Skip to content

Remora Free Body Diagram Require-GenAI task

Design · All designs
Evidence · 1 claim (1 for) · 1 study (1 design), q2 · 0 of 1 report an effect size · 1 claim rests on one study

Description

A task deployed in an undergraduate introductory physics course in which students collaborate with GenAI to construct the most accurate free body diagram of a remora fish attached to a shark. The problem meets the accuracy-ceiling criterion because an accurate diagram requires forces specific to remora biology that "GenAI consistently failed to produce correctly without disciplinary guidance from the student." It elicits five categories of process artifact (tool used, prompting summary, final output, critique, assumption reflection), with Q2 evidencing Physics-Driven AI Interaction and Q4 evidencing Physics-Grounded Evaluation.

Design Implications

Context

Requirements

  • Students must document their own reasoning about what GenAI got wrong and why, so cognitive contribution is distinguishable from AI output

Constraints

  • The task does not require students to submit interaction logs directly; Q2 functions as a self-report of the prompting conversation

Target Learners

  • Undergraduate introductory physics students

Learning Goals

  • Physics-driven AI interaction and physics-grounded evaluation of AI-generated content

Claims

Examples

-

Key Sources

  • Gao, Y., Chen, Z., Li, M., & Zhai, X. (2026). Generative AI as a Design Variable: An Evidence-Centered Framework for Principled Governance in STEM Assessment. doi:10.48550/arxiv.2605.24837
Page metadata
Field Value
type design
id remora-free-body-diagram-task
title Remora Free Body Diagram Require-GenAI task
description A task deployed in an undergraduate introductory physics course in which students collaborate with GenAI to construct the most accurate free body diagram of a remora fish attached to a shark.
status review
generated by process:settle-candidates on 2026-10-11
trust unverified — no one has confirmed this page's content
sources 1 — gao-2026

Frontmatter is the page's machine-readable record — see the Schema & Guide.