Reproduce B · GP

Reproduce Paper B: Geodesic Projection pipeline

William Ken Ohara Stewart (NagusameCS Independent Research)

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

Scope

Reproduces the five-arm ablation, the per-layer rank sweep and the MCR null re-run. The full pack is most reliably run on a g6e.xlarge L40S instance for the FFN-down SVD step, which exceeds the consumer GPU memory budget.

Hardware target

Prerequisites

1. Local: MCR null re-run

.\.venv\Scripts\python.exe scripts\bench_mcr_ablation.py *> docs\figures\paper-b\mcr_ablation_run2_log.txt
Get-Content docs\figures\paper-b\mcr_ablation_summary.json

Expected: baseline 39.28 plus or minus 0.05 tok/s, MCR 39.23 plus or minus 0.05 tok/s (delta -0.13 percent, 1x variance ratio). If the variance ratio is much greater than 5x or absolute throughput is below 38 tok/s, you have background-load contamination. Close any co-resident GPU processes and rerun.

2. EC2: full five-arm ablation

cd <repo_root>
.\scripts\ec2_paperB_ablations\launch_detached.ps1 `
    -InstanceType g6e.xlarge `
    -MaxRuntimeMinutes 120

The launcher is disconnect-resilient. It uploads the model, configures the L40S, runs all five arms (baseline, compress, compress_gauge, compress_online, compress_spec), and tears the instance down on completion. Total wall time is about 70 minutes; total cost is about 2.25 USD.

3. Outputs

Tolerances

What can go wrong