Date
Publisher
arXiv
Developing expertise in diagnostic reasoning requires practice with diverse student artifacts, yet privacy regulations prohibit sharing authentic student work for teacher professional development (PD) at scale. We present DrawSim-PD, the first generative framework that simulates NGSS-aligned, student-like science drawings exhibiting controllable pedagogical imperfections to support teacher training. Central to our approach are apability profiles--structured cognitive states encoding what students at each performance level can and cannot yet demonstrate. These profiles ensure cross-modal coherence across generated outputs: (i) a student-like drawing, (ii) a first-person reasoning narrative, and (iii) a teacher-facing diagnostic concept map. Using 100 curated NGSS topics spanning K-12, we construct a corpus of 10,000 systematically structured artifacts. Through an expert-based feasibility evaluation, K--12 science educators verified the artifacts' alignment with NGSS expectations (>84% positive on core items) and utility for interpreting student thinking, while identifying refinement opportunities for grade-band extremes. We release this open infrastructure to overcome data scarcity barriers in visual assessment research.
Study at a glance
- Question: Can a generative framework simulate realistic student science drawings with pedagogical imperfections to support teacher training?
- Setting and data: 100 curated K-12 Next Generation Science Standards topics, generating a corpus of 10,000 artifacts evaluated by K-12 science educators.
- Method: System development and expert-based feasibility evaluation.
Why it matters
Teachers need practice with diverse student work to build diagnostic skills, but privacy regulations prevent sharing real student artifacts for professional development at scale.
Key findings
- DrawSim-PD successfully generated a corpus of 10,000 structured multimodal artifacts across 100 Next Generation Science Standards topics using structured capability profiles.
- K-12 science educators verified the simulated artifacts' alignment with science standards, giving over 84% positive ratings on core evaluation items.
- Educators confirmed the artifacts' utility for interpreting student thinking while noting opportunities to refine outputs at the grade-band extremes.
Summary drafted with AI from the paper’s abstract and may contain errors. See the full paper for details.
What is the application?
Who is the user?
Why use AI?
