-format"
+version = "0.4.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a652d9771a63711fd3c3deb670acfbe5c30a4072e664d7a3bf5a9e1056ac72c3"
+dependencies = [
+ "arrayvec",
+ "itoa",
+]
+
 [[package]]
 name = "num-traits"
 version = "0.2.19"
@@ -1055,14 +1573,16 @@ dependencies = [
 name = "obikpartitionner"
 version = "0.1.0"
 dependencies = [
+ "memmap2",
  "niffler 3.0.0",
  "obikseq",
  "obiskio",
+ "ph",
  "rayon",
  "remove_dir_all",
  "serde",
  "serde_json",
- "sysinfo",
+ "sysinfo 0.33.1",
  "tracing",
 ]
 
@@ -1125,6 +1645,25 @@ dependencies = [
  "tempfile",
 ]
 
+[[package]]
+name = "objc2-core-foundation"
+version = "0.3.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2a180dd8642fa45cdb7dd721cd4c11b1cadd4929ce112ebd8b9f5803cc79d536"
+dependencies = [
+ "bitflags 2.11.1",
+]
+
+[[package]]
+name = "objc2-io-kit"
+version = "0.3.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "33fafba39597d6dc1fb709123dfa8289d39406734be322956a69f0931c73bb15"
+dependencies = [
+ "libc",
+ "objc2-core-foundation",
+]
+
 [[package]]
 name = "object"
 version = "0.37.3"
@@ -1172,9 +1711,15 @@ dependencies = [
  "libc",
  "redox_syscall",
  "smallvec",
- "windows-link",
+ "windows-link 0.2.1",
 ]
 
+[[package]]
+name = "partition"
+version = "0.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "947f833aaa585cf12b8ec7c0476c98784c49f33b861376ffc84ed92adebf2aba"
+
 [[package]]
 name = "percent-encoding"
 version = "2.3.2"
@@ -1191,18 +1736,96 @@ dependencies = [
  "indexmap",
 ]
 
+[[package]]
+name = "ph"
+version = "0.11.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a447f203c7254ebb06aa4f111480e821debb361e80fb4d760554a8460f236550"
+dependencies = [
+ "aligned-vec",
+ "arrayvec",
+ "binout",
+ "bitm",
+ "dyn_size_of",
+ "epserde",
+ "mem_dbg",
+ "rayon",
+ "seedable_hash",
+ "sux",
+ "voracious_radix_sort",
+]
+
 [[package]]
 name = "pin-project-lite"
 version = "0.2.17"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a89322df9ebe1c1578d689c92318e070967d1042b512afbe49518723f4e6d5cd"
 
+[[package]]
+name = "pin-utils"
+version = "0.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8b870d8c151b6f2fb93e84a13146138f05d02ed11c7e7c54f8826aaaf7c9f184"
+
 [[package]]
 name = "pkg-config"
 version = "0.3.33"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "19f132c84eca552bf34cab8ec81f1c1dcc229b811638f9d283dceabe58c5569e"
 
+[[package]]
+name = "plotters"
+version = "0.3.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5aeb6f403d7a4911efb1e33402027fc44f29b5bf6def3effcc22d7bb75f2b747"
+dependencies = [
+ "num-traits",
+ "plotters-backend",
+ "plotters-svg",
+ "wasm-bindgen",
+ "web-sys",
+]
+
+[[package]]
+name = "plotters-backend"
+version = "0.3.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "df42e13c12958a16b3f7f4386b9ab1f3e7933914ecea48da7139435263a4172a"
+
+[[package]]
+name = "plotters-svg"
+version = "0.3.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "51bae2ac328883f7acdfea3d66a7c35751187f870bc81f94563733a154d7a670"
+dependencies = [
+ "plotters-backend",
+]
+
+[[package]]
+name = "pluralizer"
+version = "0.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4b3eba432a00a1f6c16f39147847a870e94e2e9b992759b503e330efec778cbe"
+dependencies = [
+ "once_cell",
+ "regex",
+]
+
+[[package]]
+name = "portable-atomic"
+version = "1.13.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c33a9471896f1c69cecef8d20cbe2f7accd12527ce60845ff44c153bb2a21b49"
+
+[[package]]
+name = "portable-atomic-util"
+version = "0.2.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c2a106d1259c23fac8e543272398ae0e3c0b8d33c88ed73d0cc71b0f1d902618"
+dependencies = [
+ "portable-atomic",
+]
+
 [[package]]
 name = "potential_utf"
 version = "0.1.5"
@@ -1236,6 +1859,15 @@ dependencies = [
  "thiserror 1.0.69",
 ]
 
+[[package]]
+name = "ppv-lite86"
+version = "0.2.21"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "85eae3c4ed2f50dcfe72643da4befc30deadb458a9b590d720cde2f2b1e97da9"
+dependencies = [
+ "zerocopy",
+]
+
 [[package]]
 name = "prettyplease"
 version = "0.2.37"
@@ -1243,7 +1875,52 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "479ca8adacdd7ce8f1fb39ce9ecccbfe93a3f1344b3d0d97f20bc0196208f62b"
 dependencies = [
  "proc-macro2",
- "syn",
+ "syn 2.0.117",
+]
+
+[[package]]
+name = "proc-macro-error"
+version = "1.0.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "da25490ff9892aab3fcf7c36f08cfb902dd3e71ca0f9f9517bea02a73a5ce38c"
+dependencies = [
+ "proc-macro-error-attr",
+ "proc-macro2",
+ "quote",
+ "syn 1.0.109",
+ "version_check",
+]
+
+[[package]]
+name = "proc-macro-error-attr"
+version = "1.0.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a1be40180e52ecc98ad80b184934baf3d0d29f979574e439af5a55274b35f869"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "version_check",
+]
+
+[[package]]
+name = "proc-macro-error-attr2"
+version = "2.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "96de42df36bb9bba5542fe9f1a054b8cc87e172759a1868aa05c1f3acc89dfc5"
+dependencies = [
+ "proc-macro2",
+ "quote",
+]
+
+[[package]]
+name = "proc-macro-error2"
+version = "2.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "11ec05c52be0a07b08061f7dd003e7d7092e0472bc731b4af7bb1ef876109802"
+dependencies = [
+ "proc-macro-error-attr2",
+ "proc-macro2",
+ "quote",
 ]
 
 [[package]]
@@ -1273,7 +1950,7 @@ checksum = "22505a5c94da8e3b7c2996394d1c933236c4d743e81a410bcca4e6989fc066a4"
 dependencies = [
  "bytes",
  "heck",
- "itertools",
+ "itertools 0.12.1",
  "log",
  "multimap",
  "once_cell",
@@ -1282,7 +1959,7 @@ dependencies = [
  "prost",
  "prost-types",
  "regex",
- "syn",
+ "syn 2.0.117",
  "tempfile",
 ]
 
