Jaehong Oh.
Robotics · AI · Mathematics
Robotics engineer and AI researcher working at the intersection of learned organisation, representation identity, and delay-robust embodied control. The current ULR programme tests what models genuinely share, what makes representations identical, and which organisational claims survive typed baselines. Negative results and boundary conditions are published alongside what survives.
Highlights
Current focus: Unified Latent Representation — Main research · Canon 24. Canon 24 records an ontology verdict of NO: no additional neural-specific ULR object is currently established. Read the founding Motivation and its mathematical self-corrections to see why that negative verdict sharpens rather than ends the programme. The SCC programme is preserved as historical · archived programme, and the original ONN + ORTSF programme is marked Audited · archived programme after its strong higher-order claim was narrowed to a scoped boundary. Its original framing remains available as the published 2026 paper.
Recent writing
ULR evidence map →ULR Current Research Status
ULR is the current Main research programme. It does not claim to have discovered a separate neural ontology; it rigorously separates Sharing, Identity, Role, and Formation and tests the residual left after those distinctions. The current ontology verdict is NO, and Canon 24, LEDGER 105, and PROGRESS 31 define the canonical state.
Why ULR? — Motivation and Self-Correction
The motivation for ULR is not a belief in one immense hidden latent entity. It is to determine precisely whether and when a local readout is insufficient, whether organisation across conditions genuinely constrains unobserved responses, and whether that constraint survives the strongest typed baselines.
ULR Canon 24 — Canonical State
Canon 24 does not adopt a separate neural-specific ULR ontology. It preserves 6 empirical atoms, 44 gauge and assembly atoms, 3 observer-boundary atoms, and 1 small-neural application, while retaining Z0 typed pluralism as the winner for the current registry.
From SCC to ULR — The Main Research Transition
On July 24, 2026, the research focus shifted from SCC to ULR alone. SCC's CV-1.17 results and audit record remain in the historical layer, but ULR's Sharing, Identity, Role, and Formation programme now governs existence judgments and execution priorities.
Research programme
All threads →An ongoing programme on learned organisation, representation identity, observer-relative role, and embodied control — with canonical claims, retractions, and open gates kept visibly separate.
Main research · Canon 24
Unified Latent Representation
The current Main programme on what learned systems share, what makes a representation identical, how learning differs from inference for an observer, and when organisation genuinely forms. Its central result is a disciplined negative ontology verdict, not a claim that a universal latent object has been found.
Active · book in progress
Mathematical foundations
RelationWorld Theory — a mathematically rigorous theory of discrete gauge structure on finite graphs, developing analogues of Yang–Mills, Uhlenbeck compactness, and Cheeger spectral geometry in a purely combinatorial setting.
Audited · scalar single-mode result
Delay-robust control
Delay-aware control after audit: a scoped sufficient condition for one additive delayed scalar recurrence, explicitly decoupled from ontology cohomology. Coupled multimode dynamics, physical gain mapping, and system-level certification are not yet established.