diff options
Diffstat (limited to 'visual-composer')
| -rw-r--r-- | visual-composer/physical-hardware-evidence.md | 40 | ||||
| -rw-r--r-- | visual-composer/qa-ledger.md | 13 |
2 files changed, 53 insertions, 0 deletions
diff --git a/visual-composer/physical-hardware-evidence.md b/visual-composer/physical-hardware-evidence.md new file mode 100644 index 0000000..b271127 --- /dev/null +++ b/visual-composer/physical-hardware-evidence.md @@ -0,0 +1,40 @@ +# Visual contract: hardware-realistic CLLN evidence + +- **Artifact:** three-panel quantitative result figure. +- **Target venue / format:** ICLR two-column paper, full-width figure. +- **Core claim:** local innovation subtraction restores nonlinear CLLN + learning under published component imperfections and remains effective with + nonideal local sampling. +- **Reviewer question:** does the method survive component mismatch, sampler + mismatch, noise, stale refresh, and their combination at the task endpoint? +- **Evidence layer:** hardware-realistic simulation; no fabricated-chip claim. +- **Source data:** + `results/physical_bias/p5_full_grid_bias_crossover.json`, + `results/physical_bias/p9_grid_correlated_autozero.json`, and + `results/physical_bias/p8_spice_autozero_primitive.json`. +- **Statistics / uncertainty:** four device draws are averaged within each of + 40 tasks; tasks are resampled for percentile 95% bootstrap intervals. +- **Figure prototype:** horizontal method comparison, mismatch response curves, + and horizontal nonideality comparison. +- **Panel map:** + - (a) nonlinear CLLN final error across clean, raw, calibration, + overclamping, SDIL, and their combination; + - (b) final error against measured local sampling-error RMSE for pedestal + and gain mismatch sweeps; + - (c) final error under common pedestal, sampling noise, stale neutral + refresh, and combined nonidealities. +- **Exact label inventory:** nonlinear CLLN, component errors, sample-path + mismatch, residual sampling error, nonideal local sampling, final + classification error. +- **Caption role:** identify the published component-error scale, the local + correlated-double-sampling operation, task/device counts, and the boundary + between simulation and fabricated hardware. +- **Manuscript placement:** Part 3, after the digital scaling result. +- **Output formats:** editable SVG, vector PDF, PNG preview, analysis JSON, and + source CSV. +- **Traceability:** every plotted aggregate is regenerated by + `experiments/plot_physical_hardware_evidence.py`; the SPICE primitive is + carried in the analysis manifest and reserved for supplementary evidence. +- **Constraint:** circuit-solver failures remain classification failures. + Sampler RMSE excludes the missing diagnostic value on failed solves, while + the task endpoint includes every trial. diff --git a/visual-composer/qa-ledger.md b/visual-composer/qa-ledger.md index 319c1f2..c9e66e5 100644 --- a/visual-composer/qa-ledger.md +++ b/visual-composer/qa-ledger.md @@ -13,3 +13,16 @@ 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. +## Hardware-realistic CLLN figure + +| Issue | Artifact | Severity | Fix | Status | +|:--|:--|:--|:--|:--| +| Method and condition labels collided | Panels (a) and (c) | High | Replaced vertical bars with horizontal bars and single-line labels | Resolved | +| Different mismatch units were not directly comparable | Panel (b) | High | Used measured residual local-rate RMSE as the common x-axis and retained mismatch family as series | Resolved | +| Zero-error conditions were visually ambiguous | Panels (a) and (c) | Low | Kept a small x-axis margin below zero so zero-valued error bars remain visible | Resolved | +| Generic SPICE primitive could be read as a full-circuit simulation | Figure scope | High | Excluded it from the main plotted panels and recorded its limited scope in the analysis and visual contract | Resolved | +| Color-only distinctions could fail in print | Panel (b) | Medium | Added distinct circle and diamond markers | Resolved | + +Rendered inspection: no clipped labels, tick-label collision, legend overlap, +or panel overlap at 2,560-by-765 PNG resolution. SVG text remains editable and +the PDF uses embedded TrueType fonts. |