Sep 2026· Zenodo (CERN European Organization for Nuclear Research)
Computability, Logic, AI Algorithms
Abstract
A Legendre pair of odd length n consists of two cyclic sign sequences whose periodic autocorrelations sum to −2 at every nonzero shift; it yields a Hadamard matrix of order 2n + 2. Let p be an odd prime and q a positive integer, with n = p²q odd. For every offset c modulo n, neither sequence can be invariant under the affine map i ↦ (1 + pq)i + c. An odd-cycle argument gives autocorrelation bounds that are individually sharp even for sequences of sum 1. The result excludes specified symmetries in searches for Legendre pairs, including at lengths 117 and 333; it does not decide existence at length 333. The general direct obstruction was previously stated publicly under the GitHub handle byclaude. This article gives a self-contained proof with sharp bounds and derives the affine consequence. The source archive contains the manuscript, Lean formalization, claim map and verification instructions. The article and explanatory text are licensed under CC BY 4.0; original code and Lean sources are licensed under MIT. Third-party terms are retained as described in LICENSES.md. Use of generative AI. OpenAI's ChatGPT and Codex, together with Anthropic's Claude, were used in developing the mathematics, writing and checking the programs, and preparing the text. The author is responsible for the mathematical statements, computations and references.
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· EUROMICRO Conference on Soft...· 64 citations· ⚡6
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.· arXiv.org· 62 citations· ⚡3
A comprehensive overview of how enhanced sampling methods are reshaping the field, with a particular focus on the data-driven construction of collective variables, is provided.
Kai Zhu, Enrico Trizio, Jintu Zhang et al.· Chemical Reviews· 58 citations
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.· International Conference on...· 48 citations· ⚡4
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.· arXiv.org· 44 citations· ⚡2
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.· arXiv.org· 41 citations
AI is making software generation faster, but speed does not remove the need for expertise. As more work is delegated to AI, tacit knowledge may become one of the most important human advantages in software engineering. The post Beyond Prompt Engineering: The Role of Tacit Knowledge in Software Engineering appeared first on GPT-Lab.
MIT News · Artificial Intelligence· news.mit.eduSep 16, 2026