Skip to content
#generative ai Open access

kellermap: certified reductions of polynomial Keller maps

Sep 2026 · Zenodo (CERN European Organization for Nuclear Research)

Abstract

kellermap constructs and verifies reductions of polynomial maps with constantJacobian determinant. Every transformation is a certificate object that carriesits own obligations; verification names the obligation that failed rather thanreturning a boolean, and a collision is transported across each step andre-verified, so that a reduction of a counterexample is still a counterexample. Version 0.7 adds the multi-affine normal form of Theorem 2.1(b), a descentstep that deletes a coordinate two elementary changes have made triangular,and the arithmetic that makes the library correct over coefficient rings thatare not fields: elimination to a unit pivot rather than to a non-zero one, anddeterminants taken without dividing. Version 0.6 implemented the second andthird stages of the Bass-Connell-Wright Reduction Theorem, collision-hullcompression, and the symmetric lift to the gradient form of a quartic over afield containing i. Applied in sequence to the smallest degree-three map thisproject holds, the chain runs 11, 22, 23, 19, 38 variables with every stepverified and the collision arriving at the far end. The constructions are other people's. What this project contributes is thecomposition of them, the certificates, and eight reconstruction scripts thatrecompute the published results in plain SymPy without using the library. Nominimality and no priority is claimed for any figure: both figures this chainreaches were published elsewhere first, by a different route, and the recordof what this project claimed too widely and corrected is in `docs/errata.md`. Generative AI tools were used in two roles: one model wrote code, tests anddocumentation in conversation with the maintainer, and a different modelaudited the release candidates. `docs/provenance.md` names the tools and sayswhat each did. Every audit of this milestone found faults that the test suite,the coverage requirement and the mutation sweep had all passed, and more thanonce the fault was in a repair made for the previous audit. Neither model is anauthor. The maintainer set the tasks, ran the gates, read the deliveries anddecided what entered the repository.

View source

Similar papers

#artificial intelligence Conference Open access Apr 2020

ECCOLA - a Method for Implementing Ethically Aligned AI Systems

The method, ECCOLA, is presented, which aims at making the high-level AI ethics principles more practical, making it possible for developers to more easily implement them in practice.

Ville Vakkuri, Kai-Kristian Kemell, P. Abrahamsson · 64 citations · ⚡6
#computer vision Review Apr 2024

AI-powered Code Review with LLMs: Early Results

The goal is to not only refine the accuracy of the LLM-based tool but also to underscore its potential in streamlining the software development lifecycle through proactive code improvement and education.

Z. Rasheed, Malik Abdul Sami, Muhammad Waseem et al. · 62 citations · ⚡3
#computer vision Open access Mar 2024

LLM-based agents for automating the enhancement of user story quality: An early report

The use of large language models to automatically improve the user story quality in Austrian Post Group IT agile teams is explored, with a reference model for an Autonomous LLM-based Agent System developed and implemented at the company.

Zheying Zhang, M. Rayhan, Tomas Herda et al. · 48 citations · ⚡4
#computer vision Review Mar 2024

System for systematic literature review using multiple AI agents: Concept and an empirical evaluation

This paper introduces a novel multi-AI-agent system designed to fully automate SLRs, and demonstrates how it substantially reduces the time and effort traditionally required for SLRs while maintaining comprehensiveness and precision.

Abdul Malik Sami, Z. Rasheed, Kai-Kristian Kemell et al. · 44 citations · ⚡2
#computer vision Feb 2024

Can Large Language Models Serve as Data Analysts? A Multi-Agent Assisted Approach for Qualitative Data Analysis

The proposed LLM-based multi-agent system automates qualitative data analysis process, creating opportunities for researchers and practitioners, and future improvements focus on enhancing multilingual performance and integrating continuous expert feedback.

Z. Rasheed, Muhammad Waseem, Aakash Ahmad et al. · 41 citations

Related blog posts

Microsoft Research Blog Oct 12, 2026

Simulating student learning for better AI tutoring

StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across subjects like chess, writing, and mathematics. The post Simulating student learning for better AI tutoring appeared first on Microsoft Research.

GPT-Lab Oct 12, 2026

AI Has Grown Up. Have We?

AI is moving beyond impressive demos. After World Summit AI 2026 in Amsterdam, GPT-Lab's Muhammad Waseem reflects on what organizations need to make AI agents reliable, responsible and genuinely useful in everyday work. The post AI Has Grown Up. Have We? appeared first on GPT-Lab.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.