analiza aiqbench
This article focuses on Why3-py, a tool designed to formally verify statistical Python code used in hypothesis testing and meta-analysis, directly addressing the reproducibility crisis through rigorous mathematical validation of AI-relevant algorithms. By transforming dynamic Python programs into verification-oriented representations, the research ensures that underlying assumptions in data science workflows are explicit and provably correct rather than implicit or erroneous. This work represents a significant advancement in Machine Learning safety and reliability by applying formal methods to the statistical foundations often used in training and evaluating models.
Why3-py: A Tool for Formal Verification of Hypothesis Testing and Meta-Analysis in Python
arXiv:2607.03951v2 Announce Type: replace-cross Abstract: The reproducibility crisis in scientific research has received widespread recognition, thereby increasing the importance of meta-analyses that integrate statistical analyses from multiple studies. However, statistical methods often have ambiguous and implicit underlying assumptions, which can lead to their erroneous applications and interpretations. To address this issue, we propose a formal verification framework for statistical Python programs. Specifically, we present Why3-py, a Python front-end for the Why3 verification platform that transforms Python code into verification-oriented WhyML representations, addressing the challenges arising from Python's dynamic typing and runtime polymorphism. Furthermore, we extend the StatWhy tool to support the verification of meta-analysis methods. These tools enable meta-analysts to identify overlooked assumptions and misuse of analyses, and to verify the correct use of hypothesis testing and meta-analysis methods in Python code.
Abstract:The reproducibility crisis in scientific research has received widespread recognition, thereby increasing the importance of meta-analyses that integrate statistical analyses from multiple studies. However, statistical methods often have ambiguous and implicit underlying assumptions, which can lead to their erroneous applications and interpretations. To address this issue, we propose a formal verification framework for statistical Python programs. Specifically, we present Why3-py, a Python front-end for the Why3 verification platform that transforms Python code into verification-oriented WhyML representations, addressing the challenges arising from Python's dynamic typing and runtime polymorphism. Furthermore, we extend the StatWhy tool to support the verification of meta-analysis methods. These tools enable meta-analysts to identify overlooked assumptions and misuse of analyses, and to verify the correct use of hypothesis testing and meta-analysis methods in Python code.
Software Engineering (cs.SE); Artificial Intelligence (cs.AI); Logic in Computer Science (cs.LO); Programming Languages (cs.PL)
arXiv:2607.03951 [cs.SE]
(or arXiv:2607.03951v2 [cs.SE] for this version)
https://doi.org/10.48550/arXiv.2607.03951 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 230 cuvinte
