OutFigure
Learning infrastructure
“Getting the right answer does not necessarily mean learning happened.”
OutFigure grew out of what Cognivia’s error-modeling engine needed: a reliable way to measure what a learner knows, what changed, and what lasts. I’m building that infrastructure for other learning platforms.
Inside the project
The evidence behind progress
OutFigure follows the evidence behind a learner’s progress. It records each assessment, predicts how they will answer without help, and checks that prediction against what happens next.
From answer to learning record
- Assessment events
- Each answer, hint, piece of feedback and tutor turn, posted from your backend with a pseudonymous learner identifier. Corrections supersede; nothing is overwritten.
- Evidence record
- Every answer is either counted as independent evidence or set aside with a reason, under a named eligibility version. Assisted work is kept, and kept separate.
- Learner-concept state
- What a learner has answered unaided on a concept, how recent it is, and how far the evidence goes. Where it is thin, the state says so instead of reporting a score.
- Outcome audit
- Predictions are frozen when issued, then matched to the answers that arrive later. An answer that never arrives is an open case, not a failure.
Why I’m building it
“Not what they clicked. Not what they completed. Not whether they got one answer right. What actually changed in their head?”
Example assessment
Six answers. Five correct.
How much independent evidence?
Six answers, five correct, five assisted. One correct answer was given without help.
In development
Currently building. The same work on learning state, memory, and cognitive error patterns in Cognivia feeds into OutFigure.