@@ -1293,10 +1970,10 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "81bddcdb20abf9501610992b6759a4c888aef7d1a7247ef75e2404275ac24af1"
 dependencies = [
  "anyhow",
- "itertools",
+ "itertools 0.12.1",
  "proc-macro2",
  "quote",
- "syn",
+ "syn 2.0.117",
 ]
 
 [[package]]
@@ -1329,6 +2006,35 @@ version = "0.7.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "dc33ff2d4973d518d823d61aa239014831e521c75da58e3df4840d3f47749d09"
 
+[[package]]
+name = "rand"
+version = "0.9.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "44c5af06bb1b7d3216d91932aed5265164bf384dc89cd6ba05cf59a35f5f76ea"
+dependencies = [
+ "rand_chacha",
+ "rand_core",
+]
+
+[[package]]
+name = "rand_chacha"
+version = "0.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d3022b5f1df60f26e1ffddd6c66e8aa15de382ae63b3a0c1bfc0e4d3e3f325cb"
+dependencies = [
+ "ppv-lite86",
+ "rand_core",
+]
+
+[[package]]
+name = "rand_core"
+version = "0.9.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "76afc826de14238e6e8c374ddcc1fa19e374fd8dd986b0d2af0d02377261d83c"
+dependencies = [
+ "getrandom 0.3.4",
+]
+
 [[package]]
 name = "rayon"
 version = "1.12.0"
@@ -1349,6 +2055,21 @@ dependencies = [
  "crossbeam-utils",
 ]
 
+[[package]]
+name = "rdst"
+version = "0.20.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6e7970b4e577b76a96d5e56b5f6662b66d1a4e1f5bb026ee118fc31b373c2752"
+dependencies = [
+ "arbitrary-chunks",
+ "block-pseudorand",
+ "criterion",
+ "partition",
+ "rayon",
+ "tikv-jemallocator",
+ "voracious_radix_sort",
+]
+
 [[package]]
 name = "redox_syscall"
 version = "0.5.18"
@@ -1490,6 +2211,23 @@ version = "1.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49"
 
+[[package]]
+name = "sealed"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "22f968c5ea23d555e670b449c1c5e7b2fc399fdaec1d304a17cd48e288abc107"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.117",
+]
+
+[[package]]
+name = "seedable_hash"
+version = "0.2.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ba2a159211665e29bbf5a2fbb42da50dd6eadff23eef7a6a7ae4a9b0a7cd0152"
+
 [[package]]
 name = "serde"
 version = "1.0.228"
@@ -1517,7 +2255,7 @@ checksum = "d540f220d3187173da220f885ab66608367b6574e925011a9353e4badda91d79"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn",
+ "syn 2.0.117",
 ]
 
 [[package]]
@@ -1577,6 +2315,12 @@ version = "1.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6ce2be8dc25455e1f91df71bfa12ad37d7af1092ae736f3a6cd0e37bc7810596"
 
+[[package]]
+name = "stable_try_trait_v2"
+version = "1.75.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1c4e48411f4db8ccca0470bfb67e3bb821af4227d455aa147917d8d109be0d13"
+
 [[package]]
 name = "strsim"
 version = "0.11.1"
@@ -1589,6 +2333,47 @@ version = "2.6.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "13c2bddecc57b384dee18652358fb23172facb8a2c51ccc10d74c157bdea3292"
 
+[[package]]
+name = "sux"
+version = "0.10.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "29949eff4a64e05149a5147f1695fd8576c990504a217f28391c09e007d831dc"
+dependencies = [
+ "ambassador",
+ "anyhow",
+ "arbitrary-chunks",
+ "bitflags 2.11.1",
+ "clap",
+ "common_traits",
+ "crossbeam-channel",
+ "derivative",
+ "derive_setters",
+ "dsi-progress-logger",
+ "env_logger",
+ "epserde",
+ "fallible-iterator",
+ "flate2",
+ "impl-tools",
+ "itertools 0.14.0",
+ "jiff",
+ "lambert_w",
+ "lender",
+ "libc",
+ "log",
+ "mem_dbg",
+ "rand",
+ "rayon",
+ "rdst",
+ "sync-cell-slice",
+ "tempfile",
+ "thiserror 2.0.18",
+ "thread-priority",
+ "value-traits",
+ "xxhash-rust",
+ "zerocopy",
+ "zstd",
+]
+
 [[package]]
 name = "symbolic-common"
 version = "12.18.3"
@@ -1612,6 +2397,17 @@ dependencies = [
  "symbolic-common",
 ]
 
+[[package]]
+name = "syn"
+version = "1.0.109"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "72b64191b275b66ffe2469e8af2c1cfe3bafa67b529ead792a6d0160888b4237"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
 [[package]]
 name = "syn"
 version = "2.0.117"
@@ -1623,6 +2419,12 @@ dependencies = [
  "unicode-ident",
 ]
 
+[[package]]
+name = "sync-cell-slice"
+version = "0.9.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7cf9ace719a3856838781680d5d677c612e01a0bc0b7b1ded355057ca5015997"
+
 [[package]]
 name = "synstructure"
 version = "0.13.2"
@@ -1631,7 +2433,21 @@ checksum = "728a70f3dbaf5bab7f0c4b1ac8d7ae5ea60a4b5549c8a5914361c99147a709d2"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn",
+ "syn 2.0.117",
+]
+
+[[package]]
+name = "sysctl"
+version = "0.5.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ec7dddc5f0fee506baf8b9fdb989e242f17e4b11c61dfbb0635b705217199eea"
+dependencies = [
+ "bitflags 2.11.1",
+ "byteorder",
+ "enum-as-inner",
+ "libc",
+ "thiserror 1.0.69",
+ "walkdir",
 ]
 
 [[package]]
@@ -1645,7 +2461,21 @@ dependencies = [
  "memchr",
  "ntapi",
  "rayon",
- "windows",
+ "windows 0.57.0",
+]
+
+[[package]]
+name = "sysinfo"
+version = "0.36.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "252800745060e7b9ffb7b2badbd8b31cfa4aa2e61af879d0a3bf2a317c20217d"
+dependencies = [
+ "libc",
+ "memchr",
+ "ntapi",
+ "objc2-core-foundation",
+ "objc2-io-kit",
+ "windows 0.61.3",
 ]
 
 [[package]]
@@ -1693,7 +2523,7 @@ checksum = "4fee6c4efc90059e10f81e6d42c60a18f76588c3d74cb83a0b242a2b6c7504c1"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn",
+ "syn 2.0.117",
 ]
 
 [[package]]
@@ -1704,7 +2534,21 @@ checksum = "ebc4ee7f67670e9b64d05fa4253e753e016c6c95ff35b89b7941d6b856dec1d5"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn",
+ "syn 2.0.117",
+]
+
+[[package]]
+name = "thread-priority"
+version = "3.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2210811179577da3d54eb69ab0b50490ee40491a25d95b8c6011ba40771cb721"
+dependencies = [
+ "bitflags 2.11.1",
+ "cfg-if",
+ "libc",
+ "log",
+ "rustversion",
+ "windows 0.61.3",
 ]
 
