What If Your Life Had Multiple Possible Versions? Building an Auditable Counterfactual Self Architecture

Can AI simulate alternative versions of a person without confusing historical evidence, plausible assumptions, and fictional narratives?

Most AI systems are designed to predict what happens next.

But there is another, more difficult problem:

What could have happened if one important decision had been different?

What if Alan Turing had accepted John von Neumann's offer and stayed at Princeton in 1938?

What if he had remained at the National Physical Laboratory and continued working on the ACE computer?

What if the prosecution in 1952 had never happened?

These are not ordinary prediction questions. They involve incomplete evidence, alternative causal paths, uncertain outcomes, and the danger of turning plausible fiction into apparent historical fact.

This is the problem behind Counterfactual Self Architecture (CSA).

I recently published the research framework on PhilPapers:

"Read the CSA paper on PhilPapers" (https://philpapers.org/rec/ALHCSA)

1. The problem: AI is good at storytelling, but storytelling is not evidence

Give a generative AI model a person's biography and ask it to imagine an alternative life.

It will probably produce a convincing narrative.

But what does that narrative actually represent?

• A historically supported possibility?
• A plausible extrapolation?
• An unsupported assumption?
• Or simply a coherent story generated by a language model?

These categories are fundamentally different.

A narrative can be internally consistent while being historically or causally unjustified.

CSA starts from this distinction: counterfactual coherence must not be confused with counterfactual warrant.

1. CSA: A different way to structure possible selves

Counterfactual Self Architecture is a framework for representing alternative versions of a person's trajectory.

Instead of generating one unrestricted alternative biography, CSA organizes the process around explicit reference information, interventions, and uncertainty.

Its architecture distinguishes several important elements:

Reference Record

A structured representation of what is known about the subject.

Identity and Continuity Constraints

A way to distinguish characteristics that remain stable from those that may change across alternative scenarios.

Divergence Points

Explicit interventions that define where an alternative trajectory separates from the reference history.

Counterfactual Branches

Alternative trajectories generated from those interventions.

Evaluation and Audit

A mechanism for examining whether the generated scenario is supported, coherent, or speculative.

The objective is not to produce the most entertaining alternative life.

It is to make the assumptions behind each alternative visible and auditable.

1. The critical technical component: ICC

One of the central challenges is deciding what the system actually knows about a person.

CSA uses an evidence-status approach called ICC:

Status| Meaning
Preserved| Supported information retained across the scenario
Variable| Information that may change under the intervention
Unknown| Insufficient evidence
Disputed| Credible evidence or interpretations remain in disagreement

The distinction between Unknown and Disputed is especially important.

Unknown means that the available information is insufficient.

Disputed means that there is a genuine disagreement that should remain visible rather than being silently resolved by the model.

This creates an important engineering principle:

The system must be allowed to abstain.

A model should not be forced to invent certainty simply because a user expects a complete narrative.

1. Why Alan Turing is an interesting stress test

A natural next step is to examine CSA through a historical case study.

Alan Turing offers an unusually interesting example because his biography contains several documented decision points.

Consider three possible interventions:

Scenario A — Princeton, 1938

Turing accepts von Neumann's offer instead of returning to Cambridge.

The system can establish the historical decision and explore possible institutional consequences. However, it cannot confidently determine how his wartime contribution or later career would have changed.

Scenario B — The ACE project

Turing remains at the National Physical Laboratory after 1948.

This scenario raises questions about his potential role in the development of early computing. But the fact that he remained at NPL would not, by itself, establish that he would have completed the ACE project sooner or led it successfully.

Scenario C — The 1952 prosecution

The prosecution does not occur.

This intervention changes an important part of the historical record. But it does not prove that Turing would have lived longer or that every other institutional consequence would have disappeared.

These scenarios reveal why counterfactual modeling needs more than a powerful language model.

It needs explicit boundaries around what can and cannot be inferred.

1. Three extensions worth exploring

The Turing case also points toward three possible extensions of the CSA framework.

A. Archival Subject Mode

Most personal AI systems assume that the subject is alive and can provide additional information.

Historical figures create a different problem.

Their available information comes from archives, public records, correspondence, institutional documents, and historical research.

Archival Subject Mode would explicitly distinguish historical subjects from living participants and from research involving deceased human participants.

B. Archival Prospective Simulation

A particularly interesting possibility is to simulate a historical person's future from a specific date using only the information available at that time.

For example:

What might Turing's next decade have looked like from the summer of 1950?

This requires a strict historical knowledge cutoff.

The system must not use his 1952 morphogenesis publication as information available to a simulation supposedly operating in 1950.

And if the scenario depicts him working in 1955, it must explicitly state the survival assumption required to reach that date.

This is not historical prediction. It is a constrained simulation of possible futures from a frozen historical reference point.

C. Causal Firewall

Some outcomes depend on complex systems that cannot be reliably reconstructed from individual biography alone.

Political institutions, military decisions, security policies, and economic conditions are examples.

A Causal Firewall would prevent the model from converting weak contextual evidence into confident individual-level causal claims.

The model could describe possible outcomes, but it should not select one as established without sufficient support.

1. The deeper engineering question

CSA raises a broader question for AI architecture:

Can we build generative systems that represent uncertainty as part of their structure rather than treating it as a weakness to hide?

This is relevant beyond historical simulations.

Possible applications include:

• Personal decision-support systems.
• Digital identity and personal history modeling.
• AI-assisted scenario planning.
• Historical research.
• Long-term career and life-path exploration.
• Auditable simulations of alternative decisions.

However, these applications should not be confused with a validated product. CSA is a proposed research framework, and its operational effectiveness still requires implementation, independent evaluation, and empirical testing.

1. From generating stories to auditing possibilities

The most interesting direction for generative AI may not be generating increasingly realistic fictional scenarios.

It may be developing systems that can explain:

1. What is known.
2. What has been changed.
3. What remains uncertain.
4. Which conclusions follow from the intervention.
5. Where the system must stop making claims.

That is the central ambition of Counterfactual Self Architecture.

The goal is not to make AI better at imagining what could have happened. It is to make AI more accountable for explaining why a particular possibility deserves consideration.

Research paper: "Counterfactual Self Architecture (CSA) — PhilPapers" (https://philpapers.org/rec/ALHCSA)

Author: Seyed Alireza Alhosseini Almodarresieh
Independent Researcher
"https://almodarresieh.github.io/" (https://almodarresieh.github.io/)

An open research direction: How should an AI system distinguish a plausible counterfactual from a convincing but unsupported story?