What Do Text Prompts Actually Carry in Zero-Shot Anomaly Detection? Geometry, Not Semantics

Zero-shot anomaly detection with CLIP is standardly credited to the defect semantics of text prompts. This assumption is central for two reasons. The text branch is the only part that ever mentions defects, and prompt design is the field's main axis of progress. We argue instead that the text branch contributes only geometry, not semantics: a single direction from normal to anomalous in feature space. Vision alone supplies a functionally equivalent one, to the same effect. (1) Reduction. The text branch of both representative pipelines provably reduces to a monotone function of a single projection onto one direction (rank correlation $>0.99$), which turns the question of what text contributes into the question of what makes this direction work: geometry or semantics. (2) Substitution. A direction computed from a few normal images, swapped in for the text pair with no other change, matches the complete pipeline on all combinations of pipeline and benchmark. The direction proves not only sufficient but exhaustive: across 5k diverse prompts, directional alignment alone determines performance ($R^2\ge 0.8736$) and semantics add nothing ($\Delta R^2\le 0.0012$). (3) Prediction. For 10k entirely unseen prompts, we first forecast each prompt's performance, one forecast per prompt, from a single geometric quantity, without running the pipeline. We then run the pipeline on all 10k prompts and measure the actual performance of each. The per-prompt forecasts match the per-prompt measurements closely, ranking unseen prompts at correlation $0.8440$ to $0.8643$ ($p\approx 0$) with no systematic bias (calibration slope within $0.04$ of unity). Across these analyses, text prompts in zero-shot anomaly detection carry geometry, not semantics. The geometry is a direction from normal to anomalous, and vision alone supplies an equivalent one, to the same effect. We call this the modal load-bearing of text.