Measuring Cross-Coverage Divergence for Threat-Intelligence Analysis
Maryam Fooladi, Federico Bottino, Alberto Trivero
Paper, NLPAICS 2026 — Alicante, Spain, 2026
Abstract
Open-source intelligence relies heavily on source-level signals — domain provenance, amplification patterns, account coordination — which work against fabricated infrastructure but offer little leverage on content from established state media that is correctly attributed and passes source-level heuristics. We ask whether framing divergence across editorially-coherent outlet blocs is measurable as a content-level observable, and whether cross-bloc divergence exceeds the editorial polarization already present within a single domestic press tradition. Building on the event-state (ρ_e) density-matrix formalism of Bottino et al. (2026), we represent each bloc by a density matrix on a 15-dimensional framing-feature space and compute pairwise trace distances. On two contested events (Hormuz blockade 2026, n = 16, direct state-aligned coverage; Navalny death 2024, n = 14, state-aligned bloc reconstructed via quoted-proxy), the cross-bloc distance between state-aligned and mainstream-Western outlets exceeds the US-right/US-left distance by a factor of roughly 1.8 on both events. Top-eigenvector decomposition attributes the gap to interpretable framing axes — economic consequences and conflict framing on Hormuz, morality on Navalny. We position this as a measurement rather than a classifier; at two events the work characterizes the observable's behavior rather than calibrating thresholds.