diff --git a/src/nodes/face_aligner_node.hpp b/src/nodes/face_aligner_node.hpp
index a684b1a..f14cda4 100644
--- a/src/nodes/face_aligner_node.hpp
+++ b/src/nodes/face_aligner_node.hpp
@@ -4,12 +4,16 @@
 #include <iostream>
 
 // ── FaceAlignerFunc ───────────────────────────────────────────────────────────
+/// TRACES: AR-005, AR-030 | SR-002
+///
 // KPN node: applies a 5-point similarity transform to each detected face,
 // producing a 112×112 BGR crop suitable for ArcFace inference.
 //
-// Alignment uses cv::estimateAffinePartial2D (RANSAC) to fit the detected
-// landmarks to ArcFace canonical positions.  Degenerate detections (where the
-// affine fit fails) are silently dropped from the output vectors.
+// Alignment is an Umeyama least-squares fit over all five landmarks (AR-005),
+// not a robust one: a RANSAC fit discards the very landmarks AR-030 reads.
+// Degenerate detections (where the fit fails) are dropped from the output
+// vectors. The fit's residual is the AR-030 visibility measure and comes free,
+// since the warp needs the transform anyway.
 
 struct FaceAlignerFunc {
     static constexpr std::string_view label() { return "face_aligner"; }
diff --git a/tests/test_calibration.cpp b/tests/test_calibration.cpp
index 8728f9e..2b92434 100644
--- a/tests/test_calibration.cpp
+++ b/tests/test_calibration.cpp
@@ -1,6 +1,12 @@
+// TRACES: AR-023 | SR-002
+//
 // Unit tests for gallery calibration: the sigmoid math, the pairwise fit on
 // separable data, and the in-memory hash-keyed cache (hit / stale / cold).
 // All pure, GPU-free, model-free.
+//
+// The three `[report]` cases at the bottom carry their own GR-003 tags: they
+// verify the build report, which is fitted from the same distributions but is a
+// separate requirement.
 #include <catch2/catch_test_macros.hpp>
 #include <catch2/matchers/catch_matchers_floating_point.hpp>
 
@@ -183,6 +189,7 @@ Embedding unit_axis(int slot) {
 }
 }  // namespace
 
+// TRACES: GR-003 | SR-001
 TEST_CASE("report surfaces actors that can never be recognised", "[report][GR-003]") {
     // An actor with no usable image is a silent recall ceiling: the pipeline
     // will never name them, and nothing in the gallery says why. This is the
@@ -212,6 +219,7 @@ TEST_CASE("report surfaces actors that can never be recognised", "[report][GR-00
     CHECK(r.actors[1].references == 0);
 }
 
+// TRACES: GR-003 | SR-001
 TEST_CASE("report surfaces actors too thin to calibrate on", "[report][GR-003]") {
     // Below the positive-pair threshold an actor contributes nothing to the
     // intra-class side of the fit. They are not broken, so nothing complains —
@@ -237,6 +245,7 @@ TEST_CASE("report surfaces actors too thin to calibrate on", "[report][GR-003]")
     CHECK(r.actors_below_positive_threshold >= 1);
 }
 
+// TRACES: GR-003 | SR-001
 TEST_CASE("report round-trips", "[report][GR-003]") {
     ActorGallery g;
     ActorGallery::Actor act;
diff --git a/tests/test_face_tracker.cpp b/tests/test_face_tracker.cpp
index 26b2c82..c0645bf 100644
--- a/tests/test_face_tracker.cpp
+++ b/tests/test_face_tracker.cpp
@@ -1,13 +1,17 @@
+// TRACES: AR-007, AR-008 | SR-002
+//
 // Unit tests for FaceTrackerFunc (nodes/face_tracker_node.hpp): frame-to-frame
 // track linking and, crucially, cross-cut re-association. Pure, GPU-free,
 // model-free — drives the node's operator() with hand-built EmbeddedSceneFrames
 // and inspects the emitted track_ids.
 //
-// The behaviour under test: on a camera-angle change (Frame::is_cut) the tracker
-// parks its tracks instead of destroying them, and revives a parked track_id
-// when a post-cut detection's raw last-frame-embedding cosine similarity clears
-// cut_revive_sim. IoU is deliberately driven to 0 across the cut (boxes moved) so
-// only the embedding path can re-link — exactly the scenario a cut creates.
+// The behaviour under test: there is one track pool keyed on `last_seen`
+// (AR-008), so a face lost across a camera-angle change (Frame::is_cut) is an
+// ordinary association candidate rather than a parked track needing a revival
+// path — the raw-cosine `cut_revive_sim` that guarded that path is retired
+// (AR-024). On a cut the association weight drops to embedding-only (AR-007),
+// and IoU is deliberately driven to 0 across the cut (boxes moved) so only the
+// embedding path can re-link — exactly the scenario a cut creates.
 #include <catch2/catch_test_macros.hpp>
 
 #include "config.hpp"
diff --git a/tests/test_similarity.cpp b/tests/test_similarity.cpp
index 14d2bc3..b508077 100644
--- a/tests/test_similarity.cpp
+++ b/tests/test_similarity.cpp
@@ -1,5 +1,11 @@
+// TRACES: AR-026 | SR-001
+//
 // Unit tests for the CPU reference similarity engine (backends/gemm_backend.cpp,
 // SAE_GEMM_CPU) and the l2_normalise helper. All pure, GPU-free, model-free.
+//
+// This is the CI half of AR-026: equivalence between the GEMM path and
+// hand-computed dot products on small input. Throughput at scale (AR-027) is T4
+// and cannot run here.
 #include <catch2/catch_test_macros.hpp>
 #include <catch2/matchers/catch_matchers_floating_point.hpp>