Searcharxiv⌕ Search

arXiv subjects

Antonio Diaz

Publications and source records attributed to Antonio Diaz.

10 recordsLinked to original sources
arXiv2026

A Hierarchical Consistency Framework for Auditing Retrieval-Augmented Generation Systems

Retrieval-augmented generation (RAG) is commonly evaluated by whether the final answer is correct. That test is insufficient: an answer can match its reference while the context that produced it contains a direct contradiction, leaving the contested evidence invisible to answer-only review and retrieval relevance scores. This paper presents the Hierarchical Consistency Framework (HCF), a post-hoc, model-agnostic audit of three distinct levels of a RAG process: the knowledge corpus, the final retrieved context, and the generated answer. HCF represents corpus conflicts as source-linked atomic facts, thereby identifying the documents responsible, and returns each Answer Consistency Score (ACS) with an explanation of supporting and contradictory contextual statements. We evaluate HCF on several controlled corpora spanning five domains and 100 query-corpus instances. A human evaluator compares every generated response with its supplied ground-truth response. The results show that the three diagnostic levels can dissociate: the corpus with the highest mean retrieval similarity has the lowest mean ACS, while a structurally degraded corpus performs worse at corpus level but better at answer level. Most importantly, HCF identifies contradictory retrieved evidence in several cases where the answer still matches the ground truth. HCF does not certify factual truth; it makes the evidence supporting and challenging an answer inspectable and attributable.

cs.AI↗
arXiv2026

An Auditable Symbolic-RAG-Generative AI Architecture for Goal-Oriented Conversation Orchestration

Goal-oriented conversational systems must answer factual questions, understand visitor-provided information, and advance business objectives without becoming rigid questionnaires. This paper proposes a Symbolic-RAG-Generative architecture centered on the Goal-oriented Retrieval-Augmented Conversation Engine (GRACE). An instruction-constrained Business Goal Compiler transforms business intent into an immutable objective set, normalized priority vector, canonical questions, and initial state vector. At runtime, GRACE receives the complete conversation history, latest visitor message, current state, and grounded answer generated by a separate RAG component. It updates completion only from visitor-authored evidence and selects one contextually modulated follow-up. The core policy maximizes expected business progress subject to a minimum visitor-utility constraint. We formalize the state, monotonic transitions, source separation, question modulation, and constrained policy; present the reference architecture; and define an evaluation comprising 24 English real-estate and 10 Spanish professional-cleaning conversations, totaling 119 protocol-defined visitor turns. Across both domains, GRACE achieves 84.9% exact state-transition accuracy, 91.6% evidence precision, 89.6% evidence recall, 100% monotonicity, and 94.1% terminal-state accuracy. The evaluation establishes compelling symbolic-state performance across standard, multi-goal, RAG-detour, validation, refusal, and robustness scenarios.

cs.AI↗
arXiv2022

Time and Cost-Efficient Bathymetric Mapping System using Sparse Point Cloud Generation and Automatic Object Detection

Generating 3D point cloud (PC) data from noisy sonar measurements is a problem that has potential applications for bathymetry mapping, artificial object inspection, mapping of aquatic plants and fauna as well as underwater navigation and localization of vehicles such as submarines. Side-scan sonar sensors are available in inexpensive cost ranges, especially in fish-finders, where the transducers are usually mounted to the bottom of a boat and can approach shallower depths than the ones attached to an Uncrewed Underwater Vehicle (UUV) can. However, extracting 3D information from side-scan sonar imagery is a difficult task because of its low signal-to-noise ratio and missing angle and depth information in the imagery. Since most algorithms that generate a 3D point cloud from side-scan sonar imagery use Shape from Shading (SFS) techniques, extracting 3D information is especially difficult when the seafloor is smooth, is slowly changing in depth, or does not have identifiable objects that make acoustic shadows. This paper introduces an efficient algorithm that generates a sparse 3D point cloud from side-scan sonar images. This computation is done in a computationally efficient manner by leveraging the geometry of the first sonar return combined with known positions provided by GPS and down-scan sonar depth measurement at each data point. Additionally, this paper implements another algorithm that uses a Convolutional Neural Network (CNN) using transfer learning to perform object detection on side-scan sonar images collected in real life and generated with a simulation. The algorithm was tested on both real and synthetic images to show reasonably accurate anomaly detection and classification.

