Mistake Taxonomy Engine
Purpose: To analyze a student's incorrect work and classify the error type.
Mechanism: Uses Natural Language Processing (NLP) (like a fine-tuned Transformer model) to sort mistakes into categories, such as:
Conceptual Misunderstanding: Requires a new, deep explanation.
Calculation/Procedural Error: Requires targeted practice on execution.
Memory Decay: Requires simple retrieval practice (quizzes/flashcards).
Prerequisite Gap: Triggers an intervention to review foundational skills.
Prerequisite Flow Module (Knowledge Graph)
Purpose: To ensure students build knowledge on a solid, complete foundation.
Mechanism: Maintains a Knowledge Graph (using a graph database) that maps every concept and its hard prerequisite dependencies (e.g., limits must be mastered before derivatives).
Intervention: If the Mistake Taxonomy identifies a Prerequisite Gap, this module pauses the current advanced lesson and immediately schedules remedial learning and testing for the missing foundational skill. The student cannot proceed until the gap is closed, preventing the knowledge "pyramid" from collapsing.
Adaptive Spaced Repetition (ASR) Scheduler
Purpose: To calculate the ideal moment for the student to review material to combat memory decay.
Mechanism: The review interval is highly customized based on the error type from the Taxonomy Engine, not just a generic algorithm.
A severe Conceptual Misunderstanding triggers a shorter, more urgent review interval.
A simple Memory Decay error allows for a longer interval.
Content: The scheduler selects not just when, but what kind of review material is most effective (e.g., a video explanation vs. a set of procedural practice problems).
Summary
CARS is a dynamic system that treats every mistake as a diagnostic opportunity. By combining sophisticated error analysis with a structural understanding of knowledge dependencies, it provides a truly personalized, self-correcting, and continuously adaptive learning experience.
Log in or sign up for Devpost to join the conversation.