Fidelity table — openai/math @ adc7f124

Every verdict on this page is pre-referee: one model-assisted reading per family, validated mechanically, not yet re-read by a named human referee. The repository's own scope note is shown next to each verdict so you can judge for yourself. Verdict scale: full Lean states the headline claim · partial only one of several claims, or a special case · weaker-statement a nontrivially weaker statement · supporting-only a lemma or auxiliary statement. Click a row for the evidence.