ContentGrapher
AboutResearchHelp Docs
Analyze →
ContentGrapher
Analyze →
AboutResearchHelp Docs
← All reference pages

Boundary Classifications

What core, supportive, adjacent, and excluded mean, and what to do with each.

What boundary classifications are

Every concept on your page is classified by whether it belongs there. The classification is not about quality; it is about scope. A well-written section on the wrong topic still weakens the page's structural signal — a page covering unrelated topics is harder for AI systems to accurately represent for any one of them.

ContentGrapher assigns one of four labels to each concept it identifies in your content. Your page's primary topic is always classified as core — this is a fixed rule, not a judgment call. Every other concept is evaluated based on its relationship to the page's structural role.

To see the classification of a concept, select the concept on the concept map. The detail shows the classification under "On this page", below the statement of how well the page explains the concept.

At a glance

Quick reference for how each classification is defined, how the report labels it, and what to do with it.

ClassificationLabel in the reportMeaningAction
CoreCore to this pageEssential to what this page does. The primary topic is always core.Make sure it is well integrated. Select the concept on the map to see how well the page explains it.
SupportiveSupporting contextProvides useful context but does not need full explanation here.A brief, accurate mention is sufficient. Do not over-explain.
AdjacentPossible separate topic · brief mentions can stayBelongs on a separate, more focused page.Link to the concept's dedicated page rather than explaining it here.
ExcludedAssessed as outside this page’s scopeOut of scope entirely. Its presence dilutes retrieval accuracy.Remove or significantly reduce.

Core

A core concept is essential to what this page is trying to do. If your page explains how OAuth 2.0 works, then "authorization code flow" is core. It must be covered fully at the depth this page's audience and retrieval role require.

Action: Make sure every core concept is well integrated. Select the concept on the map: "On this page" shows how well the page explains it. "Well integrated" means it is fully covered. "Lightly explained", "Needs more explanation" or "Naming varies" means it needs more work, and the next steps can include a task for it. See Coverage Score for how these states are defined.

Supportive

A supportive concept provides useful context but does not need to be fully explained here. It grounds the core without becoming its own topic.

Action: A brief, accurate mention is sufficient. Do not over-explain supportive concepts; doing so pulls focus from the page's core topic and introduces content that belongs elsewhere.

Adjacent

An adjacent concept belongs on a separate, more focused page. It may be closely related, but it has its own depth of explanation that this page cannot and should not provide.

Action: Link to the adjacent concept's dedicated page rather than explaining it here. If that page does not exist, creating it is a content planning task, not a gap in this page. The report label "Possible separate topic · brief mentions can stay" means that a short mention with a link can stay on this page.

If the analysis suggests a separate page for the concept, the next steps include a "Decide page scope" task with the reason that the analysis gives. See the guide to page scope tasks for how to act on it.

This "belongs elsewhere" judgment is the classification ContentGrapher has studied most closely. The Agreement Study, ContentGrapher's published research, compared how eight AI models make this exact call on the same set of pages, with a sample of those calls reviewed by a panel of models from five different makers. It is a useful read if you want to understand how consistent this judgment is and why a borderline concept can land on either side of the line.

Excluded

An excluded concept is out of scope entirely. In ContentGrapher's model, its presence dilutes the page's structural signal: a page that mixes unrelated topics is harder for AI systems to accurately represent for any one of them.

Action: Remove or significantly reduce excluded content. If you believe the classification is wrong, check whether the concept introduces a different structural role (explain, guide, compare, evaluate, or convert) than this page's primary role.

The reason behind a classification

Select a concept on the concept map. Under "On this page", the detail shows its classification and, on the next line, the reason. That line starts with "Why".

For the page's main topic, the line reads "Why: it is the main topic of this page, so it is always core." For other core and supportive concepts, it says that the analysis judged the concept essential, or relevant but secondary, to the page's role, and recorded no other reason. The analysis records a reason only for adjacent and excluded concepts.

For an adjacent or excluded concept, the line starts with "Why · not verified:" and gives one or more reasons: "it belongs on a page with a different role", "it needs its own full explanation to be useful", "readers look for it as a task of its own", or "it belongs to an earlier or later step in the reader’s task". The analysis wrote these reasons, and nobody has checked them against your page. If the analysis recorded no reason, the line reads "Why: the analysis recorded no reason for this label."

When a classification leads to a page-scope suggestion, the "Decide page scope" task shows the reason for that suggestion under "Recommendation · not verified". Check that reason against your page before you act on it.

For borderline concepts, the label can change between runs. In the Findability Study, the lists of belongs-elsewhere concepts overlapped by about 60% on average across repeated runs, against a pre-registered target of 70%, and came in under that target. The figures are study-specific; your page will differ. If you re-analyze and a borderline concept lands on the other side of the line, compare the page-scope tasks in both reports before you change the page.

The upper part of the detail of the selected concept Cache invalidation: "Selected concept", the name "Cache invalidation" and the button "Page overview". Under "On this page": "Needs more explanation" with the amber dot, "Possible separate topic · brief mentions can stay" and the line "Why · not verified: it belongs on a page with a different role; readers look for it as a task of its own."

If the classification seems wrong

First, select the concept on the map and read its classification, the "Why" line under it, and how well the page explains it. If the concept has a "Decide page scope" task, read the reason in that task. It is the most direct path to understanding whether to accept or dispute the classification.

Second, check what primary retrieval role ContentGrapher detected for this page. A concept classified as adjacent is often correctly placed because it belongs to a different stage of the explanation journey than this page's role allows. See Primary Retrieval Role for how roles are defined.

Third: your page's primary topic (the anchor) is always classified as core. This is a fixed rule that the analysis cannot change.

Fourth: if you believe the page's primary role is miscategorized, check the topic first. An incorrect topic produces an incorrect role classification. After the concept map appears and before the full analysis finishes, a "Topic" line shows above the map. Select "Edit topic" (the pencil) beside it to correct the topic; ContentGrapher then runs a new analysis with the corrected topic. The pencil is not available while the full analysis runs, and the Topic line no longer shows once the analysis has finished.

A note on borderline calls. In the Agreement Study, a five-model review panel from five different makers judged a sample of belongs-elsewhere classifications and found that roughly four in five were at least defensible while roughly three in five were clearly right. That gap, around 20% of sampled calls, is where the panel itself disagreed. These are the borderline classifications where reasonable expert reviewers can land on either side. The figures are specific to that study; the classification on your page will reflect your content. The practical reading: when a call feels contestable, weigh the structural reason against your page, and decide on the page itself rather than on the label alone.

Why this matters

AI systems retrieve by concept association. In ContentGrapher's model, a page that tries to explain everything about a topic ends up explaining nothing fully. Boundary classification is how ContentGrapher identifies scope dilution.

Related topics

→Coverage Score→Primary Retrieval Role→How do I read the concept map?→Why does the same concept sometimes get a different boundary classification between runs?
← All reference pages