Reproduce D · OTT/GTC

Reproduce Paper D: OTT and the GTC manifold runtime

William Ken Ohara Stewart (NagusameCS Independent Research)

HyperTensor Project · April 2026 · Paper D (HTML) · Paper D (PDF) · repro tree

Scope

Reproduces the 97x batched-Jacobi gain, the four-model TwoNN intrinsic-dimension survey, the curvature-warp 0/12 cross-model null, and the HJB pre-training feasibility result.

Hardware target

Prerequisites

1. Batched-Jacobi micro-benchmark

.\build_host\geodessical.exe $model `
    --axex-jacobi --axex-jacobi-batch 32 -p "warm" -n 8 --temp 0

Expected: a 97x speedup over the per-element Jacobi reference.

2. TwoNN intrinsic-dimension survey

python scripts\axiom_survey.py `
    --models smollm2-135m,gemma-4-e2b,phi-3.5-mini,llama-3.1-8b `
    --axiom-samples 256 --axiom-probe 1024

Expected k_int at 95 percent variance: 17 (SmolLM2), 25 (Gemma-4), 11 (Phi-3.5), about 1682 for Llama-3.1-8B (note the 8B value is attention-only; FFN sits much higher).

3. Curvature warp cross-model null

python scripts\curvature_warp_eval.py

Expected: 0 of 12 cross-model arms exceed the equivariance gate. This is the negative result reported in Paper D and it is the correct outcome.

4. HJB pre-training feasibility

python scripts\hjb_residual_pretrain.py --steps 200

Expected: HJB residual decreases monotonically and converges within the 200-step budget. Outputs land in docs/figures/paper-d/hjb_feasibility/.

Outputs

Tolerances