Auditing and generating synthetic data with controllable trust trade-offs

B Belgodere, P Dognin, A Ivankay… - IEEE Journal on …, 2024 - ieeexplore.ieee.org
Real-world data often exhibits bias, imbalance, and privacy risks. Synthetic datasets have
emerged to address these issues by enabling a paradigm that relies on generative AI …

Optimized ensemble machine learning model for software bugs prediction

F Johnson, O Oluwatobi, O Folorunso… - Innovations in Systems …, 2023 - Springer
Software accuracy and efficiency checks are becoming of paramount interest to system
users before utilization. As a result, twenty-first-century programmers are consciously …

New graphical software tool for creating cause-effect graph specifications

E Krupalija, Š Bećirović, I Prazina, E Cogo… - … Software and Systems, 2022 - hrcak.srce.hr
Sažetak Cause-effect graphing is a commonly used black-box technique with many
applications in practice. It is important to be able to create accurate cause-effect graph …

[PDF][PDF] Metrics As Scores: A Tool-and Analysis Suite and Interactive Application for Exploring Context-Dependent Distributions

S Hönel, M Ericsson, W Löwe… - Journal of Open Source …, 2023 - joss.theoj.org
Summary Metrics As Scores can be thought of as an interactive, multiple analysis of
variance (abbr.“ANOVA,” Chambers et al., 2017). An ANOVA might be used to estimate the …

Risk assessment and statistical significance in the age of foundation models

A Nitsure, Y Mroueh, M Rigotti, K Greenewald… - arXiv preprint arXiv …, 2023 - arxiv.org
We propose a distributional framework for assessing socio-technical risks of foundation
models with quantified statistical significance. Our approach hinges on a new statistical …

Contextual Operationalization of Metrics as Scores: Is My Metric Value Good?

S Hönel, M Ericsson, W Löwe… - 2022 IEEE 22nd …, 2022 - ieeexplore.ieee.org
Software quality models aggregate metrics to indicate quality. Most metrics reflect counts
derived from events or attributes that cannot directly be associated with quality. Worse, what …

An Introduction to the Evaluation of Perception Algorithms and LiDAR Point Clouds Using a Copula-Based Outlier Detector

N Reis, J Machado da Silva, MV Correia - Remote Sensing, 2023 - mdpi.com
The increased demand for and use of autonomous driving and advanced driver assistance
systems has highlighted the issue of abnormalities occurring within the perception layers …

Multivariate Stochastic Dominance via Optimal Transport and Applications to Models Benchmarking

G Rioux, A Nitsure, M Rigotti, K Greenewald… - arXiv preprint arXiv …, 2024 - arxiv.org
Stochastic dominance is an important concept in probability theory, econometrics and social
choice theory for robustly modeling agents' preferences between random outcomes. While …

Aggregation as Unsupervised Learning in Software Engineering and Beyond

M Ulan - 2021 - diva-portal.org
Engineering and Beyond, Linnaeus University Dissertations No 430/2021, ISBN: 978-91-
89460-40-9 (print), 978-91-89460-41-6 (pdf). Ranking alternatives is fundamental to …

Ensemble-based software fault prediction with two staged data pre-processing

SP Kulkarni, S Patel - International Journal of Computer …, 2023 - inderscienceonline.com
Software fault prediction is the process of identifying the software modules which are more
likely to be defective or faulty before the testing phase of software development life-cycle …