Question
What is relationship documentation?
Quick Answer
Writing down how two ideas relate prevents assuming a connection that does not exist.
Example: In 1967, psychologist Loren Chapman presented participants with lists of word pairs and asked them to estimate how often certain pairs appeared together. Participants consistently overestimated the co-occurrence of semantically related pairs — like 'bacon' and 'eggs' — even when the actual data showed no correlation between them. The participants were not lying or lazy. Their brains were filling in relationships that felt natural, bypassing what the data actually showed. Chapman called this illusory correlation: the tendency to perceive a relationship between two things based on expectation rather than evidence. His follow-up research with Jean Chapman in 1969 demonstrated the same effect among trained clinicians interpreting psychological test results — experts with years of experience still saw relationships that did not exist in the data, because those relationships matched their prior assumptions. The only reliable antidote was forcing the relationship to be stated explicitly and then checked against evidence.
This concept is part of Relationship Mapping in the How to Think curriculum.
Learn more in these lessons
Go beyond the answer
This topic is part of Context Engineering for Humans — a guided sequence of 16 lessons.
After completing this path you will engineer context deliberately: recognize which context you are in and load it on purpose, externalize the assumptions and decisions that machines and colleagues silently need, structure information so it survives handoff (identifiers, atomic units, explicit relationships), and manage the switching costs that fragment thinking. Your AI sessions start warm and your writing stops being misread.
Start the path →