AI methodology statement
This research was carried out with assistance from large language model systems: Codex (OpenAI) in the early stages, and Claude (Anthropic) thereafter, in the versions ChatGPT 6 Astra, Sol 5.6, Claude Opus 5.5, Sonnet 5.5, Haiku 5.5 and Fable 5.1. GitHub Copilot assisted in project maintenance. These tools materially affected every section of the paper.
They proposed and developed ideas in discussion with the author, searched the literature, carried out mathematical derivations and proofs, wrote the code for the experiments, the computer certificates and the Lean development, drafted, reviewed, and revised the text.
OpenAI Codex was also used for developing the research-workflow tooling of the project.
GitHub Copilot was used for code completion, reviews of pull requests and commit messages. Pull requests were also reviewed by Claude Haiku 5.5.
The author directed the research, contributed ideas, checked the proofs and the Lean statements, edited the manuscript and extended the literature search. The author verified the correctness and originality of all content, including references.
Back to top