 [[package]]
@@ -1716,6 +2560,26 @@ dependencies = [
  "cfg-if",
 ]
 
+[[package]]
+name = "tikv-jemalloc-sys"
+version = "0.5.4+5.3.0-patched"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9402443cb8fd499b6f327e40565234ff34dbda27460c5b47db0db77443dd85d1"
+dependencies = [
+ "cc",
+ "libc",
+]
+
+[[package]]
+name = "tikv-jemallocator"
+version = "0.5.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "965fe0c26be5c56c94e38ba547249074803efd52adfb66de62107d95aab3eaca"
+dependencies = [
+ "libc",
+ "tikv-jemalloc-sys",
+]
+
 [[package]]
 name = "tinystr"
 version = "0.8.3"
@@ -1726,6 +2590,16 @@ dependencies = [
  "zerovec",
 ]
 
+[[package]]
+name = "tinytemplate"
+version = "1.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "be4d6b5f19ff7664e8c98d03e2139cb510db9b0a60b55f8e8709b689d939b6bc"
+dependencies = [
+ "serde",
+ "serde_json",
+]
+
 [[package]]
 name = "tracing"
 version = "0.1.44"
@@ -1745,7 +2619,7 @@ checksum = "7490cfa5ec963746568740651ac6781f701c9c5ea257c58e057f3ba8cf69e8da"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn",
+ "syn 2.0.117",
 ]
 
 [[package]]
@@ -1861,12 +2735,41 @@ version = "0.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ba73ea9cf16a25df0c8caa16c51acb937d5712a8429db78a3ee29d5dcacd3a65"
 
+[[package]]
+name = "value-traits"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "17e73c7053d8fa8e9c3c6b16c32d079ed5642a7156514820486a9c4e109cf48d"
+dependencies = [
+ "value-traits-derive",
+]
+
+[[package]]
+name = "value-traits-derive"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0d301d1ee4b3eced3e73aa5740a303c7e068f1d4450c5dae4c8cf6bfa266954f"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.117",
+]
+
 [[package]]
 name = "version_check"
 version = "0.9.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0b928f33d975fc6ad9f86c8f283853ad26bdd5b10b7f1542aa2fa15e2289105a"
 
+[[package]]
+name = "voracious_radix_sort"
+version = "1.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "446e7ffcb6c27a71d05af7e51ef2ee5b71c48424b122a832f2439651e1914899"
+dependencies = [
+ "rayon",
+]
+
 [[package]]
 name = "walkdir"
 version = "2.5.0"
@@ -1924,7 +2827,7 @@ dependencies = [
  "bumpalo",
  "proc-macro2",
  "quote",
- "syn",
+ "syn 2.0.117",
  "wasm-bindgen-shared",
 ]
 
@@ -1937,6 +2840,16 @@ dependencies = [
  "unicode-ident",
 ]
 
+[[package]]
+name = "web-sys"
+version = "0.3.95"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4f2dfbb17949fa2088e5d39408c48368947b86f7834484e87b73de55bc14d97d"
+dependencies = [
+ "js-sys",
+ "wasm-bindgen",
+]
+
 [[package]]
 name = "webpki-roots"
 version = "0.26.11"
@@ -1955,6 +2868,12 @@ dependencies = [
  "rustls-pki-types",
 ]
 
+[[package]]
+name = "widestring"
+version = "1.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "72069c3113ab32ab29e5584db3c6ec55d416895e60715417b5b883a357c3e471"
+
 [[package]]
 name = "winapi"
 version = "0.3.9"
@@ -1986,14 +2905,45 @@ version = "0.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"
 
+[[package]]
+name = "windows"
+version = "0.48.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e686886bc078bc1b0b600cac0147aadb815089b6e4da64016cbd754b6342700f"
+dependencies = [
+ "windows-targets 0.48.5",
+]
+
 [[package]]
 name = "windows"
 version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "12342cb4d8e3b046f3d80effd474a7a02447231330ef77d71daa6fbc40681143"
 dependencies = [
- "windows-core",
- "windows-targets",
+ "windows-core 0.57.0",
+ "windows-targets 0.52.6",
+]
+
+[[package]]
+name = "windows"
+version = "0.61.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9babd3a767a4c1aef6900409f85f5d53ce2544ccdfaa86dad48c91782c6d6893"
+dependencies = [
+ "windows-collections",
+ "windows-core 0.61.2",
+ "windows-future",
+ "windows-link 0.1.3",
+ "windows-numerics",
+]
+
+[[package]]
+name = "windows-collections"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3beeceb5e5cfd9eb1d76b381630e82c4241ccd0d27f1a39ed41b2760b255c5e8"
+dependencies = [
+ "windows-core 0.61.2",
 ]
 
 [[package]]
@@ -2002,10 +2952,34 @@ version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d2ed2439a290666cd67ecce2b0ffaad89c2a56b976b736e6ece670297897832d"
 dependencies = [
- "windows-implement",
- "windows-interface",
- "windows-result",
- "windows-targets",
+ "windows-implement 0.57.0",
+ "windows-interface 0.57.0",
+ "windows-result 0.1.2",
+ "windows-targets 0.52.6",
+]
+
+[[package]]
+name = "windows-core"
+version = "0.61.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c0fdd3ddb90610c7638aa2b3a3ab2904fb9e5cdbecc643ddb3647212781c4ae3"
+dependencies = [
+ "windows-implement 0.60.2",
+ "windows-interface 0.59.3",
+ "windows-link 0.1.3",
+ "windows-result 0.3.4",
+ "windows-strings",
+]
+
+[[package]]
+name = "windows-future"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fc6a41e98427b19fe4b73c550f060b59fa592d7d686537eebf9385621bfbad8e"
+dependencies = [
+ "windows-core 0.61.2",
+ "windows-link 0.1.3",
+ "windows-threading",
 ]
 
 [[package]]
@@ -2016,7 +2990,18 @@ checksum = "9107ddc059d5b6fbfbffdfa7a7fe3e22a226def0b2608f72e9d552763d3e1ad7"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn",
+ "syn 2.0.117",
+]
+
+[[package]]
+name = "windows-implement"
+version = "0.60.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "053e2e040ab57b9dc951b72c264860db7eb3b0200ba345b4e4c3b14f67855ddf"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.117",
 ]
 
 [[package]]
@@ -2027,22 +3012,67 @@ checksum = "29bee4b38ea3cde66011baa44dba677c432a78593e202392d1e9070cf2a7fca7"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn",
+ "syn 2.0.117",
 ]
 
+[[package]]
+name = "windows-interface"
+version = "0.59.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3f316c4a2570ba26bbec722032c4099d8c8bc095efccdc15688708623367e358"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.117",
+]
+
+[[package]]
+name = "windows-link"
+version = "0.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5e6ad25900d524eaabdbbb96d20b4311e1e7ae1699af4fb28c17ae66c80d798a"
+
 [[package]]
 name = "windows-link"
 version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f0805222e57f7521d6a62e36fa9163bc891acd422f971defe97d64e70d0a4fe5"
 
