§ projects · selected code

Projects.

4 PROJECTS · 3 OPEN SOURCE · 6 MERGED UPSTREAM PRS

Research software I lead or co-author, and contributions to tools others depend on.

§01/ co-author · 2026

benchgap

Fills the empty cells of LLM leaderboards. Calibrates benchmarks against each other on the models measured on both, predicts each missing score from that model's own results, and attaches a cross-validated error and confidence level to every estimate. Data refreshed daily from BenchLM, with a public OpenAPI 3.1 JSON API. Built with Roland Hollós.

  • Python
  • Curve fitting
  • LLM evaluation
  • PHP
§02/ author · 2026

Distribird

Multi-agent LangGraph pipeline that turns scientific literature into informative Bayesian priors. Searches Semantic Scholar and OpenAlex in parallel, extracts reported numerical values, and fits a probability distribution via AIC model selection. Built with HUN-REN AI1Science.

  • Python
  • LangGraph
  • LLM agents
  • Bayesian inference
§03/ lead developer · 2025 – 2026

Syxplain

Neurosymbolic web platform that turns a table of numbers into a readable law. An LLM agent steers PySR symbolic regression on a Slurm HPC cluster, interprets the whole Pareto front, and grounds every explanation in real literature through deep research. Built with HUN-REN AI1Science.

  • Python
  • FastAPI
  • React
  • PySR
  • Slurm
Source privateTry the tool
§04/ contributor · 2023 – 2024

SpotBugs

6 merged pull requests to the widely-used Java static-analysis tool, including two new CERT Java detectors with full test cases: SER11-J (prevent overwriting of externalizable objects) and VNA04-J (ensure calls to chained methods are atomic). The atomicity detector connects to the published Acta Cybernetica paper on multithreading atomicity.

  • Java
  • Static analysis
  • CERT Java
  • AST visitors