# Emergent Causality and the Foundation of Consciousness

arXiv: https://arxiv.org/abs/2302.03189 · HTML: https://mlsanity.com/paper/2302.03189/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 26 references that are in the map.
- First posted on arXiv 7 Feb 2023.

## Builds on (most cited first, 5 of 5)

- [Shaking the foundations: delusions in sequence models for interaction and control](https://mlsanity.com/paper/2110.10819/) (2021)
- [The Optimal Choice of Hypothesis Is the Weakest, Not the Shortest](https://mlsanity.com/paper/2301.12987/) (2023)
- [Symbol Emergence and The Solutions to Any Task](https://mlsanity.com/paper/2109.01281/) (2021)
- [Computational Dualism and Objective Superintelligence](https://mlsanity.com/paper/2302.00843/) (2023)
- [Intensional Artificial Intelligence: From Symbol Emergence to Explainable and Empathetic AI](https://mlsanity.com/paper/2104.11573/) (2021)

## Built on by (most cited first, 9 of 9)

- [On the Computation of Meaning, Language Models and Incomprehensible Horrors](https://mlsanity.com/paper/2304.12686/) (2023)
- [Is Complexity an Illusion?](https://mlsanity.com/paper/2404.07227/) (2024)
- [Are Biological Systems More Intelligent Than Artificial Intelligence?](https://mlsanity.com/paper/2405.02325/) (2024)
- [Agent Identity Evals: Measuring Agentic Identity](https://mlsanity.com/paper/2507.17257/) (2025)
- [Why Is Anything Conscious?](https://mlsanity.com/paper/2409.14545/) (2024)
- [What Capable Agents Must Know: Selection Theorems for Robust Decision-Making under Uncertainty](https://mlsanity.com/paper/2603.02491/) (2026)
- [Artificial Consciousness as Interface Representation](https://mlsanity.com/paper/2508.04383/) (2025)
- [What the F*ck Is Artificial General Intelligence?](https://mlsanity.com/paper/2503.23923/) (2025)
- [A Mind Cannot Be Smeared Across Time](https://mlsanity.com/paper/2601.11620/) (2026)

## Abstract (arXiv)

To make accurate inferences in an interactive setting, an agent must not confuse passive observation of events with having intervened to cause them. The do operator formalises interventions so that we may reason about their effect. Yet there exist pareto optimal mathematical formalisms of general intelligence in an interactive setting which, presupposing no explicit representation of intervention, make maximally accurate inferences. We examine one such formalism. We show that in the absence of a do operator, an intervention can be represented by a variable. We then argue that variables are abstractions, and that need to explicitly represent interventions in advance arises only because we presuppose these sorts of abstractions. The aforementioned formalism avoids this and so, initial conditions permitting, representations of relevant causal interventions will emerge through induction. These emergent abstractions function as representations of one`s self and of any other object, inasmuch as the interventions of those objects impact the satisfaction of goals. We argue that this explains how one might reason about one`s own identity and intent, those of others, of one`s own as perceived by others and so on. In a narrow sense this describes what it is to be aware, and is a mechanistic explanation of aspects of consciousness.