Back to indexGetting startedMar 30, 20264 min

Getting Started with the Semantic Map

A short walkthrough for selecting countries, reading point clusters, and understanding what semantic proximity means in practice.

Open atlas Country Selection and Semantic Map View Official ConstitutionalMap AI tutorial playlist

What the map is actually showing

Each point in the 3D canvas stands for one constitutional article or a similar legal unit. Nearby points are not grouped by country first; they are grouped by semantic similarity.

That means the best way to start is not to load everything at once. Select one or two countries and watch how their articles spread across the same global semantic space.

A simple first workflow

Pick one country as your anchor and add a second country for contrast. This keeps the canvas legible and makes the first clusters easier to interpret.

Open the atlas in your locale and select one country on the map.
Add a second country with a different constitutional tradition.
Look for dense regions before opening any article details.
Switch color mode between countries and global clusters.

How to read the visualization

What You Are Seeing

Each point in the 3D view represents a constitutional article or other meaningful legal unit. Nearby points are not nearby because they come from the same country, but because the language of those passages is semantically similar. Use country selection to compare how different constitutions occupy the same semantic terrain.

The map and the country list are selection tools. They decide which constitutions are loaded into the scene. Selecting more countries does not change the geometry of the embedding itself; it changes which parts of that global semantic space you can inspect.

Semantic Space

The embedding turns legal text into vectors, and the clustering step groups vectors that tend to discuss related constitutional themes. In country mode, color shows political origin. In cluster mode, color shows thematic neighborhood.

Large, dense clouds usually indicate recurring constitutional ideas such as rights, institutions, emergency powers, elections, or amendment rules. Isolated points often mark unusual provisions, rare wording, or country-specific constitutional design choices.

The platform offers two types of search: keyword search finds literal term occurrences, while semantic search retrieves conceptually nearby passages even without matching terms. Search results highlight regions of the semantic space in the 3D canvas, linking what you read to where it sits.

How to Read the Metrics

In the country statistics, Coverage measures how much of the global cluster landscape a constitution reaches. Entropy measures how evenly its segments are distributed across that landscape: high entropy suggests a broader semantic spread, while low entropy suggests concentration in fewer themes.

In the article detail panel, Global Cluster is the identifier of the thematic group assigned to that segment in the worldwide clustering. When the value is -1, it means the segment was left outside the defined thematic groupings in that global step. Probability indicates how confidently the clustering model placed that segment in that group: higher values mean a cleaner fit, while lower values usually mark more ambiguous or boundary cases.