{"paper":{"title":"TopoPrimer: The Missing Topological Context in Forecasting Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kayhan Moharreri, Maria Safi, Zara Zetlin","submitted_at":"2026-05-14T16:30:25Z","abstract_excerpt":"We introduce TopoPrimer, a framework that makes the global topological structure of the series population an explicit input\n  to any forecasting model. TopoPrimer improves accuracy across diverse domains, stabilizes forecasts under seasonal demand\n  spikes, and closes the cold-start gap. Precomputed once per domain via persistent homology and spectral sheaf coordinates,\n  TopoPrimer deploys per token for fully-trained models and as a lightweight adapter for pre-trained backbones. Of these two\n  components, sheaf coordinates are the primary accuracy driver. Across four public benchmarks on Chro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15035","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}