arXiv subjects

David N. Olivieri

Publications and source records attributed to David N. Olivieri.

7 recordsLinked to original sources

arXiv2026

Transformer Field Theory: A Response-Theoretic Approach to Mechanistic Interpretability

Mechanistic interpretability often studies Transformer behavior by intervening on internal activations through activation patching, causal tracing, path patching, and steering directions. This paper develops Transformer Field Theory: a response-theoretic framework in which the residual stream of a fixed forward pass is treated as a Transformer field over layer depth and token position. In this formulation, patching becomes a localized source insertion into the Transformer field, first-order sensitivity fields predict patch effects, Green functions describe downstream propagation, and patch selection is posed as an adjoint inverse problem. Empirically, we test the theory's forward response objects in GPT-2-style autoregressive Transformers. Localized Transformer-field interventions exhibit a bounded local linear regime; first-order sensitivities predict patch effects across layer-token sites; localized sources generate structured anisotropic Transformer-field propagation; high-sensitivity sites and sliced Green operators provide reduced response descriptions; and prompt-induced Transformer-field displacements partially transfer answer behavior. These results establish sensitivities, Transformer-field responses, and sliced Green operators as practical objects for organizing patching experiments, while providing the forward mathematical basis for patch-site inference and cross-scale response transfer.

cs.LG↗

arXiv2026

Sheaf-Theoretic Transport and Obstruction for Detecting Scientific Theory Shift in AI Agents

Scientific theory shift in AI agents requires more than fitting equations to data. An artificial scientific agent must detect whether an existing representational framework remains transportable into a new regime, or whether its language has become locally-to-globally obstructed and must be extended. This paper develops a finite sheaf-theoretic framework for detecting theory-shift candidates through transport and obstruction. Contexts are organized as a local-to-global structure in which source, overlap, target, and validation charts are fitted, restricted, and tested for gluing. Obstruction measures failure of coherence through residual fit, overlap incompatibility, constraint violation, limiting-relation failure, and representational cost. We evaluate the framework on a controlled transition-card benchmark designed to separate deformation within a source language from extension of that language. The main result is direct obstruction ranking: the intended deformation or extension is usually the lowest-obstruction candidate, and transition type is separated in the benchmark. A constellation kernel over the same signatures is included only as a secondary representational-similarity probe. The aim is not to reconstruct historical paradigm shifts or solve open-ended autonomous theory invention, but to isolate a finite diagnostic subproblem for AI agents: detecting when representational transport fails and extension becomes the coherent next move.

cs.AI↗

arXiv2026

Patch-Effect Graph Kernels for LLM Interpretability

Mechanistic interpretability aims to reverse-engineer transformer computations by identifying causal circuits through activation patching. However, scaling these interventions across diverse prompts and task families produces high-dimensional, unstructured datasets that are difficult to compare systematically. We propose a framework that reframes mechanistic analysis as a graph machine-learning problem by representing activation-patching profiles as patch-effect graphs over model components. We introduce three graph-construction methods: direct-influence via causal mediation, partial-correlation, and co-influence and apply graph kernels to analyze the resulting structures. Evaluating this approach on GPT-2 Small using Indirect Object Identification (IOI) and related tasks, we find that patch-effect graphs preserve discriminative structural signals. Specifically, localized edge-slot features provide higher classification accuracy than global graph-shape descriptors. A screened paired-patching validation suggests that CI and PC selected candidate edges correspond to stronger activation-influence effects than random or low-rank candidates. Crucially, by evaluating these representations against rigorous prompt-only and raw patch-effect controls, we make the evidential scope of the benchmark explicit: graph features compress structured patching signal, while raw tensors and surface cues define strong baselines that any circuit-level claim should address. Ultimately, our framework provides a compression and evaluation pipeline for comparing patching-derived structures under controlled baselines, separating robust slice-discriminative evidence from stronger task-general causal-circuit claims.

cs.AI↗

arXiv2021

Comment on "An efficient code to solve the Kepler equation. Elliptic case"

