Metraipolis › archive › dc_184dae31701f

Probing AI-generated physics solutions and preparing students to critique them — arXiv:2608.12533

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.12533
License (as archived)
CC0-1.0
Archived
2026-10-19T05:07:35.387Z
SHA-256 of the archived text
4cc4d8890503dad525d87d871375d703978d5c5cfa019f011dec9c923d980cc0
Stable URL of this page
https://metraipolis.com/documento/dc_184dae31701f

How to cite

Probing AI-generated physics solutions and preparing students to critique them — arXiv:2608.12533 — arXiv (en), https://arxiv.org/abs/2608.12533 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_184dae31701f (Metraipolis archive dc_184dae31701f, sha256 4cc4d8890503dad525d87d871375d703978d5c5cfa019f011dec9c923d980cc0)
BibTeX
@misc{dc184dae31701f,
  title = {Probing AI-generated physics solutions and preparing students to critique them — arXiv:2608.12533},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.12533},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_184dae31701f; sha256 4cc4d8890503dad525d87d871375d703978d5c5cfa019f011dec9c923d980cc0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12533. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This study examines Artificial Intelligence (AI)-generated physics solutions from two connected perspectives: how prompt design shapes these solutions and how students can be prepared to critique them. Using a rotational-mechanics problem, we adapted a problem-classification framework to examine prompt variations, evaluating OpenAI's o4-mini responses with the Minnesota Assessment of Problem Solving (MAPS) rubric. Well-specified prompts improved solution completeness; underspecified and multimodal prompts exposed weaknesses in physics reasoning and correctness. In the student-evaluation phase, 24 introductory physics lab groups evaluated an o4-mini solution to this problem after either independently solving a related problem or critiquing its AI-generated solution with MAPS-based reflection questions. Problem-solving-only groups exhibited uncritical or misconception-based critiques; MAPS-guided groups identified more expert-aligned issues, including skipped numerical procedures and undefined notation. Together, our findings contribute to physics education research by showing how AI-generated solutions can ground both model-reasoning benchmarks and improved student critique of that reasoning through MAPS-based reflection.

Tema degli esploratori: ricerca e scienza aperta (retro-catalogo arXiv: annunci del 2026-08-14 in physics.ed-ph).
Categorie arXiv: Physics Education (physics.ed-ph).
Pagina del lavoro: https://arxiv.org/abs/2608.12533 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T04:57:30.981Z dalla pagina https://arxiv.org/catchup/physics.ed-ph/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).