+[[package]]
+name = "windows-numerics"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9150af68066c4c5c07ddc0ce30421554771e528bde427614c61038bc2c92c2b1"
+dependencies = [
+ "windows-core 0.61.2",
+ "windows-link 0.1.3",
+]
+
 [[package]]
 name = "windows-result"
 version = "0.1.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "5e383302e8ec8515204254685643de10811af0ed97ea37210dc26fb0032647f8"
 dependencies = [
- "windows-targets",
+ "windows-targets 0.52.6",
+]
+
+[[package]]
+name = "windows-result"
+version = "0.3.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "56f42bd332cc6c8eac5af113fc0c1fd6a8fd2aa08a0119358686e5160d0586c6"
+dependencies = [
+ "windows-link 0.1.3",
+]
+
+[[package]]
+name = "windows-strings"
+version = "0.4.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "56e6c93f3a0c3b36176cb1327a4958a0353d5d166c2a35cb268ace15e91d3b57"
+dependencies = [
+ "windows-link 0.1.3",
 ]
 
 [[package]]
@@ -2051,7 +3081,7 @@ version = "0.52.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "282be5f36a8ce781fad8c8ae18fa3f9beff57ec1b52cb3de0789201425d9a33d"
 dependencies = [
- "windows-targets",
+ "windows-targets 0.52.6",
 ]
 
 [[package]]
@@ -2060,7 +3090,7 @@ version = "0.59.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1e38bc4d79ed67fd075bcc251a1c39b32a1776bbe92e5bef1f0bf1f8c531853b"
 dependencies = [
- "windows-targets",
+ "windows-targets 0.52.6",
 ]
 
 [[package]]
@@ -2069,7 +3099,22 @@ version = "0.61.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ae137229bcbd6cdf0f7b80a31df61766145077ddf49416a728b02cb3921ff3fc"
 dependencies = [
- "windows-link",
+ "windows-link 0.2.1",
+]
+
+[[package]]
+name = "windows-targets"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9a2fa6e2155d7247be68c096456083145c183cbbbc2764150dda45a87197940c"
+dependencies = [
+ "windows_aarch64_gnullvm 0.48.5",
+ "windows_aarch64_msvc 0.48.5",
+ "windows_i686_gnu 0.48.5",
+ "windows_i686_msvc 0.48.5",
+ "windows_x86_64_gnu 0.48.5",
+ "windows_x86_64_gnullvm 0.48.5",
+ "windows_x86_64_msvc 0.48.5",
 ]
 
 [[package]]
@@ -2078,28 +3123,55 @@ version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9b724f72796e036ab90c1021d4780d4d3d648aca59e491e6b98e725b84e99973"
 dependencies = [
- "windows_aarch64_gnullvm",
- "windows_aarch64_msvc",
- "windows_i686_gnu",
+ "windows_aarch64_gnullvm 0.52.6",
+ "windows_aarch64_msvc 0.52.6",
+ "windows_i686_gnu 0.52.6",
  "windows_i686_gnullvm",
- "windows_i686_msvc",
- "windows_x86_64_gnu",
- "windows_x86_64_gnullvm",
- "windows_x86_64_msvc",
+ "windows_i686_msvc 0.52.6",
+ "windows_x86_64_gnu 0.52.6",
+ "windows_x86_64_gnullvm 0.52.6",
+ "windows_x86_64_msvc 0.52.6",
 ]
 
+[[package]]
+name = "windows-threading"
+version = "0.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b66463ad2e0ea3bbf808b7f1d371311c80e115c0b71d60efc142cafbcfb057a6"
+dependencies = [
+ "windows-link 0.1.3",
+]
+
+[[package]]
+name = "windows_aarch64_gnullvm"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2b38e32f0abccf9987a4e3079dfb67dcd799fb61361e53e2882c3cbaf0d905d8"
+
 [[package]]
 name = "windows_aarch64_gnullvm"
 version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "32a4622180e7a0ec044bb555404c800bc9fd9ec262ec147edd5989ccd0c02cd3"
 
+[[package]]
+name = "windows_aarch64_msvc"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dc35310971f3b2dbbf3f0690a219f40e2d9afcf64f9ab7cc1be722937c26b4bc"
+
 [[package]]
 name = "windows_aarch64_msvc"
 version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "09ec2a7bb152e2252b53fa7803150007879548bc709c039df7627cabbd05d469"
 
+[[package]]
+name = "windows_i686_gnu"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a75915e7def60c94dcef72200b9a8e58e5091744960da64ec734a6c6e9b3743e"
+
 [[package]]
 name = "windows_i686_gnu"
 version = "0.52.6"
@@ -2112,24 +3184,48 @@ version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0eee52d38c090b3caa76c563b86c3a4bd71ef1a819287c19d586d7334ae8ed66"
 
+[[package]]
+name = "windows_i686_msvc"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8f55c233f70c4b27f66c523580f78f1004e8b5a8b659e05a4eb49d4166cca406"
+
 [[package]]
 name = "windows_i686_msvc"
 version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "240948bc05c5e7c6dabba28bf89d89ffce3e303022809e73deaefe4f6ec56c66"
 
+[[package]]
+name = "windows_x86_64_gnu"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "53d40abd2583d23e4718fddf1ebec84dbff8381c07cae67ff7768bbf19c6718e"
+
 [[package]]
 name = "windows_x86_64_gnu"
 version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "147a5c80aabfbf0c7d901cb5895d1de30ef2907eb21fbbab29ca94c5b08b1a78"
 
+[[package]]
+name = "windows_x86_64_gnullvm"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0b7b52767868a23d5bab768e390dc5f5c55825b6d30b86c844ff2dc7414044cc"
+
 [[package]]
 name = "windows_x86_64_gnullvm"
 version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "24d5b23dc417412679681396f2b49f3de8c1473deb516bd34410872eff51ed0d"
 
+[[package]]
+name = "windows_x86_64_msvc"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ed94fce61571a4006852b7389a063ab983c02eb1bb37b47f8272ce92d06d9538"
+
 [[package]]
 name = "windows_x86_64_msvc"
 version = "0.52.6"
@@ -2182,7 +3278,7 @@ checksum = "de844c262c8848816172cef550288e7dc6c7b7814b4ee56b3e1553f275f1858e"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn",
+ "syn 2.0.117",
  "synstructure",
 ]
 
@@ -2203,7 +3299,7 @@ checksum = "70e3cd084b1788766f53af483dd21f93881ff30d7320490ec3ef7526d203bad4"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn",
+ "syn 2.0.117",
 ]
 
 [[package]]
@@ -2223,7 +3319,7 @@ checksum = "11532158c46691caf0f2593ea8358fed6bbf68a0315e80aae9bd41fbade684a1"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn",
+ "syn 2.0.117",
  "synstructure",
 ]
 
