arXiv subjects

Nicolas Sanchez

Publications and source records attributed to Nicolas Sanchez.

3 recordsLinked to original sources

arXiv2026

Green Shielding: A User-Centric Approach Towards Trustworthy AI

Large language models (LLMs) are increasingly deployed, yet their outputs can be highly sensitive to routine, non-adversarial variation in how users phrase queries, a gap not well addressed by existing red-teaming efforts. We propose Green Shielding, a user-centric agenda for building evidence-backed deployment guidance by characterizing how benign input variation shifts model behavior. We operationalize this agenda through the CUE criteria: benchmarks with authentic Context, reference standards and metrics that capture true Utility, and perturbations that reflect realistic variations in the Elicitation of model behavior. Guided by the PCS framework and developed with practicing physicians, we instantiate Green Shielding in medical diagnosis through HealthCareMagic-Diagnosis (HCM-Dx), a benchmark of patient-authored queries, together with structured reference diagnosis sets and clinically grounded metrics for evaluating differential diagnosis lists. We also study perturbation regimes that capture routine input variation and show that prompt-level factors shift model behavior along clinically meaningful dimensions. Across multiple frontier LLMs, these shifts trace out Pareto-like tradeoffs. In particular, neutralization, which removes common user-level factors while preserving clinical content, increases plausibility and yields more concise, clinician-like differentials, but reduces coverage of highly likely and safety-critical conditions. Together, these results show that interaction choices can systematically shift task-relevant properties of model outputs and support user-facing guidance for safer deployment in high-stakes domains. Although instantiated here in medical diagnosis, the agenda extends naturally to other decision-support settings and agentic AI systems.

cs.CL↗

arXiv2025

Disc Game Dynamics: A Latent Space Perspective on Selection and Learning in Games

Evolutionary game theory studies populations that change in response to an underlying game. Often, the functional form relating outcome to player attributes or strategy is complex, preventing mathematical progress. In this work, we axiomatically derive a latent space representation for pairwise, symmetric, zero-sum games by seeking a coordinate space in which the optimal training direction for an agent responding to an opponent depends only on their opponent's coordinates. The associated embedding represents the original game as a linear combination of copies of a simple game, the disc game, in a new coordinate space. In this article, we show that disc-game embedding is useful for studying learning dynamics. We demonstrate that a series of classical evolutionary processes simplify to constrained oscillator equations in the latent space. In particular, the continuous replicator equation reduces to a Hamiltonian system of coupled oscillators that exhibit Poincar\'e recurrence. This reduction allows exact, finite-dimensional closure when the underlying game is finite-rank, and optimal approximation otherwise. It also establishes an exact equivalence between the continuous replicator equation and adaptive dynamics in the transformed coordinates. By identifying a minimal rank representation, the disc game embedding offers numerical methods that could decouple the cost of simulation from the number of attributes used to define agents. These results generalize to metapopulation models that mix inhomogeneously, and to any time-differentiable dynamic where the rate of growth of a type, relative to its expected payout, is a nonnegative function of its frequency. We recommend disc-game embedding as an organizing paradigm for learning and selection in response to symmetric two-player zero-sum games.

cs.GT↗

arXiv2016

Intra-Binary Shock Heating of Black Widow Companions

The low mass companions of evaporating binary pulsars (black widows and their ilk) are strongly heated on the side facing the pulsar. However in high-quality photometric and spectroscopic data the heating pattern does not match that expected for direct pulsar illumination. Here we explore heating mediated by an intra-binary shock (IBS). We develop a simple analytic model and implement it in the popular `ICARUS' light curve code. The model is parameterized by the wind momentum ratio beta and velocity v_Rel v_orb and assumes that the reprocessed pulsar wind emits prompt particles or radiation to heat the companion surface. We illustrate an interesting range of light curve asymmetries controlled by these parameters. The code also computes the IBS synchrotron emission pattern, and thus can model black widow X-ray light curves. As a test we apply the results to the high quality asymmetric optical light curves of PSR J2215+5135; the resulting fit gives a substantial improvement upon direct heating models and produces an X-ray light curve consistent with that seen. The IBS model parameters imply that, at the present loss rate, the companion evaporation has a characteristic timescale tau_evap ~150My. Still, the model is not fully satisfactory, indicating additional unmodeled physical effects.

astro-ph.HE↗