8 SBFoundation as a Research Platform
Author: Todd B. Adams Companion to: Research Proposal — Dynamic Heterogeneous Multiplex Networks for Factor-Based Systemic Risk & Market Phase Transitions
8.1 What this part establishes
The proposal argues that systemic risk is an emergent property of a multi-layered financial network, and that a spatial-temporal graph model can detect its phase transitions. We hold that testing a claim that strong credibly requires more than a notebook and a static academic panel: it requires a live, point-in-time-correct, survivorship-adjusted, cost-aware, executable empirical instrument. This part of the research programme documents such an instrument. It runs the full chain from raw vendor data to real paper-broker fills each night; it already implements the proposal’s stock–factor layer in production; it already carries correlation-network and crowding machinery; and it has already stress-tested — and, on the simplest hypothesis, falsified — a published connectedness methodology on its own universe. The chapters that follow are the evidence for these statements, tied section by section to the proposal.
We frame the platform throughout as the instrument, not the subject: its point-in-time, survivorship-corrected, cost-aware, and overfitting-audited discipline is what makes a surviving result believable, and that is the property these chapters are written to demonstrate.
8.2 Reading order
The chapters are numbered as a reading order. Each is short and cross-links into the deeper appendices rather than restating them.
| # | Chapter | Question it answers | Proposal § |
|---|---|---|---|
| 00 | Overview (this chapter) | What is this evidence package and why does it exist? | §1 |
| 01 | Platform as research substrate | Why is a live end-to-end trading platform the right instrument for this research? | §1, §3 |
| 02 | The end-to-end pipeline | Does it really run data → live trading, reproducibly? | §3 |
| 03 | The multiplex data substrate | Can it source the proposal’s three network layers? | §5 |
| 04 | The factor layer as multiplex Layer 1 | Is the bipartite stock–factor layer hypothetical, or built? | §3, §6 |
| 05 | Systemic-risk & crowding groundwork | Is there prior, aligned network work here? | §2, §3 |
| 06 | The integrated target architecture | Where does the Supra-Laplacian / spatial-temporal graph engine mount? | §3 |
| 07 | Gap analysis & research roadmap | What is built versus proposed, honestly? | §3, §5 |
| 08 | Validation & anti-overfitting | How are network claims protected from self-deception? | §6 |
| 09 | Reproducibility & experiment infrastructure | Is each experiment auditable and repeatable? | §3 |
| 10 | Literature bridge | How do the proposal’s papers and the platform’s reference library reconcile? | §2 |
8.3 What these chapters are written to demonstrate
- The research question has platform-grounded precedent — the stock–factor layer, crowding, and a falsified connectedness spike already exist here (chapters 01, 04, 05, 10).
- The platform supports the research — substrate, mount points, honest gaps, and validation rigour (chapters 03, 06, 07, 08, 09).
- The chain runs end to end, data to live trading — a production pipeline terminating in real broker fills, not a simulator (chapters 02, 09).
8.4 How build status is stated
Every forward-looking claim is labelled in prose so that nothing is over-claimed. We say a capability is implemented when it runs in production today and is traceable to committed code and nightly runs; is partially built when the substrate exists and is adjacent but the specific capability is incomplete; and is proposed — not yet built when it is a research extension. The proposed extensions are the research programme’s forward agenda. The single canonical inventory of what is built, partial, or absent — and, crucially, which absences are deliberate design choices rather than gaps — is the platform capability map.