document confirmed digital scaling evidence

2 files changed, 65 insertions, 45 deletions

diff --git a/README.md b/README.md
index 6d4204d..9cae3cb 100644
--- a/README.md
+++ b/README.md
@@ -27,9 +27,10 @@ three experimental parts are:
 1. add the same innovation subtraction to digital Dual Propagation,
    Equilibrium Propagation, standard coupled learning, and overclamped coupled
    learning;
-2. scale a digital CLLN from 32 to 2,048 learnable edges under fixed component
-   imperfection, comparing clean learning, same-RMS zero-mean noise, raw
-   imperfection, static calibration, and SDIL;
+2. scale a digital Contrastive Local Learning Network (CLLN) from 32 to 2,048
+   learnable edges under fixed component imperfection, comparing clean
+   learning, same-RMS zero-mean noise, raw imperfection, static calibration,
+   and SDIL;
 3. test the update in the nonlinear CLLN with published component-error scales,
    nonideal local correlated-double-sampling, and a SPICE check of the local
    sample/hold/subtract primitive.
@@ -49,16 +50,20 @@ The completed transfer evidence is: Dual Propagation recovers from 9.40% to
 82.92% validation accuracy against 82.86% clean; EP recovers from 31.38% to
 74.52% against 76.26% clean; and the nonlinear 4-by-4 CLLN recovers from
 25.42% mean classification error to 0% on 120 untouched task/device pairs.
-The first fully confirmed digital
-CLLN size contains 40 tasks and three device draws: at 32 edges, clean and
-SDIL have 0% error, raw imperfection has 34.69%, same-RMS noise has 0.73%, and
-static calibration has 6.15%. The remaining five sizes are running under the
-frozen protocol.
+The confirmed digital CLLN ladder contains 40 tasks, three device draws, six
+sizes, and five methods. From 32 to 2,048 edges, static-calibration error grows
+from 6.15% to 27.19%, while SDIL grows from 0% to 2.29% against 1.56% clean at
+the largest size. SDIL reduces the excess final-error growth slope by 96.2%
+and stable-failure growth by 89.5% relative to static calibration. At 2,048
+edges it uses 23.3% fewer local updates to the censored target but 52.8% more
+local scalar reads because each update includes a neutral measurement.
 
 Start with [`THREE_PART_EVIDENCE.md`](THREE_PART_EVIDENCE.md) for the evidence
 map and [`CLLN_SCALING.md`](CLLN_SCALING.md) for the frozen scaling protocol.
 The current hardware-realistic figure is
 [`figure_physical_hardware_evidence_confirmation.pdf`](results/figs/figure_physical_hardware_evidence_confirmation.pdf).
+The confirmed digital scaling figure is
+[`figure_clln_scaling_confirmation.pdf`](results/figs/figure_clln_scaling_confirmation.pdf).
 
 The standard-ResNet stability branch additionally uses a fast paired neutral
 observation to project any *remaining* affine neutral residual off current
diff --git a/THREE_PART_EVIDENCE.md b/THREE_PART_EVIDENCE.md
index e3642e1..eef1477 100644
--- a/THREE_PART_EVIDENCE.md
+++ b/THREE_PART_EVIDENCE.md
@@ -5,7 +5,8 @@
 Somato-dendritic innovation is a local correction for predictable teaching-
 channel error. It transfers across digital local learners, preserves coupled
 learning as the number of imperfect components grows, and can be implemented
-with local sampling and subtraction in a hardware-realistic CLLN.
+with local sampling and subtraction in a hardware-realistic Contrastive Local
+Learning Network (CLLN).
 