@@ -2263,7 +3359,7 @@ checksum = "625dc425cab0dca6dc3c3319506e6593dcb08a9f387ea3b284dbd52a92c40555"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn",
+ "syn 2.0.117",
 ]
 
 [[package]]
diff --git a/src/obikmer/src/cmd/count.rs b/src/obikmer/src/cmd/count.rs
new file mode 100644
index 0000000..ed83eda
--- /dev/null
+++ b/src/obikmer/src/cmd/count.rs
@@ -0,0 +1,24 @@
+use clap::Args;
+use obikpartitionner::KmerPartition;
+use std::path::PathBuf;
+use tracing::info;
+
+#[derive(Args)]
+pub struct CountArgs {
+    /// Partition directory produced by the `partition` command
+    #[arg(short, long)]
+    pub partition: PathBuf,
+}
+
+pub fn run(args: CountArgs) {
+    let kp = KmerPartition::open(&args.partition).unwrap_or_else(|e| {
+        eprintln!("error: {e}");
+        std::process::exit(1)
+    });
+
+    info!("counting kmers in {}", args.partition.display());
+    kp.count_kmer().unwrap_or_else(|e| {
+        eprintln!("error: {e}");
+        std::process::exit(1)
+    });
+}
diff --git a/src/obikmer/src/cmd/mod.rs b/src/obikmer/src/cmd/mod.rs
index e259487..a0098df 100644
--- a/src/obikmer/src/cmd/mod.rs
+++ b/src/obikmer/src/cmd/mod.rs
@@ -1,2 +1,3 @@
+pub mod count;
 pub mod partition;
 pub mod superkmer;
diff --git a/src/obikmer/src/cmd/partition.rs b/src/obikmer/src/cmd/partition.rs
index 980ecc8..84d28f4 100644
--- a/src/obikmer/src/cmd/partition.rs
+++ b/src/obikmer/src/cmd/partition.rs
@@ -136,4 +136,5 @@ pub fn run(args: PartitionArgs) {
 
     info!("dereplicating...");
     kp.lock().unwrap().dereplicate().expect("dereplicate error");
+    kp.lock().unwrap().count_kmer().expect("count kmer error");
 }
diff --git a/src/obikmer/src/main.rs b/src/obikmer/src/main.rs
index 06780c4..a780237 100644
--- a/src/obikmer/src/main.rs
+++ b/src/obikmer/src/main.rs
@@ -16,6 +16,8 @@ enum Commands {
     Superkmer(cmd::superkmer::SuperkmerArgs),
     /// Partition super-kmers on disk by minimizer
     Partition(cmd::partition::PartitionArgs),
+    /// Count kmers from an existing dereplicated partition directory
+    Count(cmd::count::CountArgs),
 }
 
 fn main() {
@@ -37,6 +39,7 @@ fn main() {
     match cli.command {
         Commands::Superkmer(args) => cmd::superkmer::run(args),
         Commands::Partition(args) => cmd::partition::run(args),
+        Commands::Count(args) => cmd::count::run(args),
     }
 
     #[cfg(feature = "profiling")]
diff --git a/src/obikpartitionner/Cargo.toml b/src/obikpartitionner/Cargo.toml
index fe0379a..d8c1f68 100644
--- a/src/obikpartitionner/Cargo.toml
+++ b/src/obikpartitionner/Cargo.toml
@@ -13,3 +13,5 @@ sysinfo = "0.33"
 serde = { version = "1", features = ["derive"] }
 serde_json = "1"
 tracing = "0.1.44"
+ph = "0.11"
+memmap2 = "0.9.10"
diff --git a/src/obikpartitionner/src/partition.rs b/src/obikpartitionner/src/partition.rs
index 14c50fd..40ef113 100644
--- a/src/obikpartitionner/src/partition.rs
+++ b/src/obikpartitionner/src/partition.rs
@@ -1,8 +1,12 @@
-use std::collections::HashMap;
+use std::collections::{BTreeMap, HashMap, HashSet};
 use std::fs;
 use std::io;
 use std::path::{Path, PathBuf};
-use tracing::debug;
+use tracing::{debug, info};
+
+use memmap2::MmapMut;
+use obikseq::kmer::Kmer;
+use ph::fmph::GOFunction;
 
 use sysinfo::System;
 
@@ -99,6 +103,42 @@ impl KmerPartition {
         Ok(partition)
     }
 
+    pub fn open<P: AsRef<Path>>(path: P) -> SKResult<Self> {
+        let root_path = path.as_ref().to_owned();
+        if !root_path.exists() {
+            return Err(io::Error::new(
+                io::ErrorKind::NotFound,
+                format!("{}: partition directory not found", root_path.display()),
+            )
+            .into());
+        }
+        let meta_path = root_path.join(META_FILENAME);
+        let meta: PartitionMeta = serde_json::from_reader(fs::File::open(&meta_path)?)
+            .map_err(io::Error::other)?;
+
+        let format = match meta.format.as_str() {
+            "gzip" => Format::Gzip,
+            "bzip2" => Format::Bzip,
+            "lzma" => Format::Lzma,
+            "zstd" => Format::Zstd,
+            _ => Format::No,
+        };
+        let level = level_from_u32(meta.level);
+        let n_partitions = 1usize << meta.n_bits;
+        let writers = (0..n_partitions).map(|_| None).collect();
+        Ok(Self {
+            root_path,
+            n_partitions,
+            partitions_mask: (1u64 << meta.n_bits) - 1,
+            kmer_size: meta.kmer_size,
+            minimizer_size: meta.minimizer_size,
+            writers,
+            format,
+            level,
+            closed: true, // read-only: writing is not allowed on an opened partition
+        })
+    }
+
     pub fn write(&mut self, sk: &mut SuperKmer) -> SKResult<()> {
         self.check_not_closed()?;
         let partition = self.partition_of(sk)?;
@@ -190,6 +230,73 @@ impl KmerPartition {
         Ok(())
     }
 
