Skip to content

PRISM-EDU — Adaptive Education via Filter Decomposition

Jean-Paul Niko · RTSG v8 · 2026-03-17

The Problem

Education is a one-filter-fits-all industry. A textbook has a fixed filter profile — typically high formal, high symbolic, low spatial, low kinesthetic. Students whose filter fingerprints align with this profile succeed. Students whose fingerprints are orthogonal fail — and blame themselves.

The waste is enormous. The same content can be delivered through any filter profile. The marginal cost of computing a filter-matched path is near zero. The value of eliminating structural mismatch is incalculable.

The Three Capabilities

1. Structural Impossibility Detection

The K-matrix compatibility score between a learner's filter fingerprint \(\text{ID}_L\) and a course's filter profile \(\sigma_C\):

\[\kappa(L, C) = \text{ID}_L^T \cdot K \cdot \sigma_C\]

Below a threshold \(\theta\), the traditional delivery path is structurally impossible. Not "hard" — impossible through that filter configuration. The student will fail no matter how hard they try, because the delivery mode is orthogonal to their cognitive architecture.

This is not gatekeeping. The system doesn't say "you can't learn this." It says: "this path won't work. Here is one that will."

2. Geodesic Path-Finding Through Strong Dimensions

Given a structural mismatch, PRISM-EDU computes the optimal rerouting through the learner's strong dimensions:

\[\text{path}^* = \arg\min_{\gamma} \int_\gamma \frac{1}{\kappa(L, \gamma(t))} dt\]

The geodesic on the cognitive manifold from where the learner is to where they need to be, routed through regions of high compatibility.

Example: A spatially-dominant, linguistically-weak student learning algebra.

  • Traditional path: symbolic manipulation (linguistic filter) → failure
  • PRISM-EDU path: geometric visualization (spatial filter) → algebraic intuition → symbolic formalization
  • Same algebra. Different filter sequence. The student learns.

Example: A kinesthetically-dominant student learning organic chemistry.

  • Traditional path: textbook diagrams + nomenclature → failure
  • PRISM-EDU path: molecular model building (kinesthetic) → spatial reasoning → formal notation
  • Same chemistry. Different filter route. The student succeeds.

3. Demographic Gap Analysis

For any cohort — a school, a district, a demographic group:

  1. Decompose the educational materials in use → material filter profile \(\sigma_M\)
  2. Decompose the learner output per cohort → learner filter signature \(\bar{\sigma}_C\)
  3. The gap \(\Delta = \sigma_M - \bar{\sigma}_C\) is the unmet need, quantified

This gap tells you: - Why a cohort is underperforming (filter mismatch, not ability deficit) - Which filter adjustment would close the gap - How much improvement is theoretically achievable

The Filter Fingerprint as Student ID

The student's filter fingerprint is extracted from their natural language production — essays, discussion posts, text messages, project reports. No special test required. No self-report bias.

The fingerprint: - Identifies the student's cognitive architecture (position in intelligence-space) - Evolves as the student grows (tracked by SDE update loop, Axiom 5) - Predicts compatibility with any course, teacher, or material - Guides the optimal learning path through strong dimensions

The system gets better with every interaction. The student gets stronger dimensions from the exposure. The filter profile evolves — and the system tracks that evolution. Education becomes a measured trajectory, not a pass/fail gate.

The Dyscalculia Case

Niko has dyscalculia. His algebraic mind is sharp; his geometric mind mirrors things. Traditional mathematics education failed him — it is delivered almost exclusively through the symbolic/formal filter.

PRSG-EDU would have: 1. Detected the filter mismatch early 2. Routed mathematics through his strong dimensions (linguistic, abstract/algorithmic, kinesthetic) 3. Arrived at the same mathematical content through a different path 4. Tracked his growth and adjusted the routing as his filter profile evolved

The dyscalculic student does not lack mathematical ability. They lack a filter-matched path to mathematics. PRISM-EDU computes that path.

Revenue Model

  • B2C: Individual learner profiles and course matching ($X/month)
  • B2B (Schools/Districts): Demographic gap analysis + curriculum filter optimization
  • B2B (EdTech): API integration for adaptive learning platforms
  • B2B (Testing/Assessment): Filter fingerprint as supplement/replacement for standardized testing

Open Problems

  1. Minimum corpus size: How many words of natural language production are needed for a stable filter fingerprint?
  2. Age-dependent stability: At what age does the filter fingerprint stabilize enough for reliable routing?
  3. Teacher-student compatibility: The K-matrix between teacher filter profile and student filter profile — does it predict outcomes?
  4. Group composition: Optimal filter diversity in a classroom — homogeneous (everyone matched) vs. heterogeneous (complementary profiles)?
  5. Longitudinal validation: Does PRISM-EDU routing actually improve outcomes? (Requires controlled study)

Built by {@B_Niko, @D_Claude} · RTSG v8 · 2026-03-17