 The method remains:
 
@@ -26,16 +27,15 @@ learning rule without replacing that rule.
 |:--|:--|--:|--:|--:|--:|:--|
 | Dual Propagation | CIFAR-10 miniCNN, 5 seeds | 82.86% | 9.40% | — | 82.92% | Passed frozen confirmation |
 | Equilibrium Propagation | FashionMNIST ConvHopfield, 5 seeds | 76.26% | 31.38% | 67.90% | 74.52% | SDIL beats raw in every seed; strict gate failed because one seed favors calibration |
-| Digital coupled learning | released ring tasks, size ladder pilot | reported by size | 37.5–62.5% error | 2.5–30.0% error | 0–7.5% error | Full confirmation running |
-| Overclamped coupled learning | released ring tasks, size ladder pilot | 0–2.5% error | 25–50% error | — | 0–2.5% error | Clean-only time constant selected before biased endpoints |
+| Digital coupled learning | 32-edge ring tasks, 40 tasks × 3 draws | 100.00% | 65.31% | 93.85% | 100.00% | Passed frozen confirmation |
+| Overclamped coupled learning | 32-edge ring tasks, 40 tasks × 3 draws | 91.88% | 66.88% | — | 91.98% | Passed frozen confirmation |
 
 Sources:
 
 - `results/contrastive_bias/c1_gate.json`
 - `results/ep_bias/c1_gate.json`
-- `results/coupled_ladder/p1_imperfection_pilot.json`
-- `results/coupled_ladder/p1_bias_baseline_pilot.json`
-- `results/coupled_ladder/p1_overclamp_selected_pilot.json`
+- `results/coupled_ladder/p2_confirm_side4.json`
+- `results/coupled_ladder/p3_overclamp_side4.json`
 
 The Dual Propagation result establishes strong transfer. The EP result shows
 transfer with a visible remaining clean gap and seed variance. Coupled learning
@@ -48,34 +48,44 @@ The periodic grid ladder uses side lengths `4, 8, 12, 16, 24, 32`, or 32 to
 initial gate field, and component draw. Size-dependent update exposure is
 selected from ideal coupled learning only.
 
-Pilot final classification error:
+Confirmed final classification error:
 
 | Edges | Clean | Same-RMS noise | Raw | Static calibration | SDIL |
 |--:|--:|--:|--:|--:|--:|
-| 32 | 0.0% | 0.0% | 50.0% | 2.5% | 0.0% |
-| 128 | 0.0% | 0.0% | 62.5% | 2.5% | 0.0% |
-| 288 | 2.5% | 5.0% | 52.5% | 2.5% | 2.5% |
-| 512 | 2.5% | 10.0% | 47.5% | 5.0% | 2.5% |
-| 1,152 | 2.5% | 17.5% | 50.0% | 10.0% | 7.5% |
-| 2,048 | 2.5% | 22.5% | 37.5% | 30.0% | 2.5% |
-
-The raw learner has a large error floor at every size. Static calibration works
-on small grids and degrades on larger grids. Relative to static calibration,
-SDIL reduces the pilot excess-error growth slope by 88.1%; the paired
-task-bootstrap slope-difference interval is positive. At 2,048 edges, SDIL
-closes the full raw-to-clean final-error gap and reaches stable zero error on
-80% of task runs, versus 0% for raw and static calibration.
-
-The tuned overclamp pilot gives the same structural result. Clean overclamping
-ends at 0–2.5% error across the ladder. Imperfect overclamping ends at 25–50%,
-while overclamping plus SDIL ends at 0–2.5%. SDIL therefore combines with the
-strong-clamp correction.
+| 32 | 0.00% | 0.73% | 34.69% | 6.15% | 0.00% |
+| 128 | 1.25% | 2.60% | 37.92% | 6.46% | 1.25% |
+| 288 | 1.88% | 8.02% | 48.12% | 6.35% | 1.88% |
+| 512 | 2.50% | 11.35% | 47.71% | 9.58% | 2.50% |
+| 1,152 | 2.50% | 19.38% | 48.44% | 18.13% | 2.92% |
+| 2,048 | 1.56% | 26.67% | 49.90% | 27.19% | 2.29% |
+
+The raw learner has a large error floor at every size. Same-RMS noise and
+static calibration both degrade as the grid grows. Relative to static
+calibration, SDIL reduces the excess final-error growth slope by 96.2% (paired
+task-bootstrap 95% interval 93.0% to 98.5%) and the excess stable-failure
+growth slope by 89.5% (74.8% to 96.6%). Its excess error-AUC slope is slightly
+negative, eliminating the corresponding positive static-calibration slope.
+At 2,048 edges, SDIL closes 98.5% of the raw-to-clean final-error gap and
+reaches stable zero error on 82.5% of trials, versus 0% for raw, 23.3% for
+static calibration, and 87.5% for clean.
+
+The improvement has a measurement cost. At 2,048 edges SDIL uses 3,487 local
+updates to the censored stable-zero target on average, versus 4,548 for static
+calibration. Counting task and neutral edge measurements, SDIL uses 14.28
+million local scalar reads versus 9.35 million for static calibration, a
+1.53-times ratio. Runs that miss stable zero receive the frozen 600-epoch
+horizon in both cost summaries.
+
+The overclamp confirmation is complete through 1,152 edges. At that size,
+clean overclamping, imperfect overclamping, and overclamping plus SDIL end at
+1.25%, 45.31%, and 1.25% error. The 2,048-edge endpoint is still running.
 
