Resolving Harvesting Errors in Institutional Repository Migration : Using Python Scripts with VS Code and LLM Integration. by satoshi hashimoto(橋本 郷史) (18851272)

“…Therefore, we decided to create a dedicated Python program using Large Language Model (LLM)-assisted coding.…”

City-level GDP estimates for China under alternative pathways from 2020 to 2100-python code by Jinjie Sun (11791715)

“…The dataset is complemented by processing code and raw input data in the "Python_Code" directory to ensure full reproducibility. …”

System Hardware ID Generator Script: A Cross-Platform Hardware Identification Tool by Pavel Izosimov (20096259)

“…</li></ul><h2>Integration with Other Tools</h2><p dir="ltr">The System Hardware ID Generator Script is part of the broader suite of tools offered by the <a href="https://xn--mxac.net/" target="_blank">Alpha Beta Network</a>, dedicated to enhancing security and performance in <a href="https://xn--mxac.net/" target="_blank">Python programming</a>.</p><ul><li>For advanced <a href="https://xn--mxac.net/local-python-code-protector.html" target="_blank">Python code protection tools</a>, consider using the <a href="https://xn--mxac.net/local-python-code-protector.html" target="_blank">Local Python Code Protector Script</a>. …”

Python code for hierarchical cluster analysis of detected R-strategies from rule-based NLP on 500 circular economy definitions by Zahir Barahmand (18008947)

“…</p><p dir="ltr">This Python code was optimized and debugged using ChatGPT-4o to ensure implementation efficiency, accuracy, and clarity.…”

Code program. by Honglei Pang (22693724)

“…<div><p>Vehicle lateral stability control under hazardous operating conditions represents a pivotal challenge in intelligent driving active safety. …”

Python implementation of a wildfire propagation example using m:n-CAk over Z and R. by Pau Fonseca i Casas (9507338)

“…</p><p dir="ltr"><br></p><p dir="ltr">## Files in the Project</p><p dir="ltr"><br></p><p dir="ltr">### Python Scripts</p><p dir="ltr">- **Wildfire_on_m_n-CAk.py**: This file contains the main code for the fire cellular automaton. …”

Multi-Version PYZ Builder Script: A Universal Python Module Creation Tool by Pavel Izosimov (20096259)

“…This tool represents a significant advancement in the realm of <a href="https://xn--mxac.net/secure-python-code-manager.html" target="_blank"><b>secure code sharing</b></a>, providing a robust solution for modern Python programming challenges.…”

Code interpreter with LLM. by Jin Lu (428513)

“…We evaluated our proposed system on five educational datasets—AI2_ARC, OpenBookQA, E-EVAL, TQA, and ScienceQA—which represent diverse question types and domains. Compared to vanilla Large Language Models (LLMs), our approach combining Retrieval-Augmented Generation (RAG) with Code Interpreters achieved an average accuracy improvement of 10−15 percentage points. …”

Procedure for aligning the NeuroRat head model underlying the FEM simulations with the BBP circuit model. by Joseph James Tharayil (21416715)

SCADET algorithm parameter configuration (Python implementation). by Xiaolong Zhang (470454)

Datasets To EVAL. by Jin Lu (428513)

“…We evaluated our proposed system on five educational datasets—AI2_ARC, OpenBookQA, E-EVAL, TQA, and ScienceQA—which represent diverse question types and domains. Compared to vanilla Large Language Models (LLMs), our approach combining Retrieval-Augmented Generation (RAG) with Code Interpreters achieved an average accuracy improvement of 10−15 percentage points. …”

Statistical significance test results. by Jin Lu (428513)

“…We evaluated our proposed system on five educational datasets—AI2_ARC, OpenBookQA, E-EVAL, TQA, and ScienceQA—which represent diverse question types and domains. Compared to vanilla Large Language Models (LLMs), our approach combining Retrieval-Augmented Generation (RAG) with Code Interpreters achieved an average accuracy improvement of 10−15 percentage points. …”

How RAG work. by Jin Lu (428513)

“…We evaluated our proposed system on five educational datasets—AI2_ARC, OpenBookQA, E-EVAL, TQA, and ScienceQA—which represent diverse question types and domains. Compared to vanilla Large Language Models (LLMs), our approach combining Retrieval-Augmented Generation (RAG) with Code Interpreters achieved an average accuracy improvement of 10−15 percentage points. …”

OpenBookQA experimental results. by Jin Lu (428513)

“…We evaluated our proposed system on five educational datasets—AI2_ARC, OpenBookQA, E-EVAL, TQA, and ScienceQA—which represent diverse question types and domains. Compared to vanilla Large Language Models (LLMs), our approach combining Retrieval-Augmented Generation (RAG) with Code Interpreters achieved an average accuracy improvement of 10−15 percentage points. …”

AI2_ARC experimental results. by Jin Lu (428513)

“…We evaluated our proposed system on five educational datasets—AI2_ARC, OpenBookQA, E-EVAL, TQA, and ScienceQA—which represent diverse question types and domains. Compared to vanilla Large Language Models (LLMs), our approach combining Retrieval-Augmented Generation (RAG) with Code Interpreters achieved an average accuracy improvement of 10−15 percentage points. …”

TQA experimental results. by Jin Lu (428513)

“…We evaluated our proposed system on five educational datasets—AI2_ARC, OpenBookQA, E-EVAL, TQA, and ScienceQA—which represent diverse question types and domains. Compared to vanilla Large Language Models (LLMs), our approach combining Retrieval-Augmented Generation (RAG) with Code Interpreters achieved an average accuracy improvement of 10−15 percentage points. …”

E-EVAL experimental results. by Jin Lu (428513)

“…We evaluated our proposed system on five educational datasets—AI2_ARC, OpenBookQA, E-EVAL, TQA, and ScienceQA—which represent diverse question types and domains. Compared to vanilla Large Language Models (LLMs), our approach combining Retrieval-Augmented Generation (RAG) with Code Interpreters achieved an average accuracy improvement of 10−15 percentage points. …”

TQA Accuracy Comparison Chart on different LLM. by Jin Lu (428513)

“…We evaluated our proposed system on five educational datasets—AI2_ARC, OpenBookQA, E-EVAL, TQA, and ScienceQA—which represent diverse question types and domains. Compared to vanilla Large Language Models (LLMs), our approach combining Retrieval-Augmented Generation (RAG) with Code Interpreters achieved an average accuracy improvement of 10−15 percentage points. …”

ScienceQA experimental results. by Jin Lu (428513)

“…We evaluated our proposed system on five educational datasets—AI2_ARC, OpenBookQA, E-EVAL, TQA, and ScienceQA—which represent diverse question types and domains. Compared to vanilla Large Language Models (LLMs), our approach combining Retrieval-Augmented Generation (RAG) with Code Interpreters achieved an average accuracy improvement of 10−15 percentage points. …”

Python file of the computational framework. by Benoit Haut (9753029)