# Convolutional HFA baseline protocol ## Status and claim boundary This protocol was frozen before observing any convolutional hierarchical-FA accuracy endpoint. It adds a matched local-learning baseline after the hierarchical oracle localized the ResNet bottleneck to spatial child-error fields. HFA is not an SDIL novelty claim: recursive random feedback is prior art, and a strong HFA result cannot rescue the failed frozen Oral-A A3 gate or open its sealed A4 test panel. The implementation follows the actual option-A residual DAG. Every learned forward convolution has an independent fixed 3x3 feedback tensor; shortcut adjoints are parameter-free, and ReLU and BatchNorm Jacobians are local. The feedback code never reads a downstream forward convolution. In an audit-only symmetric test, setting the feedback tensors to the forward tensors and the readout feedback to the negative readout transpose reproduces hidden negative gradients to below `2e-12` relative error and the exact-BP update to below `2e-7` absolute error. Actual experiments never make this copy. ## HFA-S1: bounded short screen Use the frozen Oral-A development split and the A2b setting: seed-0 ResNet-20, the first 10,000 post-split training examples, 5,000 validation examples, 20 epochs, batch 128, ordinary CIFAR augmentation, cosine decay without warmup, momentum 0.9, weight decay `1e-4`, and final validation evaluation only. Output learning rate is 0.1. Cross hidden learning rate `{0.01, 0.03, 0.1}` with feedback scale 1 and the single predeclared feedback seed derived from model seed 0. A 32-example training-prefix alignment probe is diagnostic only. Select maximum final validation accuracy, then lower estimated MACs, then lower hidden learning rate. The short screen opens one full validation run only if the selected trajectory is finite and reaches at least 50% validation accuracy. For interpretation, the already observed matched short endpoints are DFA `37.16%`, failed-v1 SDIL `41.98%`, and BP `74.94%`; these are comparisons, not selectable thresholds. ## HFA-S2: full validation baseline If HFA-S1 passes, train the selected HFA setting for 200 epochs on all 45,000 development-training examples. Copy the A1 schedule exactly: batch 128, momentum 0.9, weight decay `1e-4`, output base rate 0.1, and hidden base rate selected by HFA-S1, with 10x drops at epochs 100 and 150 and no warmup. Evaluate the same 5,000-example validation split only at the end. No recovery grid is allowed. This is a baseline endpoint, not an advancement test for SDIL. A finite result at or above 80% is considered a strong matched local baseline that any learned hierarchical SDIL variant must compare against. A weaker result remains reportable and cannot trigger additional HFA tuning. Neither outcome permits test-set evaluation. ## Accounting and stop rules - Record fixed feedback parameters, feedback-convolution MACs, local correlation MACs, peak memory, wall time, and zero causal queries. - All three HFA-S1 jobs must use the same clean git commit and must not touch CIFAR-10 test data. - No feedback scale, seed, optimizer, architecture, or extra learning rate is added after the S1 endpoints are read. - HFA-S2, if opened, copies the selected S1 hidden rate mechanically and does not select on intermediate validation accuracy. ## Audited outcome (2026-07-22) All three HFA-S1 trajectories are finite and test-free. Validation accuracy increases monotonically over the frozen hidden-rate grid: `39.64%` at 0.01, `41.58%` at 0.03, and `43.52%` at 0.1. The selected 0.1 run has early-third teaching alignment `0.040406`, zero causal queries, 267,904 fixed feedback parameters, and estimated work `2.4242e13` MACs. The selected endpoint exceeds matched DFA by `6.36` points and the failed-v1 short SDIL endpoint by `1.54` points, but misses the preregistered 50% HFA-S2 threshold by `6.48` points. Status is `selected_full_closed`; the 200-epoch HFA run is not launched, no extra HFA setting is allowed, and CIFAR-10 test remains untouched.