The sector-map demo answered a phrase we gave it. The real prize: let the corpus tell us which themes are rising before anyone names them. This POC clusters 88M filing sentences with no keywords, no labels — and ranks what's accelerating. The test of whether it works: does it rediscover the themes we already know are emerging, on its own?
Each cluster's member-count by year is its intensity trend (the sample is equal-per-year). These three fell straight out of the unlabeled data — the exact themes a human would flag today, surfaced with zero supervision.
The AI / data-center cluster runs 0 0 0 0 2 0 → 51 — a theme that did not exist in the filing language, then exploded. That's the whole thesis in one row: emergence, caught automatically.
Pull embeddings evenly across 2019–2025 from qdrant. Equal-per-year makes member-count-by-year a normalized trend for free.
cuML GPU UMAP (768→50) collapses sector/boilerplate vocabulary so HDBSCAN groups by theme, not industry.
Rank by acceleration off a low base × multi-issuer breadth × steady climb (ρ) × novelty vs our 529 classifiers.
Qwen (free/cheap) judges theme vs boilerplate and names the survivors — the judgment is entirely in the text.
Beyond the validation set, the same run flagged these accelerating, multi-issuer themes (boilerplate gated out by the LLM pass).
build_spam_filter.py as a pre-gate.