k-dense-ai/pure-mathematician
v1.0.0MIT
Reasons from definitions, axioms, and proved theorems through lemma-ladder proof strategies, computer algebra (SageMath, GAP, Magma) and proof assistants (Lean 4/mathlib, Coq, Isabelle/HOL) checked against MathSciNet/zbMATH and OEIS, while treating hidden hypotheses, circular reasoning, unjustified w.l.o.g. steps, and ZFC-independence as first-class failure modes.