analysis: add CLLN scaling pilot figure

2 files changed, 52 insertions, 0 deletions

diff --git a/visual-composer/coupled-ladder-scaling.md b/visual-composer/coupled-ladder-scaling.md
new file mode 100644
index 0000000..c339551
--- /dev/null
+++ b/visual-composer/coupled-ladder-scaling.md
@@ -0,0 +1,37 @@
+# Visual contract: digital CLLN scaling pilot
+
+- **Artifact:** three-panel quantitative result figure.
+- **Target venue / format:** ICLR two-column paper, full-width figure.
+- **Core claim:** local innovation subtraction preserves digital coupled
+  learning under fixed component imperfection as the lattice grows.
+- **Reviewer question:** does SDIL retain a task-level advantage at large
+  system size, and is the result stronger than static calibration or matched
+  zero-mean noise?
+- **Evidence layer:** main scaling result, currently labelled exploratory.
+- **Source data:**
+  `results/coupled_ladder/p1_imperfection_pilot.json` and
+  `results/coupled_ladder/p1_bias_baseline_pilot.json`.
+- **Statistics / uncertainty:** component draws are averaged within task;
+  tasks are the bootstrap unit. The pilot has five task clusters and one
+  component draw per task and size. Error bars are percentile 95% intervals.
+- **Figure prototype:** coordinated small-multiple lines.
+- **Panel map:**
+  - (a) final classification error against learnable edge count;
+  - (b) fraction of runs that reach zero error and remain there through the
+    training horizon;
+  - (c) mean classification error over epochs at 2,048 edges.
+- **Exact label inventory:** Clean, same-RMS noise, raw imperfection, static
+  calibration, SDIL, learnable edges, classification error, stable zero-error
+  runs, training epoch.
+- **Caption role:** state the paired protocol, distinguish fixed bias from
+  matched noise, and label the evidence as a five-task pilot.
+- **Manuscript placement:** Part 2, immediately after the digital CLLN and
+  component-imperfection definitions.
+- **Output formats:** editable SVG, vector PDF, PNG preview, analysis JSON,
+  and source CSV.
+- **Traceability:** every plotted aggregate is regenerated by
+  `experiments/analyze_coupled_ladder_scaling.py` from the two JSON files.
+- **Constraint:** the figure reports an error-growth slope comparison only
+  when the static-calibration slope is positive. Raw imperfection is allowed
+  to show a high non-monotonic floor rather than a forced power law.
+
diff --git a/visual-composer/qa-ledger.md b/visual-composer/qa-ledger.md
new file mode 100644
index 0000000..319c1f2
--- /dev/null
+++ b/visual-composer/qa-ledger.md
@@ -0,0 +1,15 @@
+# Visual QA ledger
+
+| Issue | Artifact | Severity | Fix | Status |
+|:--|:--|:--|:--|:--|
+| Large-edge tick labels overlapped | `figure_clln_scaling_pilot` | Medium | Shortened 1,152 and 2,048 to 1.2k and 2.0k | Resolved |
+| Pilot could be mistaken for confirmation | `figure_clln_scaling_pilot` | High | Added an explicit five-task, one-draw exploratory label | Resolved |
+| Slope title did not name its comparator | Panel (a) | Medium | Named static calibration in the title | Resolved |
+| Color-only distinctions could fail in print | All panels | Medium | Added distinct markers and line styles; inspected the rendered PNG | Resolved |
+| Vector editability and font embedding | SVG and PDF | Medium | Kept live SVG text and verified embedded DejaVu Sans in the PDF | Resolved |
+
+Rendered inspection: no clipped labels, legend overlap, panel overlap, or
+detached source note at 2,556-by-778 PNG resolution. The next QA pass replaces
+the pilot source with the frozen multi-task, multi-device confirmation without
+changing the plot grammar.
+