Public Status · Version 2026.08

Independent concept site — eligibility not established

This website does not represent an accredited university, nonprofit research institute, verified principal investigator, or Anthropic partner. Profiles, grants, events, facilities, and affiliations are illustrative unless independently verified.

Read the full status notice
BBQ Independent Research InitiativeIndependent research initiative · not an accredited institution · Warsaw, Poland
Operating Form
Online initiative
Domain
bbq.edu.pl
Eligibility
Not established
ILLUSTRATIVE PROJECT CONCEPT

Project NEURO-REASON: Differentiable Mathematical Theorem Proving & SMT Integration

Investigating the unification of gradient-based neural networks with exact automated theorem provers for automated proof generation in algebraic geometry and software verification.

Principal Investigator
Dr inż. Karolina Nowak
Laboratory
Autonomous Systems & Formal Verification Lab (ASFV Lab)
Funding Agency
Polish National Agency for Academic Exchange (NAWA) & NCN
Grant ID
PPN/BAP/2024/1/00045
Allocated Budget
PLN 1,420,000 (€320,000)
Project Period
2025–2028

Scientific Objective & Core Research Questions

Can neural guidance models learn search heuristics for interactive theorem provers that provably preserve soundness while outperforming classical depth-first heuristics by orders of magnitude?

Work Packages & Methodological Roadmap

  1. Designing differentiable loss functions that penalize logical contradictions in intermediate reasoning steps.
  2. Developing high-throughput Lean 4 interaction environments using custom C++ bindings.
  3. Benchmarking neural theorem provers on formal math libraries (Mathlib) and certified software verification benchmarks.

Project Deliverables & Software Artefacts

  • Lean-Guidance-Engine: Fast neural tactic suggestion engine for Lean 4 theorem proving.
  • Benchmark corpus of 50,000 formal lemmas extracted from verified systems software.
  • Open source verification toolkit under Apache 2.0 license.

Project Description

Formal verification is the gold standard for software and hardware correctness, but creating formal proofs in interactive theorem provers remains labor-intensive. Project NEURO-REASON explores deep learning architectures that act as intelligent assistants to mathematicians and computer scientists, generating verified proof steps automatically.

Project Milestones & Reporting

  • Co-organizing the Autumn Workshop on Neuro-Symbolic Verification in Warsaw.
  • Open collaboration with Inria Paris and Oxford University.

Foundation References & Publications

External scholarly reference · 2016Third-party work

The FAIR Guiding Principles for Scientific Data Management and Stewardship

Mark D. Wilkinson, Michel Dumontier, IJsbrand Jan Aalbersberg, Gabrielle Appleton, Myles Axton, Arie Baak, Niklas Blomberg, Jan-Willem Boiten, Luiz Bonino da Silva Santos, Philip E. Bourne, Jildau Bouwman, Anthony J. Brookes, Tim Clark, Mercè Crosas, Ingrid Dillo, Olivier Dumon, Scott Edmunds, Chris T. Evelo, Richard Finkers, Alejandra Gonzalez-Beltran, Alasdair J. G. Gray, Paul Groth, Carole Goble, Jeffrey S. Grethe, Jaap Heringa, Peter A. C. 't Hoen, Rob Hooft, Tobias Kuhn, Ruben Kok, Joost Kok, Scott J. Lusher, Maryann E. Martone, Albert Mons, Abel L. Packer, Bengt Persson, Philippe Rocca-Serra, Marco Roos, Rene van Schaik, Susanna-Assunta Sansone, Erik Schultes, Thierry Sengstag, Ted Slater, George Strawn, Morris A. Swertz, Mark Thompson, Johan van der Lei, Erik van Mulligen, Jan Velterop, Andra Waagmeester, Peter Wittenburg, Katherine Wolstencroft, Jun Zhao, Barend Mons

Scientific Data Vol. 3, pp. 160018(2016). DOI: 10.1038/sdata.2016.18

Defines the principles that digital research objects should be Findable, Accessible, Interoperable, and Reusable for people and machines.

External scholarly reference · 2017Third-party work

A Manifesto for Reproducible Science

Marcus R. Munafò, Brian A. Nosek, Dorothy V. M. Bishop, Katherine S. Button, Christopher D. Chambers, Nathalie Percie du Sert, Uri Simonsohn, Eric-Jan Wagenmakers, Jennifer J. Ware, John P. A. Ioannidis

Nature Human Behaviour Vol. 1, pp. 0021(2017). DOI: 10.1038/s41562-016-0021

Sets out practical measures to improve the reliability and efficiency of scientific research through stronger methods, transparency, and incentives.