A.Appendix

A.1 Repository

The Nanometers harness is implemented as a single-file Python script ( nanometers.py) with full source available on GitHub:

github.com/nanometers

Python 3.11+ · MIT License · async/await architecture

A.2 Usage

# Compute Φ(π728)\Phi(\pi_{728})

python nanometers.py 728


# Manual problem input

python nanometers.py --manual


# Run FCF_C only, skip verification

python nanometers.py 728 --models claude --skip-aristotle

A.3 Dependencies

The harness requires the following Python packages:

PackageRole
httpxAsync HTTP client for problem acquisition
openaiInference operator FRF_R
anthropicInference operator FCF_C and synthesis Σ\Sigma
beautifulsoup4HTML parsing for Fetch\texttt{Fetch}
python-dotenvAPI key management

A.4 Prompt Specification

The system prompt for FRF_R (GPT-5.4 Pro) constrains outputs to deductive strategies:

“You are an expert mathematician specializing in combinatorics, number theory, and additive combinatorics. Produce a rigorous, publication-quality proof. Require: precise logical structure with clearly stated lemmas, complete epsilon-delta arguments where applicable, explicit bounds and constants, and citation of relevant known results.”

The system prompt for FCF_C (Claude Opus 4.6) constrains outputs to constructive strategies:

“You are a research mathematician known for creative, non-obvious constructions and unexpected connections between subfields. Prioritize: probabilistic method arguments, algebraic and explicit constructions, applications of the Lovász Local Lemma, and novel approaches outside standard techniques.”

A.5 Transparency

All model outputs are logged without modification. The harness performs no filtering, editing, or post-processing of mathematical content beyond the synthesis step described in Section 2.3. Every generated file includes an attribution header identifying it as AI-generated output.

This project makes no claims of having solved any open problem. All results are presented as candidate proofs subject to verification via the predicate VV defined in Section 2.4.