ContentGrapher
AboutResearchHelp Docs
Analyze →
ContentGrapher
Analyze →
AboutResearchHelp Docs

Reference

Short reference pages for ContentGrapher concepts and output formats.

Boundary ClassificationsWhat core, supportive, adjacent, and excluded mean, and what to do with each.Delta ViewHow snapshots work and how to read the before/after comparison after re-analysis.How do I read the concept map?What each mark and line on the concept map means, what you see when you select a concept or a connection, how to move around the map, and how to read the map as a list.Coverage ScoreHow the score is computed from integration quality and depth-weighted question coverage, and what it does not measure.Primary Retrieval RoleThe five PRR types, how to diagnose a mixed-role page, and what to do when the classification seems wrong.Next stepsHow the report groups its next steps by what you do first, what each task shows, and why some concepts have no task.Which questions did Google list for my topic?What the questions in "What did Google show for this topic?" are, where they come from, and how to use them.Audience SpecificationHow the reader knowledge level changes the analysis, what each level does, and when to set it.Why does my priority list look different from a colleague's?Priority tiers are calibrated to the knowledge level you set, not fixed by the content. The same concepts appear regardless; what changes is which ones the analysis judges as load-bearing for each reader.What are the three guidance types?The analysis writes three kinds of writing guidance: adding a missing concept, clarifying a concept that is present, and stating a relationship. In the report, each one appears as a task in the next steps.Why does my analysis show the same core concepts as last time?The concept set reflects your page content, not your session history. A stable concept list across runs is a quality signal, not a cache artifact.Why does the structural recommendation change between runs?The split or keep judgment is a weighted judgment, not a deterministic calculation. The per-concept advice, shown as page scope tasks, is stable even when the judgment varies.Why does the same concept sometimes get a different boundary classification between runs?Concepts clearly within scope land consistently across runs; so do concepts clearly out of scope. Concepts near the scope threshold can land on either side. This is expected, and the structural reason is more stable than the label.What does "essential" vs "important" vs "useful" mean?Priority tiers reflect the pipeline's judgment about what a specific reader needs from this page. Essential means comprehension breaks without it. Useful does not mean optional.Do top Google results do the same job as my page?What the first line of "What did Google show for this topic?" says, how it is worked out from the titles of the top results, and how to use it.Did Google show an AI answer for my topic?What the AI answer line of "What did Google show for this topic?" says, what it does not tell you, and what to do when Google showed an AI answer.Decide page scopeWhat "Decide page scope" tasks suggest, how to read a suggested separate page, and how to act on it.