From 52a734aa8736cd8edf95f3fbf595014f7559e6f5 Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Mon, 10 Aug 2026 11:04:06 -0500 Subject: docs: add context-free SDIL project deck --- slides/visual-contract.md | 14 ++++++++++++++ 1 file changed, 14 insertions(+) create mode 100644 slides/visual-contract.md (limited to 'slides/visual-contract.md') diff --git a/slides/visual-contract.md b/slides/visual-contract.md new file mode 100644 index 0000000..86a7ffc --- /dev/null +++ b/slides/visual-contract.md @@ -0,0 +1,14 @@ +# SDIL project introduction deck: visual contract + +- **Artifact:** Seven-slide, 16:9 project introduction deck. +- **Audience:** Machine-learning researchers with no prior SDIL context. +- **Core claim:** A local learner should use the soma-unpredicted component of a mixed apical signal; this residualization protects an inherited scalable credit path from predictable traffic. +- **Reader questions:** Why is raw feedback insufficient? What exactly is new? Is the update BP-free? Is residualization necessary? Does the combined method scale? Which evidence is controlled or synthetic? +- **Evidence layers:** problem and mechanism (slides 2–3), causal ablation (slide 4), standard-depth scaling and cost (slide 5), dynamical-task evidence (slide 6), attribution and boundary (slide 7). +- **Source data:** `results/figs/figure3_innovation.png`, `results/figs/figure5_bci_v2.png`, `results/oral_a_dynamic_scaling_v2_gate.json`, and the evidence-bound manuscript. +- **Statistics:** Five seeds for the controlled traffic and ResNet panels; six task clusters by five model seeds for the synthetic BCI panel. Values shown are audited means or paired outcomes already reported in the manuscript. +- **Visual grammar:** Direct mechanism diagrams, two result figures, and editable line charts. SDIL is blue, reciprocal KP is green, DFA is orange, BP is dark gray. +- **Exact method labels:** SDIL, raw apical signal, somatic prediction, innovation, reciprocal KP, BP, DFA, local update, neutral observation. +- **Output:** Editable PPTX, PDF export, generation source, and rendered QA contact sheet. +- **Claim boundary:** Clean scaling is attributed to reciprocal KP; SDIL-specific evidence is robustness under predictable mixed traffic and the synthetic BCI mechanism test. + -- cgit v1.2.3