In a recent MNRAS article, Raposo-Pulido and Pelaez (RPP) designed a scheme for obtaining very close seeds for solving the elliptic Kepler Equation with the classical and the modified Newton-Rapshon methods. This implied an important reduction in the number of iterations needed to reach a given accuracy. However, RPP also made strong claims about the errors of their method that are incorrect. In particular, they claim that their accuracy can always reach the level $\sim5\varepsilon$, where $\varepsilon$ is the machine epsilon (e.g. $\varepsilon=2.2\times10^{-16} $ in double precision), and that this result is attained for all values of the eccentricity $e<1$ and the mean anomaly $M\in[0,π]$, including for $e$ and $M$ that are arbitrarily close to $1$ and $0$, respectively. However, we demonstrate both numerically and analytically that any implementation of the classical or modified Newton-Raphson methods for Kepler's equation, including those described by RPP, have a limiting accuracy of the order $\sim\varepsilon/\sqrt{2(1-e)}$. Therefore the errors of these implementations diverge in the limit $e\to1$, and differ dramatically from the incorrect results given by RPP. Despite these shortcomings, the RPP method can provide a very efficient option for reaching such limiting accuracy. We also provide a limit that is valid for the accuracy of any algorithm for solving Kepler equation, including schemes like bisection that do not use derivatives. Moreover, similar results are also demonstrated for the hyperbolic Kepler Equation. The methods described in this work can provide guidelines for designing more accurate solutions of the elliptic and hyperbolic Kepler equations.

astro-ph.IM↗

arXiv2018

Fast Switch and Spline Scheme for Accurate Inversion of Nonlinear Functions: The New First Choice Solution to Kepler's Equation

Numerically obtaining the inverse of a function is a common task for many scientific problems, often solved using a Newton iteration method. Here we describe an alternative scheme, based on switching variables followed by spline interpolation, which can be applied to monotonic functions under very general conditions. To optimize the algorithm, we designed a specific ultra-fast spline routine. We also derive analytically the theoretical errors of the method and test it on examples that are of interest in physics. In particular, we compute the real branch of Lambert's $W(y)$ function, which is defined as the inverse of $x \exp(x)$, and we solve Kepler's equation. In all cases, our predictions for the theoretical errors are in excellent agreement with our numerical results, and are smaller than what could be expected from the general error analysis of spline interpolation by many orders of magnitude, namely by an astonishing $3\times 10^{-22}$ factor for the computation of $W$ in the range $W(y)\in [0,10]$, and by a factor $2\times 10^{-4}$ for Kepler's problem. In our tests, this scheme is much faster than Newton-Raphson method, by a factor in the range $10^{-4}$ to $10^{-3}$ for the execution time in the examples, when the values of the inverse function over an entire interval or for a large number of points are requested. For Kepler's equation and tolerance $10^{-6}$ rad, the algorithm outperforms Newton's method for all values of the number of points $N\ge 2$.

physics.comp-ph↗

arXiv2014

KPCA Spatio-temporal trajectory point cloud classifier for recognizing human actions in a CBVR system

We describe a content based video retrieval (CBVR) software system for identifying specific locations of a human action within a full length film, and retrieving similar video shots from a query. For this, we introduce the concept of a trajectory point cloud for classifying unique actions, encoded in a spatio-temporal covariant eigenspace, where each point is characterized by its spatial location, local Frenet-Serret vector basis, time averaged curvature and torsion and the mean osculating hyperplane. Since each action can be distinguished by their unique trajectories within this space, the trajectory point cloud is used to define an adaptive distance metric for classifying queries against stored actions. Depending upon the distance to other trajectories, the distance metric uses either large scale structure of the trajectory point cloud, such as the mean distance between cloud centroids or the difference in hyperplane orientation, or small structure such as the time averaged curvature and torsion, to classify individual points in a fuzzy-KNN. Our system can function in real-time and has an accuracy greater than 93% for multiple action recognition within video repositories. We demonstrate the use of our CBVR system in two situations: by locating specific frame positions of trained actions in two full featured films, and video shot retrieval from a database with a web search application.

cs.IR↗

arXiv2004

Controllable matter-wave switchers with vector Bose-Einstein solitons

We show the possibility of producing matter-wave switching devices by using Manakov interactions between matter wave solitons in two-species Bose-Einstein Condensates (BEC). Our results establish the experimental parameters for three interaction regimes in two-species BECs: symmetric and asymmetric splitting, down-switching and up-switching. We have studied the dependence upon the initial conditions and the kind of interaction between the two components of the BECs.

cond-mat.soft↗