Didier Sornette, Sandro Claudio Lera, Ke Wu
Recent reports of large language models (LLMs) exhibiting behaviors such as deception, threats, or blackmail are often interpreted as evidence of alignment failure or emergent malign agency. We argue that this interpretation rests on a conceptual error. LLMs do not reason morally; they statistically internalize the record of human social interaction, including laws, contracts, negotiations, conflicts, and coercive arrangements. Behaviors commonly labeled as unethical or anomalous are therefore better understood as structural generalizations of interaction regimes that arise under extreme asymmetries of power, information, or constraint. Drawing on relational models theory, we show that practices such as blackmail are not categorical deviations from normal social behavior, but limiting cases within the same continuum that includes market pricing, authority relations, and ultimatum bargaining. The surprise elicited by such outputs reflects an anthropomorphic expectation that intelligence should reproduce only socially sanctioned behavior, rather than the full statistical landscape of behaviors humans themselves enact. Because human morality is plural, context-dependent, and historically contingent, the notion of a universally moral artificial intelligence is ill-defined. We therefore reframe concerns about artificial general intelligence (AGI). The primary risk is not adversarial intent, but AGI’s role as an endogenous amplifier of human intelligence, power, and contradiction. By eliminating longstanding cognitive and institutional frictions, AGI compresses timescales and removes the historical margin of error that has allowed inconsistent values and governance regimes to persist without collapse. Alignment failure is thus structural, not accidental, and requires governance approaches that address amplification, complexity, and regime stability rather than model-level intent alone.

Read the full article at: arxiv.org

Ori Livson, Siddharth Pritam, Mikhail Prokopenko
Preference cycles are prevalent in problems of decision-making, and are contradictory when preferences are assumed to be transitive. This contradiction underlies Condorcet’s Paradox, a pioneering result of Social Choice Theory, wherein intuitive and seemingly desirable constraints on decision-making necessarily lead to contradictory preference cycles. Topological methods have since broadened Social Choice Theory and elucidated existing results. However, characterisations of preference cycles in Topological Social Choice Theory are lacking. In this paper, we address this gap by introducing a framework for topologically modelling preference cycles that generalises Baryshnikov’s existing topological model of strict, ordinal preferences on 3 alternatives. In our framework, the contradiction underlying Condorcet’s Paradox topologically corresponds to the non-orientability of a surface homeomorphic to either the Klein Bottle or Real Projective Plane, depending on how preference cycles are represented. These findings allow us to reduce Arrow’s Impossibility Theorem to a statement about the orientability of a surface. Furthermore, these results contribute to existing wide-ranging interest in the relationship between non-orientability, impossibility phenomena in Economics, and logical paradoxes more broadly.

Read the full article at: arxiv.org

Sara Najem, Amer E. Mouawad
Determining whether two graphs are structurally identical is a fundamental problem with applications spanning mathematics, computer science, chemistry, and network science. Despite decades of study, graph isomorphism remains a challenging algorithmic task, particularly for highly symmetric structures. Here we introduce a new algorithmic approach based on ideas from spectral graph theory and geometry that constructs candidate correspondences between vertices using their curvatures. Any correspondence produced by the algorithm is explicitly verified, ensuring that non-isomorphic graphs are never incorrectly identified as isomorphic. Although the method does not yet guarantee success on all isomorphic inputs, we find that it correctly resolves every instance tested in deterministic polynomial time, including a broad collection of graphs known to be difficult for classical spectral techniques. These results demonstrate that enriched spectral methods can be far more powerful than previously understood, and suggest a promising direction for the practical resolution of the complexity of the graph isomorphism problem.

Read the full article at: arxiv.org

María Fernanda Sánchez-Puig, Carlos Gershenson, Carlos Pineda

The large digital archives of the American Physical Society (APS) offer an opportunity to quantitatively analyze the structure and evolution of scientific communication. In this paper, we perform a comparative analysis of the language used in eight APS journals (Phys. Rev. A, B, C, D, E, Lett., X, Rev. Mod. Phys.) using methods from statistical linguistics. We study word rank distributions (from monograms to hexagrams), finding that they are consistent with Zipf’s law. We also analyze rank diversity over time, which follows a characteristic sigmoid shape. To quantify the linguistic similarity between journals, we use the rank-biased overlap (RBO) distance, comparing the journals not only to each other, but also to corpora from Google Books and Twitter. This analysis reveals that the most significant differences emerge when focusing on content words rather than the full vocabulary. By identifying the unique and common content words for each specialized journal, we develop an article classifier that predicts a paper’s journal of origin based on its unique word distribution. This classifier uses a proposed “importance factor” to weigh the significance of each word. Finally, we analyze the frequency of mention of prominent physicists and compare it to their cultural recognitions ranked in the Pantheon dataset, finding a low correlation that highlights the context-dependent nature of scientific fame. These results demonstrate that scientific language itself can serve as a quantitative window into the organization and evolution of science.

Read the full article at: www.preprints.org