diff --git a/docs/assets/images/scene_detector_evolution.png b/docs/assets/images/scene_detector_evolution.png
new file mode 100644
index 0000000..a684941
Binary files /dev/null and b/docs/assets/images/scene_detector_evolution.png differ
diff --git a/docs/scene-boundary-detector.md b/docs/scene-boundary-detector.md
index 6d3dbb0..9f118a5 100644
--- a/docs/scene-boundary-detector.md
+++ b/docs/scene-boundary-detector.md
@@ -62,7 +62,13 @@ Everything is per second, aligned to the 1-fps presence grid.
   the films where video is weak (Downton, Sound of Metal), so it is included and
   the model uses it where it helps.
 
-![Detector development: features and model](assets/images/scene_detector_evolution.png)
+![Detector development at strict ±2 s tolerance, and where the shipped detector landed at the ±20 s tolerance the pipeline uses](assets/images/scene_detector_evolution.png)
+
+The left panel is the *feature* development, scored at a strict ±2 s tolerance so
+each change is visible — this is where "delta beats raw histogram" was measured, not
+the shipped tolerance. The right panel is the shipped detector at the ±20 s
+tolerance the pipeline actually uses (see below). The two panels are on different
+tolerances by design and must not be read as one curve.
 
 Dead ends, all measured and discarded: audio-only detection; raw
 histograms/PSDs as input; a two-tower BiLSTM (no better than the tree, far slower);
@@ -81,14 +87,22 @@ and TransNetV2 (a Conv3D net that will not co-reside with the ROCm/VAAPI stack).
   real boundaries give way to noise. Selecting at the knee **self-calibrates the
   boundary count** to roughly the true scene count, per film, with no global
   threshold that would be wrong for every grade.
-- **Trained on all nine films** for the shipped model. Café Society and Scarface
-  (the low-contrast grades) *must* be in training — held out, the model cannot
-  generalise to them; in training they reach 70–86% boundary-F1.
+- **Trained on all nine films** for the shipped model. Keeping the low-contrast
+  grades (Café Society, Scarface) in training matters most: on its own training
+  films the shipped model reaches **72.9% macro boundary-F1** (per-film 51–86%),
+  versus **29.8%** for the grayscale baseline on the same films.
 
 Boundary detection, held out (leave-one-out, ±20 s tolerance — appropriate given
-~170 s scenes): **~34% F1, versus ~27% for the grayscale baseline.** The absolute
-number is capped by the narrative-vs-audiovisual mismatch above; the point is the
-downstream effect.
+~170 s scenes): **44.1% macro F1, versus 29.8% for the grayscale baseline** — the
+honest generalisation number, each film scored by a detector trained on the other
+eight. Even the low-contrast grades generalise (Scarface held out 32%, Café Society
+51%), where the grayscale detector scores 0% and 31%. The absolute number is capped
+by the narrative-vs-audiovisual mismatch above — many boundaries have no
+audio-visual signature at all — so the point is the downstream effect, below.
+
+| boundary-F1 @±20 s | grayscale | learned (LOO) | learned (train-all) |
+| ------------------ | --------: | ------------: | ------------------: |
+| macro over 9 films | 29.8% | **44.1%** | 72.9% |
 
 ## The result that matters: actor presence
 
diff --git a/scripts/scene_detector/make_figures.py b/scripts/scene_detector/make_figures.py
index 1087700..b2b6902 100644
--- a/scripts/scene_detector/make_figures.py
+++ b/scripts/scene_detector/make_figures.py
@@ -57,15 +57,34 @@ def fig_macro():
     fig.tight_layout(); fig.savefig(OUT/"scene_presence_macro.png"); plt.close(fig)
 
 # ── Figure 3: feature/model evolution (boundary-F1 development) ──────────────
+# Two panels, because the development curve and the shipped result are measured
+# at DIFFERENT tolerances and must not be plotted on one axis:
+#   left  — relative feature progress at the strict ±2 s tolerance (how the LSTM
+#           experiments were scored; establishes which features helped)
+#   right — the shipped XGBoost detector at the ±20 s tolerance the pipeline
+#           actually uses and scores at (grayscale vs learned-LOO vs train-all)
 def fig_evolution():
+    fig,(axl,axr)=plt.subplots(1,2,figsize=(11,4.5),gridspec_kw={"width_ratios":[1.15,1]})
+
     steps=["grayscale\nbaseline","raw-hist\nLSTM","delta\nLSTM","XGBoost\n(delta+debounce)"]
-    f1=[7.2,7.5,10.8,15.2]   # boundary-F1 @±2s during development
-    fig,ax=plt.subplots(figsize=(6.5,4.5))
-    ax.plot(steps,f1,marker="o",color="#3d7ea6",lw=2,ms=8)
-    for i,v in enumerate(f1): ax.text(i,v+0.4,f"{v:.1f}%",ha="center",fontsize=10)
-    ax.set_ylabel("held-out boundary F1 @±2s (%)")
-    ax.set_title("Detector development: features + model")
-    ax.set_ylim(0,18)
+    dev=[7.2,7.5,10.8,15.2]   # boundary-F1 @±2s during LSTM-era development
+    axl.plot(steps,dev,marker="o",color="#9aa7b4",lw=2,ms=8)
+    for i,v in enumerate(dev): axl.text(i,v+0.4,f"{v:.1f}%",ha="center",fontsize=9)
+    axl.set_ylabel("boundary F1 @±2 s (%)")
+    axl.set_title("Feature progress (strict ±2 s)")
+    axl.set_ylim(0,18)
+
+    # shipped detector at the ±20s tolerance the pipeline uses — real measured
+    # macro numbers: grayscale (xgb_report gray_F1), learned LOO, learned train-all
+    names=["grayscale","learned\n(LOO)","learned\n(train-all)"]
+    f20=[29.8,44.1,72.9]; cols=["#e07a5f","#3d7ea6","#8fb8cf"]
+    bars=axr.bar(names,f20,color=cols)
+    for b,v in zip(bars,f20): axr.text(b.get_x()+b.get_width()/2,v+1.2,f"{v:.1f}%",
+                                       ha="center",fontsize=10,fontweight="bold")
+    axr.set_ylabel("boundary F1 @±20 s (%)")
+    axr.set_title("Shipped detector (±20 s, macro/9 films)")
+    axr.set_ylim(0,80)
+    fig.suptitle("Detector development, and where it landed",fontsize=13)
     fig.tight_layout(); fig.savefig(OUT/"scene_detector_evolution.png"); plt.close(fig)
 
 import csv as _csv