{"ID":5439474,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-02T18:49:48.32244458Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.30824","arxiv_id":"2606.30824","title":"Information Terra: A Narrative-Anchored Semantic-First Projection of Document Embeddings","abstract":"We introduce Information Terra, a narrative-anchored semantic-first projection that places a document corpus on an Earth-like globe whose poles are two user-chosen endpoint documents and whose prime meridian is the great-circle geodesic between them on the embedding hypersphere -- so latitude encodes narrative progress and longitude thematic deviation. Land features are recovered from document density via kernel density estimation and labeled by theme. A narrative trail built from the underlying narrative coherence graph, and constrained to be monotone in geodesic progress, provides a readable storyline. The projection's axes are semantically grounded in the user's chosen narrative endpoints, and the globe metaphor affords rotation and antipodal reading. We demonstrate the method on a 540-article Cuban Protests corpus, showing a storyline from Obama's 2016 visit to the 2021 International Aid during the protests.","short_abstract":"We introduce Information Terra, a narrative-anchored semantic-first projection that places a document corpus on an Earth-like globe whose poles are two user-chosen endpoint documents and whose prime meridian is the great-circle geodesic between them on the embedding hypersphere -- so latitude encodes narrative progress...","url_abs":"https://arxiv.org/abs/2606.30824","url_pdf":"https://arxiv.org/pdf/2606.30824v1","authors":"[\"Brian Keith-Norambuena\",\"Fausto German\",\"Chris North\"]","published":"2026-06-29T18:52:52Z","proceeding":"cs.HC","tasks":"[\"cs.HC\",\"cs.CL\",\"cs.IR\"]","methods":"[]","has_code":false}