Search Results - python code

LLM-Assisted Translation and Bounded Model Checking of Python Code

Authors: Shivaji, Shivkumar Lobakhina, Natalia Havelund, Klaus et al.

Source: Shivaji, S, Lobakhina, N, Havelund, K, Pinto, A & Cordeiro, L 2026, LLM-Assisted Translation and Bounded Model Checking of Python Code. in 3rd Artificial Intelligence ISoLA.

Subject Terms: code translation, large language models, formal verification, bounded model checking, Python

Access URL: https://research.manchester.ac.uk/en/publications/6fa0e994-01cb-4f54-a168-856aff99852a

PyGress: Tool for Analyzing the Progression of Code Proficiency in Python OSS Projects

Authors: Charatvaraphan, Rujiphart Chatchaiyadech, Bunradar Sukijprasert, Thitirat et al.

Source: 2025 40th IEEE/ACM International Conference on Automated Software Engineering (ASE). :3997-4000

Subject Terms: Software Engineering (cs.SE), FOS: Computer and information sciences, Software Engineering

Access URL: http://arxiv.org/abs/2511.05821

CodeGuide: An Artificial Intelligence Powered vs Code Extension for Automated Python Code Generation, Error Detection and Code Correction

Authors: Solapuram Shreeya Koya Bharath Kumar Chennupati Vamsee Krishna

Source: 2025 4th International Conference on Applied Artificial Intelligence and Computing (ICAAIC). :1578-1584

A Python Code Extraction and Analysis Method—Theoretical and Empirical Research

Source: Computer Science and Application. 16:268-280

A Taxonomy of Inefficiencies in LLM-Generated Python Code

Authors: Abbassi, Altaf Allah Da Silva, Leuson Nikanjam, Amin et al.

Source: 2025 IEEE International Conference on Software Maintenance and Evolution (ICSME). :393-404

Subject Terms: Software Engineering (cs.SE), FOS: Computer and information sciences, Software Engineering

Access URL: http://arxiv.org/abs/2503.06327

Retrieve, Refine, or Both? Using Task-Specific Guidelines for Secure Python Code Generation

Authors: Tony, Catherine Iannone, Emanuele Scandariato, Riccardo

Source: 2025 IEEE International Conference on Software Maintenance and Evolution (ICSME). :368-379

Design and Implementation of an LCS and Weight-Based Birthmark System for Detecting Python Code Theft

Authors: Seong-Min Kim Won-Chan Lee Heewan Park

Source: Journal of the Korea Society of Computer and Information. 30:191-203

OpCodeBERT: A Method for Python Code Representation Learning by BERT With Opcode

Authors: Canyu Qiu Jianxun Liu Xiaocong Xiao et al.

Source: IEEE Transactions on Software Engineering. 51:3103-3116

Naïve Chunking Strategies for Scalable SAS-Python Code Translation in the U.S. Census Bureau

Authors: Milne, Cameron Mamantov, Ellie Lynagh, John et al.

Contributors: Milne, Cameron Mamantov, Ellie Lynagh, John et al.

Subject Terms: Code Translation, SAS, Large Language Models (LLMs), Python

A Study of Large Language Models in Detecting Python Code Violations

Authors: Hekar A. Mohammed Salih Qusay I. Sarhan

Source: ARO-THE SCIENTIFIC JOURNAL OF KOYA UNIVERSITY. 13:215-225

Refactoring Python Code with LLM-Based Multi-Agent Systems: An Empirical Study in ML Software Projects

Authors: Alexander Puma Pucho Alexandre Mello Ferreira Elder José Reioli Cirilo et al.

Source: Anais do XXXIX Simpósio Brasileiro de Engenharia de Software (SBES 2025). :678-684

Measuring and Improving the Efficiency of Python Code Generated by LLMs Using CoT Prompting and Fine-Tuning

Authors: Ramya Jonnala Jeong Yang Young Lee 0002 et al.

Source: IEEE Access, Vol 13, Pp 119657-119681 (2025)

Subject Terms: LLMs, code generation, Electrical engineering. Electronics. Nuclear engineering, CoT, fine-tuning, vertex AI, Python, TK1-9971

Access URL: https://doaj.org/article/f8d90c3451a24f0dbb548f6c7b4fa3b2

An Empirical Study on the Performance and Energy Usage of Compiled Python Code

Authors: Vincenzo Stoico Andrei Calin Dragomir Patricia Lago

Source: Proceedings of the 29th International Conference on Evaluation and Assessment in Software Engineering. :46-56

Subject Terms: Performance (cs.PF), Software Engineering (cs.SE), FOS: Computer and information sciences, Computer Science - Software Engineering, Computer Science - Programming Languages, Computer Science - Performance, Programming Languages (cs.PL)

Access URL: http://arxiv.org/abs/2505.02346
https://hdl.handle.net/1871.1/cb0986f5-a392-43ce-a1c0-a5382c882219
https://research.vu.nl/en/publications/cb0986f5-a392-43ce-a1c0-a5382c882219
https://doi.org/10.1145/3756681.3756972

SemetonBug: A Machine Learning Model for Automatic Bug Detection in Python Code Based on Syntactic Analysis

Authors: Bahtiar Imran Selamet Riadi Emi Suryadi et al.

Source: Jurnal Informatika. 12:75-80

Visualizing Materials Science Phase Transformations : 3D Transformations from Atoms to Microstructures: "With Interactive Python Simulations and 3D Visualizations" "A Computational Approach to Understanding Microstructural Evolution" "Bridging Theory and Visualization Through Python Programming" "From Thermodynamic Principles to Microstructural Realities" "Interactive Learning Through Code, Diagrams, and Simulations"

Authors: geruganti, sudhakar

Prompt Engineering for Python Code Debugging with Large Language Models: A Comparative Analysis of Zero-Shot, Few-Shot, and Chain-of-Thought Approaches

Authors: Raihan Putra Darmawan Suryo Adhi Wibowo

Source: 2025 IEEE International Symposium on Future Telecommunication Technologies (SOFTT). :391-395

Automated Function Level Python Code Summarization Using a Transformer Based Model

Authors: Yaswanth Kharidu Yaswanth Kharidu Kharidu

Source: INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT. :1-9

Enhancing Python Code Smell Detection with Heterogeneous Ensembles

Authors: Rana Sandouka Hamoud Aljamaan

Source: International Journal of Software Engineering and Knowledge Engineering. 35:963-986

Model-Agnostic Empirical Evaluation of Test-Driven Prompt Engineering on Improving Accuracy and Efficiency in Large Language Models Python Code Generation

Authors: Muhammad Rizqullah Emad Albassam

Source: IEEE Access, Vol 14, Pp 22801-22821 (2026)

Subject Terms: Artificial intelligence, code generation, empirical software engineering, explainable artificial intelligence, large language models, prompt engineering, Electrical engineering. Electronics. Nuclear engineering, TK1-9971

File Description: electronic resource

Relation: https://ieeexplore.ieee.org/document/11386872/; https://doaj.org/toc/2169-3536

Access URL: https://doaj.org/article/b18147f03fb24845bc31551fa163326f

Automated Refactoring of Non-Idiomatic Python Code: A Differentiated Replication with LLMS

Authors: Alessandro Midolo Massimiliano Di Penta

Source: 2025 IEEE/ACM 33rd International Conference on Program Comprehension (ICPC). :01-11

Subject Terms: Software Engineering (cs.SE), FOS: Computer and information sciences, Computer Science - Software Engineering

Access URL: http://arxiv.org/abs/2501.17024