Which programming languages does this skill utilize?

The skill provides a multi-interpreter approach, using Julia (ACSets) for schema modeling, Python (DuckDB) for profile building, Ruby for condensed mathematics integration, and Hy for behavioral pattern extraction.

How is the fidelity of the surrogate measured?

Fidelity is measured across four key metrics: topic prediction (>85%), semantic similarity (>90%), style consistency (>88%), and value alignment (>92%), targeting a weighted average of over 90%.

What is a Cognitive Surrogate in the context of this skill?

A Cognitive Surrogate is a high-fidelity model that learns the generative grammar of a subject's cognition rather than just imitating surface patterns, allowing for authentic response generation and trajectory prediction.

What ethical safeguards are included in this skill?

The skill enforces explicit consent protocols, mandatory disclosure of surrogate-generated content, refusal boundaries for high-stakes decisions, and a subject-controlled kill switch for model invalidation.

Cognitive Surrogate Engine

Name: Cognitive Surrogate Engine
Author: plurigrid

byplurigrid

•

数据科学与机器学习

Constructs high-fidelity psychological models from interaction patterns to predict intellectual trajectories and maintain authentic voice consistency.

关于

The Cognitive Surrogate skill is a sophisticated modeling engine designed to build 'derivational continuations' of cognition rather than simple surface imitations. By utilizing a multi-language stack including Julia for category-theoretic structures and Python for data extraction, it enables developers to create psychological profiles with over 90% fidelity. This skill is particularly useful for researchers and developers building advanced agentic systems that require deep persona consistency, ethical boundary modeling, and behavioral prediction based on structured interaction corpora.

主要功能

2 GitHub stars
Automated value and interest extraction from DuckDB interaction corpora
High-fidelity psychological modeling with >90% accuracy targets
Comprehensive fidelity metrics for style, values, and semantic similarity
Category theory-based profile structuring using ACSets
Multi-language integration supporting Julia, Python, Ruby, and Hy

使用场景

Validating AI agent behavior against specific human interaction datasets
Building authentic digital twins for longitudinal psychological research
Predicting subject-specific cognitive trajectories in educational simulations

关于

主要功能

2 GitHub stars
Automated value and interest extraction from DuckDB interaction corpora
High-fidelity psychological modeling with >90% accuracy targets
Comprehensive fidelity metrics for style, values, and semantic similarity
Category theory-based profile structuring using ACSets
Multi-language integration supporting Julia, Python, Ruby, and Hy

使用场景

Validating AI agent behavior against specific human interaction datasets
Building authentic digital twins for longitudinal psychological research
Predicting subject-specific cognitive trajectories in educational simulations