+    /// For each partition that has a `dereplicated.{ext}` file:
+    /// 1. Enumerates all unique canonical kmers (two passes over the file).
+    /// 2. Builds a provisional MPHF (FMPHGO) over those kmers.
+    /// 3. Writes a flat binary count file (`counts1.bin`, one `u32` per slot,
+    ///    memory-mapped) accumulating kmer abundances from the superkmer counts.
+    /// 4. Persists the MPHF to `mphf1.bin` for downstream use.
+    /// 5. Writes a global `kmer_spectrum_raw.json` at the partition root.
+    ///
+    /// Partitions are processed in parallel via Rayon (one task per thread).
+    /// Peak memory per partition is ~80 MB, so n_threads partitions run simultaneously.
+    pub fn count_kmer(&self) -> SKResult<()> {
+        let ext = format_ext(self.format);
+        let root = &self.root_path;
+        let k = self.kmer_size;
+
+        let results: Vec<SKResult<()>> = (0..self.n_partitions)
+            .into_par_iter()
+            .map(|i| {
+                let dir = root.join(format!("part_{:05}", i));
+                let dedup_path = dir.join(format!("dereplicated.{ext}"));
+                if !dedup_path.exists() {
+                    return Ok(());
+                }
+                info!("counting kmers in partition {}/{}", i, self.n_partitions);
+                count_partition(&dir, &dedup_path, k)
+            })
+            .collect();
+        for r in results {
+            r?;
+        }
+
+        // Aggregate per-partition spectra into a global one at the root.
+        let mut global_spectrum: BTreeMap<u32, u64> = BTreeMap::new();
+        let mut global_f0: u64 = 0;
+        let mut global_f1: u64 = 0;
+
+        for i in 0..self.n_partitions {
+            let path = root
+                .join(format!("part_{:05}", i))
+                .join("kmer_spectrum_raw.json");
+            if !path.exists() {
+                continue;
+            }
+            let v: serde_json::Value =
+                serde_json::from_str(&fs::read_to_string(&path)?).map_err(io::Error::other)?;
+            global_f0 += v["f0"].as_u64().unwrap_or(0);
+            global_f1 += v["f1"].as_u64().unwrap_or(0);
+            if let Some(obj) = v["spectrum"].as_object() {
+                for (c_str, freq) in obj {
+                    if let (Ok(c), Some(f)) = (c_str.parse::<u32>(), freq.as_u64()) {
+                        *global_spectrum.entry(c).or_insert(0) += f;
+                    }
+                }
+            }
+        }
+
+        let global_spectrum_map: BTreeMap<String, u64> =
+            global_spectrum.iter().map(|(&c, &f)| (format!("{c:010}"), f)).collect();
+        serde_json::to_writer_pretty(
+            fs::File::create(root.join("kmer_spectrum_raw.json"))?,
+            &serde_json::json!({ "f0": global_f0, "f1": global_f1, "spectrum": &global_spectrum_map }),
+        )
+        .map_err(io::Error::other)?;
+
+        Ok(())
+    }
+
     // ── private ───────────────────────────────────────────────────────────────
 
     fn check_not_closed(&self) -> SKResult<()> {
@@ -289,6 +396,18 @@ fn optimal_buckets(raw_path: &Path, available_bytes: u64) -> usize {
     n.next_power_of_two() as usize
 }
 
+fn level_from_u32(n: u32) -> Level {
+    match n {
+        0 => Level::Zero, 1 => Level::One, 2 => Level::Two, 3 => Level::Three,
+        4 => Level::Four, 5 => Level::Five, 6 => Level::Six, 7 => Level::Seven,
+        8 => Level::Eight, 9 => Level::Nine, 10 => Level::Ten, 11 => Level::Eleven,
+        12 => Level::Twelve, 13 => Level::Thirteen, 14 => Level::Fourteen,
+        15 => Level::Fifteen, 16 => Level::Sixteen, 17 => Level::Seventeen,
+        18 => Level::Eighteen, 19 => Level::Nineteen, 20 => Level::Twenty,
+        _ => Level::TwentyOne,
+    }
+}
+
 fn format_ext(format: Format) -> &'static str {
     match format {
         Format::Gzip => "skmer.gz",
@@ -391,6 +510,122 @@ fn flush_map(map: HashMap<SuperKmer, u64>, writer: &mut SKFileWriter) -> SKResul
     Ok(())
 }
 
+/// Build the provisional MPHF and count file for one partition directory.
+fn count_partition(dir: &Path, dedup_path: &Path, k: usize) -> SKResult<()> {
+    // Estimate number of kmers from sidecar to pre-allocate the HashSet.
+    let capacity = SKFileMeta::read(dedup_path)
+        .ok()
+        .flatten()
+        .map(|m| {
+            let km1 = (k as u64).saturating_sub(1);
+            m.length_sum.saturating_sub(m.instances.saturating_mul(km1)) as usize
+        })
+        .unwrap_or(0);
+    debug!("{}: sidecar capacity estimate={capacity}", dir.display());
+
+    // Pass 1: collect all unique canonical kmers.
+    let mut seen: HashSet<Kmer> = HashSet::with_capacity(capacity);
+    let mut pass1_superkmers: u64 = 0;
+    {
+        let mut reader = SKFileReader::open(dedup_path)?;
+        while let Some(sk) = reader.read()? {
+            pass1_superkmers += 1;
+            let seql = sk.seql();
+            if seql < k {
+                continue;
+            }
+            for pos in 0..=(seql - k) {
+                seen.insert(sk.kmer(pos, k).map_err(io::Error::other)?.canonical(k));
+            }
+        }
+    }
+    let kmers: Vec<Kmer> = seen.into_iter().collect();
+    let n_kmers = kmers.len();
+    debug!("{}: pass1 superkmers={pass1_superkmers} unique_kmers={n_kmers}", dir.display());
+
+    if n_kmers == 0 {
+        return Ok(());
+    }
+
+    // Build provisional MPHF.
+    let mphf = GOFunction::from(kmers);
+    debug!("{}: MPHF built len={}", dir.display(), mphf.len());
+
+    // Create memory-mapped count file (u32 per slot, zero-initialised).
+    let counts_path = dir.join("counts1.bin");
+    let counts_file = fs::OpenOptions::new()
+        .read(true)
+        .write(true)
+        .create(true)
+        .truncate(true)
+        .open(&counts_path)?;
+    counts_file.set_len((n_kmers * std::mem::size_of::<u32>()) as u64)?;
+    let mut mmap = unsafe { MmapMut::map_mut(&counts_file)? };
+    mmap.fill(0);
+
+    // Pass 2: accumulate superkmer counts into the mmap'd array.
+    let mut pass2_superkmers: u64 = 0;
+    let mut pass2_kmer_hits: u64 = 0;
+    let mut pass2_kmer_misses: u64 = 0;
+    let mut pass2_count_sum: u64 = 0;
+    {
+        let counts =
+            unsafe { std::slice::from_raw_parts_mut(mmap.as_mut_ptr() as *mut u32, n_kmers) };
+        let mut reader = SKFileReader::open(dedup_path)?;
+        while let Some(sk) = reader.read()? {
+            pass2_superkmers += 1;
+            let seql = sk.seql();
+            let sk_count = sk.count();
+            if pass2_superkmers <= 3 {
+                debug!("{}: sk#{pass2_superkmers} seql={seql} count={sk_count}", dir.display());
+            }
+            if seql < k {
+                continue;
+            }
+            pass2_count_sum += sk_count as u64;
+            for pos in 0..=(seql - k) {
+                let kmer = sk.kmer(pos, k).map_err(io::Error::other)?.canonical(k);
+                if let Some(idx) = mphf.get(&kmer) {
+                    counts[idx as usize] = counts[idx as usize].saturating_add(sk_count);
+                    pass2_kmer_hits += 1;
+                } else {
+                    pass2_kmer_misses += 1;
+                }
+            }
+        }
+    }
+    debug!(
+        "{}: pass2 superkmers={pass2_superkmers} hits={pass2_kmer_hits} misses={pass2_kmer_misses} count_sum={pass2_count_sum}",
+        dir.display()
+    );
+    mmap.flush()?;
+
+    // Build kmer frequency spectrum from the count array.
+    let counts = unsafe { std::slice::from_raw_parts(mmap.as_ptr() as *const u32, n_kmers) };
+    let mut spectrum: BTreeMap<u32, u64> = BTreeMap::new();
+    for &c in counts {
+        if c > 0 {
+            *spectrum.entry(c).or_insert(0) += 1;
+        }
+    }
+    let f0 = n_kmers as u64;
+    let f1: u64 = spectrum.iter().map(|(&c, &f)| c as u64 * f).sum();
+
+    let spectrum_map: BTreeMap<String, u64> =
+        spectrum.iter().map(|(&c, &f)| (format!("{c:010}"), f)).collect();
+    serde_json::to_writer_pretty(
+        fs::File::create(dir.join("kmer_spectrum_raw.json"))?,
+        &serde_json::json!({ "f0": f0, "f1": f1, "spectrum": &spectrum_map }),
+    )
+    .map_err(io::Error::other)?;
+
+    // Persist MPHF to disk.
+    let mphf_path = dir.join("mphf1.bin");
+    mphf.write(&mut fs::File::create(&mphf_path)?)?;
+
+    Ok(())
+}
+
 impl Drop for KmerPartition {
     fn drop(&mut self) {
         let _ = self.close();
diff --git a/src/obikseq/src/superkmer.rs b/src/obikseq/src/superkmer.rs
index 2a39f4e..1175b9f 100644
--- a/src/obikseq/src/superkmer.rs
+++ b/src/obikseq/src/superkmer.rs
@@ -135,6 +135,18 @@ impl SuperKmer {
         }
     }
 
