Rewriting a resume without changing its evidence flips up to 41% of screening decisions.

Competence-preserving perturbations render occupation-grounded profiles into multiple presentations varying in wording, structure, polish and extraction quality, with a deterministic gate excluding any variant that alters the underlying qualification evidence. Llama-3.1-8B with its native chat template had the strongest validity at 0.781 yet reversed 29.6% of matched pairwise decisions; Mistral-7B-v0.3 reached 0.644 validity with a 41.4% flip rate. Native chat formatting improved validity for several models without removing the instability, so screening validity and presentation stability are separate properties you have to test for separately.