On the Origin of Samples: Attribution of Output to a Particular Algorithm

TL;DR

This paper formalizes the challenge of attributing biological samples to their originating algorithms, demonstrating that, under certain conditions, the problem is fundamentally unsolvable, impacting fields like astrobiology and AI safety.

Contribution

It introduces a formal framework for sample attribution and proves the problem's inherent unsolvability in the general case when no computational limits are assumed.

Findings

The attribution problem is formally defined.

Proves the problem is unsolvable without computational constraints.

Implications for astrobiology and AI safety.

Abstract

With unprecedented advances in genetic engineering we are starting to see progressively more original examples of synthetic life. As such organisms become more common it is desirable to be able to distinguish between natural and artificial life forms. In this paper, we present this challenge as a generalized version of Darwin's original problem, which he so brilliantly addressed in On the Origin of Species. After formalizing the problem of determining origin of samples we demonstrate that the problem is in fact unsolvable, in the general case, if computational resources of considered originator algorithms have not been limited and priors for such algorithms are known to be equal. Our results should be of interest to astrobiologists and scientists interested in producing a more complete theory of life, as well as to AI-Safety researchers.