The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
ChatGPT and the frustrated Socrates
Open accessAbstract
Abstract We present a case study of a conversation between ourselves and an artificial intelligence-based chatbot ChatGPT. We asked the chatbot to respond to a basic physics question that will be familiar to most physics teachers: ‘A teddy bear is thrown into the air. What is its acceleration in the highest point?’ The chatbot’s responses, while linguistically quite advanced, were unreliable in their correctness and often full of contradictions. We then attempted to engage in Socratic dialogue with the chatbot to resolve the errors and contradictions, but with little success. We found that ChatGPT is not yet good enough to be used as a cheating tool for physics students or as a physics tutor. However, we found it quite reliable in generating incorrect responses on which physics teachers could train assessment of student responses.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Failures of LLMs include lack of knowledge about object attributes (e.g., size, weight, softness) (Wang et al., 2023c; Liu et al., 2022b; Shu et al., 2023; Kondo et al., 2023), spatial relationships (e.g., above, inside, next to) (Liu et al., 2022b; Shu et al., 2023; Kondo et al., 2023), simple physical laws (e.g., gravity, motion, and force) (Gregorcic & Pendrill, 2023), and object affordance”
From Large Language Model Reasoning Failures (2026) · cites this paper as Gregorcic & Pendrill, 2023
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hestenes, D., Wells, M., & Swackhamer, G. (1992) · The Physics Teacher · doi:10.1119/1.2343497 · Cited by 3,235
Toward an Epistemology of Physics
diSessa, A. A. (1993) · Cognition and Instruction · doi:10.1080/07370008.1985.9649008 · Cited by 1,443
Common sense concepts about motion
Halloun, I. A., & Hestenes, D. (1985) · American Journal of Physics · doi:10.1119/1.14031 · Cited by 852
Science, Language, and Literacy : Case Studies of Learning in Swedish University Physics
Airey, J. (2009) · Uppsala University Publications (Uppsala University) · Cited by 113
“Force,” ontology, and language
Brookes, D. T., & Etkina, E. (2009) · Physical Review Special Topics - Physics Education Research · doi:10.1103/physrevstper.5.010110 · Cited by 93
Playing games with AIs: the limits of GPT-3 and similar large language models
Sobieszek, A., & Price, T. (2022) · Minds and Machines · doi:10.1007/s11023-022-09602-0 · Cited by 86
Critical thinking in national tests across four subjects in Swedish compulsory school
Nygren, T., Haglund, J., Samuelsson, C. R., af Geijerstam, Å., & Prytz, J. (2018) · Education Inquiry · doi:10.1080/20004508.2018.1475200 · Cited by 48
Students making sense of motion in a vertical roller coaster loop
Pendrill, A.-M., Eriksson, M., Eriksson, U., Svensson, K., & Ouattara, L. (2019) · Physics Education · doi:10.1088/1361-6552/ab3f18 · Cited by 17
Self-citationForce, acceleration and velocity during trampoline jumps—a challenging assignment
Pendrill, A.-M., & Ouattara, L. (2017) · Physics Education · doi:10.1088/1361-6552/aa89cb · Cited by 11
Self-citation
Cited by
Sorted by citations
Items 101–125 of 125
Assessment Design Before and After the Emergence of Generative AI
Tran, Q. N., Ngoc, T. N., Pham, T., Felipe, A., Huynh, T., & Tran, Q. N. (2024) · Lecture notes in mechanical engineering · doi:10.1007/978-3-031-59042-9_12 · Cited by 1
Prompts socráticos: Una propuesta de uso pedagógico en un curso de Filosofía del Derecho
Benfeld, J. (2024) · Revista Pedagogía Universitaria y Didáctica del Derecho · doi:10.5354/0719-5885.2024.73547
Perbandingan Kapabilitas Respons Chatgpt Dan Gemini Terhadap Pertanyaan Konseptual Tentang Optik