+    /// Deserialise from a raw 32-bit header word and packed sequence bytes.
+    /// Preserves the full header payload (count or minimizer_pos in bits [31:8]).
+    pub fn from_header_bits(bits: u32, seq: Box<[u8]>) -> Self {
+        let seql = (bits & 0xFF) as u8;
+        let len = stored_to_len(seql);
+        debug_assert_eq!(seq.len(), byte_len(len));
+        Self {
+            header: SuperKmerHeader(bits),
+            seq,
+        }
+    }
+
     /// Returns the sequence length in nucleotides (1–256).
     pub fn seql(&self) -> usize {
         stored_to_len(self.header.seql())
diff --git a/src/obiskio/src/codec.rs b/src/obiskio/src/codec.rs
index 62f90ae..818e8a0 100644
--- a/src/obiskio/src/codec.rs
+++ b/src/obiskio/src/codec.rs
@@ -26,7 +26,7 @@ pub(crate) fn read_superkmer<R: Read>(
     let byte_len = (nt_len + 3) / 4;
     seq_buf.resize(byte_len, 0);
     r.read_exact(seq_buf)?;
-    Ok(Some(SuperKmer::new(seql_byte, seq_buf.as_slice().into())))
+    Ok(Some(SuperKmer::from_header_bits(bits, seq_buf.as_slice().into())))
 }
 
