Browse research papers in Software - Computer Science Discover 4 academic papers with AI-powered analysis

← Back

/

Software

The engineering of software systems, including programming languages, software architecture, testing, verification, agile methods, DevOps, and the management of large-scale software projects

4 papers in this specialization

Papers

Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity

This study found that, contrary to expectations, access to AI tools (specifically, early-2025 state-of-the-art tools like Cursor Pro and Claude 3.5/3.7 Sonnet) actually *slowed down* experienced open-source developers by 19% on average when completing real-world tasks. Both developers and experts substantially overestimated the positive impact of AI, forecasting significant speedup before and after the study despite observed slowdown.

★

☆

Early_2025_AI_Experienced_OS_Devs_Study.pdf

Jul 14, 08:02 PM

Use Chat GPT to Solve Programming Bugs

This paper explores the potential of using ChatGPT for debugging assistance, bug prediction, and bug explanation. It suggests that ChatGPT's natural language processing and knowledge representation capabilities may be useful for identifying and fixing bugs, but acknowledges the need for further research and validation.

Investigating computational geometry for failure prognostics

This paper introduces RULCLIPPER, a novel prognostics algorithm using computational geometry and CBR to estimate remaining useful life (RUL) from imprecise health indicators (IHIs) represented as polygons. RULCLIPPER was evaluated on the NASA C-MAPSS turbofan engine simulator datasets, showing promising results in predicting RUL despite noisy data and varying operating conditions, with some limitations on data specific rules and IHI representation.

Gene name errors: Lessons not learned

This study found that gene name errors in supplementary Excel files continue to be a problem in genomics research, with a higher prevalence (30.9%) than previously reported. The errors are often due to automatic conversion of gene names into dates or other data formats, which is particularly prevalent in Microsoft Excel and Google Sheets. Five-digit numbers (internal date format) represent a new major source of errors, contributing to the discrepancy from past reports.