arXiv subjects

Vinicius Cardoso Garcia

Publications and source records attributed to Vinicius Cardoso Garcia.

4 recordsLinked to original sources

arXiv2026

Building AI-Intensive Software with AI: Early Results and a Cautionary Tale on Measuring Development Cost

Empirical reports on the true cost of AI-intensive software development remain scarce, and the few that exist are easy to get wrong in ways that never surface in the final number. We report early results from an ongoing case study: a six-person student team built a full conversational onboarding assistant -- RAG-based code chat, guided tours, dependency graphs, technical-debt analysis -- over one academic term using pervasive AI assistance. We instrumented development with a three-layer cost model (real AI spend, self-reported human effort, human counterfactual) and initially reported a 19.4x cost ratio. A follow-up pass revealed two independent errors -- inferring per-token cost under a flat-rate subscription, and pricing the counterfactual with the wrong regional labor rates -- that together had inflated the ratio by roughly 2x; the corrected figure is ~9.9x. We present this correction as an early, generalizable finding in its own right: both errors are easy to make, invisible in the final number, and plausibly common in similar reports. We outline next steps toward a more robust, replicable costing methodology for AI-intensive development.

cs.SE↗

arXiv2026

Does ISO-Grounded NFR Specification Improve LLM Code Generation? A Comparison of Rich and Structured Interventions against a Natural-Language Baseline

In LLM-based code generation, Non-Functional Requirements (NFRs) are often specified as terse one-line phrases. We ask whether grounding those specifications in ISO/IEC 25010 Quality Model, either as rich natural-language prose (NL-rich) or as structured JSON (Structured), improves code generated on HumanEval/HumanEval-ET compared to a RobuNFR-style one-line baseline (NL-simple). We evaluate four NFRs (performance, error handling, code smell, readability) with ten prompt variations per condition under a fixed model snapshot and paired non-parametric analysis. Primary finding: ISO-grounded enrichment improves static quality proxies (unreadability density falls across all four NFRs (e.g., Performance 0.88 -> 0.69 for NL-rich)) and reduces sensitivity to prompt wording, but does not reliably improve functional correctness; for error handling, extended-test pass rate decreases, suggesting tension between defensive coding patterns and exact-output benchmarks. Secondary finding: when ISO content is held constant, NL-rich and Structured differ negligibly in correctness (|delta| <= 0.023), indicating that semantic content matters more than JSON-vs-prose format. Practitioners should invest in standard-grounded NFR content rather than serialization form. A fully traceable replication package is provided.

cs.SE↗

arXiv2021

Integração e Entrega Contínua para aplicações móveis desenvolvidas em React Native

Continuous integration and continuous delivery are not new for developers who create web applications, however in the development of mobile applications this practice is still not very common mainly because of the challenges during the process of distributing the application. In the face of the growing number of applications, a greater requirement for quality and ever-shorter delivery times, delivering a healthy code is often extremely important to keep up with the competition. The purpose of this work is to implement an integration and continuous delivery pipeline for mobile applications developed in React Native. It intends to automate the process of build and delivery of applications developed with this technology.

cs.SE↗

arXiv2013

Systematic Mapping Study On Security Threats in Cloud Computing

Today, Cloud Computing is rising strongly, presenting itself to the market by its main service models, known as IaaS, PaaS and SaaS, that offer advantages in operational investments by means of on-demand costs, where consumers pay by resources used. In face of this growth, security threats also rise, compromising the Confidentiality, Integrity and Availability of the services provided. Our work is a Systematic Mapping where we hope to present metrics about publications available in literature that deal with some of the seven security threats in Cloud Computing, based in the guide entitled "Top Threats to Cloud Computing" from the Cloud Security Alliance (CSA). In our research we identified the more explored threats, distributed the results between fifteen Security Domains and identified the types of solutions proposed for the threats. In face of those results, we highlight the publications that are concerned to fulfill some standard of compliance.

cs.CR↗