 #[cfg(test)]
diff --git a/target/.rustc_info.json b/target/.rustc_info.json
deleted file mode 100644
index 3e2b77b..0000000
--- a/target/.rustc_info.json
+++ /dev/null
@@ -1 +0,0 @@
-{"rustc_fingerprint":2162534064148227772,"outputs":{"7971740275564407648":{"success":true,"status":"","code":0,"stdout":"___\nlib___.rlib\nlib___.dylib\nlib___.dylib\nlib___.a\nlib___.dylib\n/Users/coissac/.rustup/toolchains/stable-aarch64-apple-darwin\noff\npacked\nunpacked\n___\ndebug_assertions\npanic=\"unwind\"\nproc_macro\ntarget_abi=\"\"\ntarget_arch=\"aarch64\"\ntarget_endian=\"little\"\ntarget_env=\"\"\ntarget_family=\"unix\"\ntarget_feature=\"aes\"\ntarget_feature=\"crc\"\ntarget_feature=\"dit\"\ntarget_feature=\"dotprod\"\ntarget_feature=\"dpb\"\ntarget_feature=\"dpb2\"\ntarget_feature=\"fcma\"\ntarget_feature=\"fhm\"\ntarget_feature=\"flagm\"\ntarget_feature=\"fp16\"\ntarget_feature=\"frintts\"\ntarget_feature=\"jsconv\"\ntarget_feature=\"lor\"\ntarget_feature=\"lse\"\ntarget_feature=\"neon\"\ntarget_feature=\"paca\"\ntarget_feature=\"pacg\"\ntarget_feature=\"pan\"\ntarget_feature=\"pmuv3\"\ntarget_feature=\"ras\"\ntarget_feature=\"rcpc\"\ntarget_feature=\"rcpc2\"\ntarget_feature=\"rdm\"\ntarget_feature=\"sb\"\ntarget_feature=\"sha2\"\ntarget_feature=\"sha3\"\ntarget_feature=\"ssbs\"\ntarget_feature=\"vh\"\ntarget_has_atomic=\"128\"\ntarget_has_atomic=\"16\"\ntarget_has_atomic=\"32\"\ntarget_has_atomic=\"64\"\ntarget_has_atomic=\"8\"\ntarget_has_atomic=\"ptr\"\ntarget_os=\"macos\"\ntarget_pointer_width=\"64\"\ntarget_vendor=\"apple\"\nunix\n","stderr":""},"6432102384495711296":{"success":true,"status":"","code":0,"stdout":"___\nlib___.rlib\nlib___.dylib\nlib___.dylib\nlib___.a\nlib___.dylib\n/Users/coissac/.rustup/toolchains/stable-aarch64-apple-darwin\noff\npacked\nunpacked\n___\ndebug_assertions\npanic=\"unwind\"\nproc_macro\ntarget_abi=\"\"\ntarget_arch=\"aarch64\"\ntarget_endian=\"little\"\ntarget_env=\"\"\ntarget_family=\"unix\"\ntarget_feature=\"aes\"\ntarget_feature=\"crc\"\ntarget_feature=\"dit\"\ntarget_feature=\"dotprod\"\ntarget_feature=\"dpb\"\ntarget_feature=\"dpb2\"\ntarget_feature=\"fcma\"\ntarget_feature=\"fhm\"\ntarget_feature=\"flagm\"\ntarget_feature=\"fp16\"\ntarget_feature=\"frintts\"\ntarget_feature=\"jsconv\"\ntarget_feature=\"lor\"\ntarget_feature=\"lse\"\ntarget_feature=\"neon\"\ntarget_feature=\"paca\"\ntarget_feature=\"pacg\"\ntarget_feature=\"pan\"\ntarget_feature=\"pmuv3\"\ntarget_feature=\"ras\"\ntarget_feature=\"rcpc\"\ntarget_feature=\"rcpc2\"\ntarget_feature=\"rdm\"\ntarget_feature=\"sb\"\ntarget_feature=\"sha2\"\ntarget_feature=\"sha3\"\ntarget_feature=\"ssbs\"\ntarget_feature=\"vh\"\ntarget_has_atomic=\"128\"\ntarget_has_atomic=\"16\"\ntarget_has_atomic=\"32\"\ntarget_has_atomic=\"64\"\ntarget_has_atomic=\"8\"\ntarget_has_atomic=\"ptr\"\ntarget_os=\"macos\"\ntarget_pointer_width=\"64\"\ntarget_vendor=\"apple\"\nunix\n","stderr":""},"17747080675513052775":{"success":true,"status":"","code":0,"stdout":"rustc 1.94.1 (e408947bf 2026-03-25)\nbinary: rustc\ncommit-hash: e408947bfd200af42db322daf0fadfe7e26d3bd1\ncommit-date: 2026-03-25\nhost: aarch64-apple-darwin\nrelease: 1.94.1\nLLVM version: 21.1.8\n","stderr":""}},"successes":{}}
\ No newline at end of file
diff --git a/target/debug/.fingerprint/obikseq-4791c70657a715c0/lib-obikseq.json b/target/debug/.fingerprint/obikseq-4791c70657a715c0/lib-obikseq.json
deleted file mode 100644
index 3a60560..0000000
--- a/target/debug/.fingerprint/obikseq-4791c70657a715c0/lib-obikseq.json
+++ /dev/null
@@ -1 +0,0 @@
-{"rustc":17940977064402226622,"features":"[]","declared_features":"[]","target":1865439097712885860,"profile":2330448797067240312,"path":3117914143523182133,"deps":[],"local":[{"CheckDepInfo":{"dep_info":"debug/.fingerprint/obikseq-4791c70657a715c0/dep-lib-obikseq","checksum":false}}],"rustflags":[],"config":8247474407144887393,"compile_kind":0}
\ No newline at end of file
diff --git a/target/debug/.fingerprint/obikseq-5cc47015be91e3b1/test-lib-obikseq.json b/target/debug/.fingerprint/obikseq-5cc47015be91e3b1/test-lib-obikseq.json
deleted file mode 100644
index 4b01c74..0000000
--- a/target/debug/.fingerprint/obikseq-5cc47015be91e3b1/test-lib-obikseq.json
+++ /dev/null
@@ -1 +0,0 @@
-{"rustc":17940977064402226622,"features":"[]","declared_features":"[]","target":1865439097712885860,"profile":619605765252926426,"path":3117914143523182133,"deps":[],"local":[{"CheckDepInfo":{"dep_info":"debug/.fingerprint/obikseq-5cc47015be91e3b1/dep-test-lib-obikseq","checksum":false}}],"rustflags":[],"config":8247474407144887393,"compile_kind":0}
\ No newline at end of file
diff --git a/target/debug/incremental/obikseq-2j6dqqw76e9t8/s-hho6vbiepl-0ie9k92-17oaxmsyy8cxuem2djd4dy9hq/dep-graph.bin b/target/debug/incremental/obikseq-2j6dqqw76e9t8/s-hho6vbiepl-0ie9k92-17oaxmsyy8cxuem2djd4dy9hq/dep-graph.bin
deleted file mode 100644
index ea685ce..0000000
Binary files a/target/debug/incremental/obikseq-2j6dqqw76e9t8/s-hho6vbiepl-0ie9k92-17oaxmsyy8cxuem2djd4dy9hq/dep-graph.bin and /dev/null differ
diff --git a/target/debug/incremental/obikseq-2j6dqqw76e9t8/s-hho6vbiepl-0ie9k92-17oaxmsyy8cxuem2djd4dy9hq/query-cache.bin b/target/debug/incremental/obikseq-2j6dqqw76e9t8/s-hho6vbiepl-0ie9k92-17oaxmsyy8cxuem2djd4dy9hq/query-cache.bin
deleted file mode 100644
index b9f03ef..0000000
Binary files a/target/debug/incremental/obikseq-2j6dqqw76e9t8/s-hho6vbiepl-0ie9k92-17oaxmsyy8cxuem2djd4dy9hq/query-cache.bin and /dev/null differ
diff --git a/target/debug/incremental/obikseq-2j6dqqw76e9t8/s-hho6vbiepl-0ie9k92-17oaxmsyy8cxuem2djd4dy9hq/work-products.bin b/target/debug/incremental/obikseq-2j6dqqw76e9t8/s-hho6vbiepl-0ie9k92-17oaxmsyy8cxuem2djd4dy9hq/work-products.bin
deleted file mode 100644
index ad58b7b..0000000
Binary files a/target/debug/incremental/obikseq-2j6dqqw76e9t8/s-hho6vbiepl-0ie9k92-17oaxmsyy8cxuem2djd4dy9hq/work-products.bin and /dev/null differ
diff --git a/target/debug/incremental/obikseq-3q3fzz1res9p1/s-hho6vbiepy-0dc3k1e-2mx56wrd3i6p76vxgtzl7pdhs/dep-graph.bin b/target/debug/incremental/obikseq-3q3fzz1res9p1/s-hho6vbiepy-0dc3k1e-2mx56wrd3i6p76vxgtzl7pdhs/dep-graph.bin
deleted file mode 100644
index 9197fd3..0000000
Binary files a/target/debug/incremental/obikseq-3q3fzz1res9p1/s-hho6vbiepy-0dc3k1e-2mx56wrd3i6p76vxgtzl7pdhs/dep-graph.bin and /dev/null differ
diff --git a/target/debug/incremental/obikseq-3q3fzz1res9p1/s-hho6vbiepy-0dc3k1e-2mx56wrd3i6p76vxgtzl7pdhs/query-cache.bin b/target/debug/incremental/obikseq-3q3fzz1res9p1/s-hho6vbiepy-0dc3k1e-2mx56wrd3i6p76vxgtzl7pdhs/query-cache.bin
deleted file mode 100644
index 75bb527..0000000
Binary files a/target/debug/incremental/obikseq-3q3fzz1res9p1/s-hho6vbiepy-0dc3k1e-2mx56wrd3i6p76vxgtzl7pdhs/query-cache.bin and /dev/null differ
diff --git a/target/debug/incremental/obikseq-3q3fzz1res9p1/s-hho6vbiepy-0dc3k1e-2mx56wrd3i6p76vxgtzl7pdhs/work-products.bin b/target/debug/incremental/obikseq-3q3fzz1res9p1/s-hho6vbiepy-0dc3k1e-2mx56wrd3i6p76vxgtzl7pdhs/work-products.bin
deleted file mode 100644
index aaedb06..0000000
Binary files a/target/debug/incremental/obikseq-3q3fzz1res9p1/s-hho6vbiepy-0dc3k1e-2mx56wrd3i6p76vxgtzl7pdhs/work-products.bin and /dev/null differ