arXiv subjects

Shruti Shrestha

Publications and source records attributed to Shruti Shrestha.

4 recordsLinked to original sources

arXiv2026

How Well Do AI Systems Solve AP Physics? A Comparative Evaluation of Large Language Models on Algebra-Based Free Response Questions

The rapid advancement of LLMs has generated growing interest in their potential role in physics education and assessment, yet a focused evaluation of their performance on multi-faceted, free-response physics problems remains underexplored. In this study, we systematically evaluate the performance of four widely accessible AI systems-ChatGPT 4.1 mini, Gemini 2.5 Flash, Claude 4.0 Sonnet, and DeepSeek R1-on AP Physics 1 and 2 free-response questions administered between 2015 and 2025. Model-generated solutions were produced under standardized exam-style prompting and evaluated by three independent physics experts using official College Board scoring guidelines. All models achieved relatively high mean scores (82-92%), indicating strong capability in structured algebraic problem solving. However, substantial year-to-year variability was observed, particularly for AP Physics 1, where statistical testing revealed no consistent performance hierarchy among models. In contrast, AP Physics 2 results showed statistically significant differences, with Gemini and DeepSeek demonstrating more consistent performance than Claude. A qualitative analysis revealed recurring error patterns across all models, including misinterpretation of diagrams and graphs, incorrect graph construction, incorrect reasoning about vector direction, circuit topology errors, partial and misleading qualitative explanations, and difficulties applying three-dimensional concepts such as the right-hand rule. These findings suggest that while contemporary AI systems can effectively support routine physics problem solving, they remain limited in tasks requiring spatial reasoning, visual interpretation, and conceptual integration. The results highlight both the instructional potential and current pedagogical limitations of AI-assisted learning tools in physics education.

physics.ed-ph↗

arXiv2024

Validating polyp and instrument segmentation methods in colonoscopy through Medico 2020 and MedAI 2021 Challenges

Automatic analysis of colonoscopy images has been an active field of research motivated by the importance of early detection of precancerous polyps. However, detecting polyps during the live examination can be challenging due to various factors such as variation of skills and experience among the endoscopists, lack of attentiveness, and fatigue leading to a high polyp miss-rate. Deep learning has emerged as a promising solution to this challenge as it can assist endoscopists in detecting and classifying overlooked polyps and abnormalities in real time. In addition to the algorithm's accuracy, transparency and interpretability are crucial to explaining the whys and hows of the algorithm's prediction. Further, most algorithms are developed in private data, closed source, or proprietary software, and methods lack reproducibility. Therefore, to promote the development of efficient and transparent methods, we have organized the "Medico automatic polyp segmentation (Medico 2020)" and "MedAI: Transparency in Medical Image Segmentation (MedAI 2021)" competitions. We present a comprehensive summary and analyze each contribution, highlight the strength of the best-performing methods, and discuss the possibility of clinical translations of such methods into the clinic. For the transparency task, a multi-disciplinary team, including expert gastroenterologists, accessed each submission and evaluated the team based on open-source practices, failure case analysis, ablation studies, usability and understandability of evaluations to gain a deeper understanding of the models' credibility for clinical deployment. Through the comprehensive analysis of the challenge, we not only highlight the advancements in polyp and surgical instrument segmentation but also encourage qualitative evaluation for building more transparent and understandable AI-based colonoscopy systems.

eess.IV↗

arXiv2018

Efficiency and timing performance of the MuPix7 high-voltage monolithic active pixel sensor

The MuPix7 is a prototype high voltage monolithic active pixel sensor with 103 times 80 um2 pixels thinned to 64 um and incorporating the complete read-out circuitry including a 1.25 Gbit/s differential data link. Using data taken at the DESY electron test beam, we demonstrate an efficiency of 99.3% and a time resolution of 14 ns. The efficiency and time resolution are studied with sub-pixel resolution and reproduced in simulations.

physics.ins-det↗

arXiv2016

The MuPix System-on-Chip for the Mu3e Experiment

Mu3e is a novel experiment searching for charged lepton flavor violation in the rare decay $μ^+ \rightarrow e^+e^-e^+$. Decay vertex position, decay time and particle momenta have to be precisely measured in order to reject both accidental and physics background. A silicon pixel tracker based on $50\,μ$m thin high voltage monolithic active pixel sensors (HV-MAPS) in a 1 T solenoidal magnetic field provides precise vertex and momentum information. The MuPix chip combines pixel sensor cells with integrated analog electronics and a periphery with a complete digital readout. The MuPix7 is the first HV-MAPS prototype implementing all functionalities of the final sensor including a readout state machine and high speed serialization with 1.25 Gbit/s data output, allowing for a streaming readout in parallel to the data taking. The observed efficiency of the MuPix7 chip including the full readout system is $\geq99\%$ in a high rate test beam.

physics.ins-det↗