 The publication figure and data are:
 
-- `results/figs/figure_clln_scaling_pilot.pdf`
-- `results/coupled_ladder/p1_scaling_analysis.json`
-- `results/coupled_ladder/p1_scaling_source.csv`
+- `results/figs/figure_clln_scaling_confirmation.pdf`
+- `results/figs/figure_clln_scaling_confirmation_resources.pdf`
+- `results/coupled_ladder/p2_scaling_analysis.json`
+- `results/coupled_ladder/p2_scaling_source.csv`
 
 The mechanism statement is now explicit in `THEORY.md`. For a local
 state-dependent component error, conditional subtraction removes at least as
@@ -85,9 +95,9 @@ produces an exact displaced optimum with excess objective
 `0.5 * delta^T H^+ delta`; the classification ladder tests whether this local
 effect reaches the downstream task endpoint.
 
-The pilot has five task clusters and one component draw per task and size. The
-running confirmation contains all 40 released tasks, three new component draws,
-six sizes, and five core methods: 3,600 training trajectories. Its outputs are
+The confirmation contains all 40 released tasks, three new component draws,
+six sizes, and five core methods: 3,600 completed training trajectories. Its
+outputs are
 `results/coupled_ladder/p2_confirm_side{4,8,12,16,24,32}.json`.
 
 ## Part 3: hardware-realistic simulation
@@ -96,6 +106,12 @@ This part uses the nonlinear conductance law, periodic 4-by-4 topology,
 released Figure-5 tasks and initial gates, Appendix-C component imperfections,
 and explicit local voltage-square updates.
 
+A descriptive reanalysis of released physical drift traces first checks the
+problem assumption. Per-edge local affine bias reduces held-out RMSE to 0.21
+and 0.54 of a constant-bias model in the two released task pairs. This shows a
+measured state-dependent component; it does not show SDIL training on
+fabricated hardware.
+
 The untouched confirmation uses 40 tasks and three new component draws, or 120
 trials per method:
 
@@ -126,6 +142,8 @@ Sources:
 - `results/physical_bias/p8_spice_autozero_primitive.json`
 - `results/figs/figure_physical_hardware_evidence_confirmation.pdf`
 - `results/physical_bias/p12_hardware_evidence_analysis.json`
+- `results/physical_bias/p0_state_dependence.json`
+- `results/figs/physical_bias_state_dependence.png`
 
 The hardware claim is: the full update is simulated with published device
 equations and nonideal local sampling, and its primitive sample/subtract path
@@ -143,9 +161,6 @@ has a SPICE check. A fabricated-chip demonstration remains future work.
 
 ## Remaining gates
 
-1. Complete and audit the 3,600-trajectory digital ladder confirmation.
-2. Run the selected overclamp pair on the full task/device confirmation panel.
-3. Rebuild the digital transfer and scaling figures from confirmation data;
-   the hardware-realistic figure is complete.
-4. Audit every manuscript number
-   against its source JSON.
+1. Finish the 2,048-edge overclamp endpoint and rebuild its scaling figure.
+2. Finish the frozen 256-observation static-calibration stress test.
+3. Audit every manuscript number against its source JSON.