Researcher, developer and consultant in Computer Science, with a background in Statistics and Applied Mathematics. Currently a PhD candidate in Informatics, specializing in generative artificial intelligence, working with advanced analytical methods in R and Python to build data-driven solutions. The work bridges statistical modeling, Artificial Intelligence and business technology, with a focus on AI solutions that are mathematically sound, computationally efficient and viable in production.
Long-form articles and notable short posts published on LinkedIn.
Packages in production and research prototypes. Papers are listed under Publications. Filter by category.
Code, frozen answers, preregistration notes and Lean 4 proofs for the arXiv paper Confidence Is Not a Promise, a reference audit of what the probability of a typed decision model licenses and what a selective gate built on it can promise.
Brasil em Orbita: an interactive observatory that ranks every Brazilian municipality by its role in the urban network, crosses it with fiscal dependency and service concentration, and condenses it into a Municipal Dependency Index. Built by integrating federal open data (IBGE, Treasury, DATASUS, INEP, Central Bank); published data artifacts and full method documentation.
gedit 46 plugin for live full-view Markdown preview, with offline math (MathML via WebKit) and locally rendered Mermaid diagrams; useful for writing papers and reviewing documents without leaving the editor.
R package on R-universe: a Metropolis-Hastings sampler with a vendor-agnostic GPU-portable log-density kernel (Rust and CubeCL); pre-registered factorial benchmark against five mainstream MCMC packages.
Autonomous research loop with a local LLM critic; a generalization of karpathy/autoresearch.
Community hub for wrapping libraries as agent-callable skills, in R, Python and Julia.
Multilingual NLP metric toolkit (BLEU, CHRF, TER, semantic similarity); companion app to the FITEE back-translation study.
Code, data and prompts for the TraCE-LLM study on traceability in LLM pipelines.
Two-step RAG for metadata filtering and statistical LLM evaluation; research code.
Simple ChatGPT integration for the GNU/Linux shell.
Application of Benford's law to dictionary data, in R.
R package for the bimodal generalized extreme value model.
R package on CRAN for the bimodal Gumbel distribution, a three-parameter model for extreme data with one or two modes.
Maze generation and random-walk simulation in R.
R scraper for collecting listing data from the OLX marketplace.
Firefox extension that shows the price per kilo, litre or unit on Mercado Livre listings, spreading the shipping cost before dividing, and highlights the cheapest option.
AI-assisted platform for the academic research workflow: manuscript review, journal selection, reference-integrity checking, and research discovery through author metrics, semantic search and knowledge graphs.
Journal and conference papers.
Citable research software and data, each with its own DOI. Most recent release of each project.
Every public repository, most recent first, including course material, experiments and small tools.
A typed decision model returns 0.97 and the code acts on it as if it were a guarantee. A reference audit of two typed deciders, now on arXiv, measures what that number licenses, why a threshold chosen by point estimate breaks its own promise in 147 of 190 evaluations, and what a caller can do instead.
Read the post →Quick answers about projects, papers and how to reach me.
Researcher, developer and consultant in Computer Science with a background in Statistics and Applied Mathematics. PhD candidate in Informatics, specializing in generative artificial intelligence. Based in Brasilia, Brazil.
An autonomous research loop with a local LLM critic: the agent generates, critiques and refines its own outputs across iterations, with a model-side judge instead of a human-in-the-loop on every cycle. Source code at https://github.com/pcbrom/autoresearch.
A community hub for wrapping libraries as agent-callable skills, with implementations in R, Python and Julia. The goal is to give LLM agents typed, deterministic interfaces to existing scientific tooling instead of letting them generate fragile code on the fly. Source code at https://github.com/pcbrom/community-skills.
A published methodology for evaluating trait consistency in large language models: behavioral stability across prompts and the adversarial compensation effect. Brom, Oliveira and Weigang, Journal of the Brazilian Computer Society 32:1 (2026), DOI 10.5753/jbcs.2026.6343.
An R package distributed via R-universe: a Metropolis-Hastings MCMC sampler with a vendor-agnostic GPU-portable log-density kernel implemented in Rust with CubeCL. Includes a pre-registered factorial benchmark against five mainstream MCMC packages. Available at https://pcbrom.r-universe.dev/gpumetropolis.
An R package on CRAN implementing the bimodal Gumbel distribution, a three-parameter model for extreme-value data with one or two modes. Companion to the 2023 article in the Austrian Journal of Statistics. Available at https://cran.r-project.org/package=bgumbel.
An AI-assisted platform for the academic research workflow: manuscript review, journal selection, reference-integrity checking, and research discovery through author metrics, semantic search and knowledge graphs. Launching July 2026 at https://sota.pcbrom.com.