From 99f321f532b86fa5a2a8669a52807edff8e4be27 Mon Sep 17 00:00:00 2001
From: giles <giles.bradshaw@rose-ash.com>
Date: Sun, 10 May 2026 05:21:14 +0000
Subject: [PATCH] ocaml: phase 5.1 mst_kruskal.ml baseline (5-node MST weight
 11)

Kruskal's minimum spanning tree using path-compressing union-find:

  edges (w, u, v):
    (1, 0, 1) (2, 1, 2) (3, 0, 3) (4, 2, 3) (5, 3, 4) (6, 0, 4)

After sorting by weight and greedily unioning:
  pick (1,0,1) -> components: {0,1} {2} {3} {4}
  pick (2,1,2) -> {0,1,2} {3} {4}
  pick (3,0,3) -> {0,1,2,3} {4}
  skip (4,2,3) -- already connected
  pick (5,3,4) -> {0,1,2,3,4}
  skip (6,0,4) -- already connected

  MST weight = 1 + 2 + 3 + 5 = 11

Tests List.sort with 3-tuple destructuring lambda, compare on int,
Array.init with closure, in-place array mutation in find, boolean
union returning true iff merge happened.

147 baseline programs total.
---
 lib/ocaml/baseline/expected.json  |  1 +
 lib/ocaml/baseline/mst_kruskal.ml | 32 +++++++++++++++++++++++++++++++
 plans/ocaml-on-sx.md              |  9 +++++++++
 3 files changed, 42 insertions(+)
 create mode 100644 lib/ocaml/baseline/mst_kruskal.ml

diff --git a/lib/ocaml/baseline/expected.json b/lib/ocaml/baseline/expected.json
index 269c63b2..675c2dd7 100644
--- a/lib/ocaml/baseline/expected.json
+++ b/lib/ocaml/baseline/expected.json
@@ -89,6 +89,7 @@
   "levenshtein.ml": 11,
   "memo_fib.ml": 75025,
   "mortgage.ml": 1073,
+  "mst_kruskal.ml": 11,
   "merge_intervals.ml": 12,
   "merge_sort.ml": 44,
   "merge_two.ml": 441,
diff --git a/lib/ocaml/baseline/mst_kruskal.ml b/lib/ocaml/baseline/mst_kruskal.ml
new file mode 100644
index 00000000..85f8656e
--- /dev/null
+++ b/lib/ocaml/baseline/mst_kruskal.ml
@@ -0,0 +1,32 @@
+let edges = [
+  (1, 0, 1); (2, 1, 2); (3, 0, 3); (4, 2, 3); (5, 3, 4); (6, 0, 4)
+]
+
+let make_uf n = Array.init n (fun i -> i)
+
+let rec find p x =
+  if p.(x) = x then x
+  else begin
+    let r = find p p.(x) in
+    p.(x) <- r;
+    r
+  end
+
+let union p x y =
+  let rx = find p x in
+  let ry = find p y in
+  if rx <> ry then begin p.(rx) <- ry; true end
+  else false
+
+let mst_weight n es =
+  let sorted = List.sort (fun (w1, _, _) (w2, _, _) -> compare w1 w2) es in
+  let p = make_uf n in
+  let total = ref 0 in
+  List.iter (fun (w, u, v) ->
+    if union p u v then total := !total + w
+  ) sorted;
+  !total
+
+;;
+
+mst_weight 5 edges
diff --git a/plans/ocaml-on-sx.md b/plans/ocaml-on-sx.md
index 4e42583d..b2a64fea 100644
--- a/plans/ocaml-on-sx.md
+++ b/plans/ocaml-on-sx.md
@@ -407,6 +407,15 @@ _Newest first._
   binary search tree (`type 'a tree = Leaf | Node of 'a * 'a tree *
   'a tree`) with insert + in-order traversal. Tests parametric ADT,
   recursive match, List.append, List.fold_left.
+- 2026-05-10 Phase 5.1 — mst_kruskal.ml baseline (Kruskal MST on
+  5-node, 6-edge graph → MST weight 11). Sort edges by weight,
+  greedily add edges whose endpoints are in different components
+  using union-find with path compression. Edges (w,u,v) sorted:
+  (1,0,1) ✓ (2,1,2) ✓ (3,0,3) ✓ (4,2,3) ✗ already connected,
+  (5,3,4) ✓ (6,0,4) ✗. Picked weight: 1+2+3+5 = 11. Tests
+  List.sort with 3-tuple destructuring lambda, Array.init, in-place
+  array mutation (find compression), boolean-returning union.
+  147 baseline programs total.
 - 2026-05-10 Phase 5.1 — trie.ml baseline (prefix tree, 6 of 9
   word lookups match). Mutable record `{ terminal; children }` with
   `children : (char * trie) list`; insert recurses down character