From 1bde4e834f628f4b7b59004cabdd7bc014896e8f Mon Sep 17 00:00:00 2001
From: giles <giles.bradshaw@rose-ash.com>
Date: Sat, 9 May 2026 16:56:46 +0000
Subject: [PATCH] ocaml: phase 5.1 stable_unique.ml baseline (Hashtbl dedupe
 preserving order, 8+38 = 46)

Walk input with Hashtbl.mem + Hashtbl.add seen x () (unit-payload
turns the table into a set); on first occurrence cons to the result
list; reverse at the end:

  let stable_unique xs =
    let seen = Hashtbl.create 8 in
    let result = ref [] in
    List.iter (fun x ->
      if not (Hashtbl.mem seen x) then begin
        Hashtbl.add seen x ();
        result := x :: !result
      end
    ) xs;
    List.rev !result

For [3;1;4;1;5;9;2;6;5;3;5;8;9]:
  result = [3;1;4;5;9;2;6;8]   (input order, dupes dropped)
  length = 8, sum = 38         total = 46

Tests Hashtbl as a set abstraction (unit-payload), the rev-build
idiom, and 'not (Hashtbl.mem seen x)' membership negation.

82 baseline programs total.
---
 lib/ocaml/baseline/expected.json    |  1 +
 lib/ocaml/baseline/stable_unique.ml | 15 +++++++++++++++
 plans/ocaml-on-sx.md                |  8 ++++++++
 3 files changed, 24 insertions(+)
 create mode 100644 lib/ocaml/baseline/stable_unique.ml

diff --git a/lib/ocaml/baseline/expected.json b/lib/ocaml/baseline/expected.json
index f21e85c2..fe1185bc 100644
--- a/lib/ocaml/baseline/expected.json
+++ b/lib/ocaml/baseline/expected.json
@@ -70,6 +70,7 @@
   "run_length.ml": 11,
   "safe_div.ml": 20,
   "shuffle.ml": 55,
+  "stable_unique.ml": 46,
   "subset_sum.ml": 8,
   "tic_tac_toe.ml": 1,
   "word_freq.ml": 8,
diff --git a/lib/ocaml/baseline/stable_unique.ml b/lib/ocaml/baseline/stable_unique.ml
new file mode 100644
index 00000000..4a108575
--- /dev/null
+++ b/lib/ocaml/baseline/stable_unique.ml
@@ -0,0 +1,15 @@
+let stable_unique xs =
+  let seen = Hashtbl.create 8 in
+  let result = ref [] in
+  List.iter (fun x ->
+    if not (Hashtbl.mem seen x) then begin
+      Hashtbl.add seen x ();
+      result := x :: !result
+    end
+  ) xs;
+  List.rev !result
+
+;;
+
+List.length (stable_unique [3;1;4;1;5;9;2;6;5;3;5;8;9])
++ List.fold_left (+) 0 (stable_unique [3;1;4;1;5;9;2;6;5;3;5;8;9])
diff --git a/plans/ocaml-on-sx.md b/plans/ocaml-on-sx.md
index 8a5be0a8..5f4ddf4a 100644
--- a/plans/ocaml-on-sx.md
+++ b/plans/ocaml-on-sx.md
@@ -407,6 +407,14 @@ _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.
+- 2026-05-09 Phase 5.1 — stable_unique.ml baseline (Hashtbl-tracked
+  dedupe preserving order, length+sum = 8+38 = 46). Walks input
+  with `Hashtbl.mem` + `Hashtbl.add seen x ()` (unit-payload to use
+  the table as a set); on first occurrence cons to the result list,
+  reverse at the end. For [3;1;4;1;5;9;2;6;5;3;5;8;9] yields
+  [3;1;4;5;9;2;6;8] — 8 elements summing to 38. Tests Hashtbl as
+  a set abstraction (ignoring values), and the rev-build idiom. 82
+  baseline programs total.
 - 2026-05-09 Phase 5.1 — run_decode.ml baseline (RLE decode, sum of
   expansion = 21). Inverse of run_length.ml: takes a list of
   `(value, count)` tuples, expands each pair via inner `rep` helper,