Azizah, M. A., & Mansyur, J. (2025) · JPFT (Jurnal Pendidikan Fisika Tadulako Online) · doi:10.22487/jpft.v12i1.3510 · Cited by 3
REVOLUTION OR DISTRACTION? ANALYZING GENERATIVE AI’S IMPACT ON UNDERGRADUATE STUDENT PERFORMANCE
Abdulrauf, A., Abodunrin, O. B., & Omoloba, O. (2025) · FUDMA Journal of Sciences · doi:10.33003/fjs-2025-0904-3574
Networked observatory for virtual astronomy (NOVA): teaching astronomy with AI
Pinochet, J. (2025) · Physics Education · doi:10.1088/1361-6552/ade358
Enhancing Scenario-Based Modeling Using Large Language Models
Harel, D., Katz, G., Marron, A., & Szekely, S. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-96841-9_3
Contract Interpretation and Artificial Intelligence
Arietti, E., & Smítal, J. (2025) · AUC IURIDICA · doi:10.14712/23366478.2025.677
A Survey of the Applications of Large Language Models in the Educational Sector
Muchina, F. E., Damle, A., Yadav, S., Kaushik, A., & Morris, D. B. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-9195-3.ch006
Budimaier, F., Fasching, M., Reumann, A., & Campos, E. (2026) · Physical Review Physics Education Research · doi:10.1103/n611-h1mh
Capability of ChatGPT and Gemini in solving optics problem
Azizah, M. A., Werdhiana, I. K., Kaharu, S. N., & Mansyur, J. (2026) · AIP conference proceedings · doi:10.1063/5.0328898
Fan, J., Huang, M., Zhao, X., Fang, Y., Zhang, H., & Lu, J. (2026) · TechTrends · doi:10.1007/s11528-026-01188-z · Cited by 1
The Janus-Faced Nature of AI in STEM Education
Wulff, P. (2026) · Maarif global education series · doi:10.1007/978-981-95-9023-0_4
Anonymous, Chen, X., Xiong, Y., Xu, S., Li, Q., & Zhou, S. (2026) · Physical Review Physics Education Research · doi:10.1103/9t5b-twsb
Learning by Assessing AI: Peer Assessment of Large Language Models in an Introductory Logic Course
Jakobsen, D., Thorvaldsen, S., & Øhrstrøm, P. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-32115-2_40
Churiyah, M., Rusmana, D., Permansah, S., Dirgatama, C. H. A., & Indrawati, C. D. S. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7155486
Soyoof, A., Reynolds, B. L., & Liu, G. (2026) · Acta Psychologica · doi:10.1016/j.actpsy.2026.107759
Çörekci, G., & Çörekci, A. M. (2026) · Physics Education · doi:10.1088/1361-6552/ae9bf4
Akhmedov, B. B., & Yuldashev, M. (2026) · Physics Education · doi:10.1088/1361-6552/aeab1e
Santoso, P. H., Nurlina, N., & Mutmainna, M. (2026) · Physics Education · doi:10.1088/1361-6552/aeab3f
Do-It-with-AI Framework for Invention: A Kundt’s Tube Case Study
Eadkhong, T., Attachaiya, P., Luanghiranpusit, S., Chimtab, J., Dam-O, P., Danworaphong, S., & Sirisathitkul, C. (2026) · Inventions · doi:10.3390/inventions11050108
Metadata
- Authors
- Gregorcic, B., & Pendrill, A.-M.
- Affiliations
- Uppsala University (SE)
- Lund University (SE)
- Corresponding author
- Gregorcic, Bor
- Venue
- Physics Education
- Publisher
- IOP Publishing
- Published
- 2023-03-22
- Volume
- 58
- Issue
- 3
- Pages
- 035021
- ISSN
- 0031-9120 (ISSN-L)
- 1361-6552
- OpenAlex
- W4360846784
- Cited by
- 125
- References
- 9
- Citations by year
- 2026: 18 · 2025: 42 · 2024: 37 · 2023: 28
- FWCI
- 29.34
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Physics Education (publishedVersion, cc-by)
- Uppsala University Publications (Uppsala University) (submittedVersion, other-oa)
- Lund University Publications (Lund University) (submittedVersion)
- Topics
- Social Sciences › Education › Artificial Intelligence in Education
- Physical Sciences › Computer Science › Artificial Intelligence › Intelligent Tutoring Systems and Adaptive Learning
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- ChatGPT, large language models, Socratic dialogue, physics tutoring, academic dishonesty, incorrect responses, physics misconceptions, chatbot reliability
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
