Detecting Underspecification in Software Requirements via k-NN Coverage Geometry

TL;DR

geogap{} is a geometric approach that detects missing requirement types in software specifications by analyzing requirement coverage using pretrained sentence embeddings and k-nearest-neighbour distances, achieving high accuracy.

Contribution

It introduces a novel geometric method combining multiple scoring components to identify underspecified requirement types without requiring manual annotation.

Findings

Achieves 0.935 AUROC on PROMISE NFR benchmark.

Effectively detects completely absent requirement types.

Each component of the pipeline contributes measurable value.

Abstract

We propose \geogap{}, a geometric method for detecting missing requirement types in software specifications. The method represents each requirement as a unit vector via a pretrained sentence encoder, then measures coverage deficits through $k$-nearest-neighbour distances z-scored against per-project baselines. Three complementary scoring components -- per-point geometric coverage, type-restricted distributional coverage, and annotation-free population counting -- fuse into a unified gap score controlled by two hyperparameters. On the PROMISE NFR benchmark, \geogap{} achieves 0.935 AUROC for detecting completely absent requirement types in projects with $N \geq 50$ requirements, matching a ground-truth count oracle that requires human annotation. Six baselines confirm that each pipeline component -- per-project normalisation, neural embeddings, and geometric scoring -- contributes measurable value.