pcbrom.com is live
Why a researcher benefits from an address of their own on the web, and what this site collects about its visitors: nothing.
Read the post →
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 published on LinkedIn.
Packages in production, published papers and research prototypes. Filter by category.
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.
R package on CRAN for the bimodal Gumbel distribution, a three-parameter model for extreme data with one or two modes.
R package for the bimodal generalized extreme value model.
Metropolis-Hastings sampler with a GPU-portable log-density kernel; R package heading to CRAN.
Code, data and prompts for the TraCE-LLM study on traceability in LLM pipelines.
Multilingual NLP metric toolkit (BLEU, CHRF, TER, semantic similarity); companion app to the FITEE back-translation study.
Two-step RAG for metadata filtering and statistical LLM evaluation; research code.
Maze generation and random-walk simulation in R.
Application of Benford's law to dictionary data, in R.
R scraper for collecting listing data from the OLX marketplace.
Simple ChatGPT integration for the GNU/Linux shell.
Trait and Consistency Evaluation: behavioral stability and the adversarial compensation effect. Published in JBCS.
Evaluating large language models on Chinese translation through back-translation. Published in FITEE.
A methodology for implementing AI in the Brazilian federal government's public services; best industrial paper candidate at WEBIST 2024.
The bimodal Gumbel model with application to environmental data. Austrian Journal of Statistics.
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.
Every public repository, most recent first, including course material, experiments and small tools.
Why a researcher benefits from an address of their own on the web, and what this site collects about its visitors: nothing.
Read the post →