cs.CV↗
arXiv2020

Event reconstruction for KM3NeT/ORCA using convolutional neural networks

The KM3NeT research infrastructure is currently under construction at two locations in the Mediterranean Sea. The KM3NeT/ORCA water-Cherenkov neutrino detector off the French coast will instrument several megatons of seawater with photosensors. Its main objective is the determination of the neutrino mass ordering. This work aims at demonstrating the general applicability of deep convolutional neural networks to neutrino telescopes, using simulated datasets for the KM3NeT/ORCA detector as an example. To this end, the networks are employed to achieve reconstruction and classification tasks that constitute an alternative to the analysis pipeline presented for KM3NeT/ORCA in the KM3NeT Letter of Intent. They are used to infer event reconstruction estimates for the energy, the direction, and the interaction point of incident neutrinos. The spatial distribution of Cherenkov light generated by charged particles induced in neutrino interactions is classified as shower- or track-like, and the main background processes associated with the detection of atmospheric neutrinos are recognized. Performance comparisons to machine-learning classification and maximum-likelihood reconstruction algorithms previously developed for KM3NeT/ORCA are provided. It is shown that this application of deep convolutional neural networks to simulated datasets for a large-volume neutrino telescope yields competitive reconstruction results and performance improvements with respect to classical approaches.

astro-ph.IM↗
arXiv2020

gSeaGen: the KM3NeT GENIE-based code for neutrino telescopes

The gSeaGen code is a GENIE-based application developed to efficiently generate high statistics samples of events, induced by neutrino interactions, detectable in a neutrino telescope. The gSeaGen code is able to generate events induced by all neutrino flavours, considering topological differences between track-type and shower-like events. Neutrino interactions are simulated taking into account the density and the composition of the media surrounding the detector. The main features of gSeaGen are presented together with some examples of its application within the KM3NeT project.

astro-ph.IM↗
arXiv2014

Fluid description of multi-component solar partially ionized plasma

We derive self-consistent formalism for the description of multi-component partially ionized solar plasma, by means of the coupled equations for the charged and neutral components for an arbitrary number of chemical species, and the radiation field. All approximations and assumptions are carefully considered. Generalized Ohm's law is derived for the single-fluid and two-fluid formalism. Our approach is analytical with some order-of-magnitude support calculations. After general equations are developed we particularize to some frequently considered cases as for the interaction of matter and radiation.

astro-ph.SR↗
arXiv2007

A family of acyclic functors

We determine a family of functors from a poset to abelian groups such that the higher direct limits vanish on them. This is done by first characterizing the projective functors. Then a spectral sequence arising from the grading of the poset is used. Also the dual version for injective functors and higher inverse limits is included. Graded posets include simplicial complexes, subdivision categories and simplex-like posets.

math.AT↗
arXiv2007

A method for integral cohomology of posets

We present a method to compute integral cohomology of posets. This toolbox is applicable as soon as the sub-posets under each object possess certain structure. This is the case for simplicial complexes and simplex-like posets. The method is based on homological algebra arguments in the category of functors and on a spectral sequence built upon the poset. We show its relation to discrete Morse theory. As application we give an alternative proof of Webb's conjecture for saturated fusion systems and we compute the cohomology of Coxeter complexes for finite and infinite Coxeter groups.

math.AT↗
arXiv2004

All p-local finite groups of rank two for odd prime p

In this paper we give a classification of the rank two p-local finite groups for odd p. This study requires the analisis of the possible saturated fusion systems in terms of the outer automorphism group ant the proper F-radical subgroups. Also, for each case in the classification, either we give a finite group with the corresponding fusion system or we check that it corresponds to an exotic p-local finite group, getting some new examples of these for p = 3.

math.AT↗