Tootfinder

Revolutionizing Validation and Verification: Explainable Testing Methodologies for Intelligent Automotive Decision-Making Systems
Halit Eris, Stefan Wagner
https://arxiv.org/abs/2506.16876

Revolutionizing Validation and Verification: Explainable Testing Methodologies for Intelligent Automotive Decision-Making Systems
Autonomous Driving Systems (ADS) use complex decision-making (DM) models with multimodal sensory inputs, making rigorous validation and verification (V&V) essential for safety and reliability. These models pose challenges in diagnosing failures, tracing anomalies, and maintaining transparency, with current manual testing methods being inefficient and labor-intensive. This vision paper presents a methodology that integrates explainability, transparency, and interpretability into V&V processes. W…

Distribution Testing in the Presence of Arbitrarily Dominant Noise with Verification Queries
Hadley Black, Christopher Ye
https://arxiv.org/abs/2509.17269 https://

Distribution Testing in the Presence of Arbitrarily Dominant Noise with Verification Queries
We study distribution testing without direct access to a source of relevant data, but rather to one where only a tiny fraction is relevant. To enable this, we introduce the following verification query model. The goal is to perform a statistical task on distribution $\boldsymbol{p}$ given sample access to a mixture $\boldsymbol{r} = λ\boldsymbol{p} + (1-λ)\boldsymbol{q}$ and the ability to query whether a sample was generated by $\boldsymbol{p}$ or by $\boldsymbol{q}$. In general, if $m_0$ sa…

DiCriTest: Testing Scenario Generation for Decision-Making Agents Considering Diversity and Criticality
Qitong Chu, Yufeng Yue, Danya Yao, Huaxin Pei
https://arxiv.org/abs/2508.11514

DiCriTest: Testing Scenario Generation for Decision-Making Agents Considering Diversity and Criticality
The growing deployment of decision-making agents in dynamic environments increases the demand for safety verification. While critical testing scenario generation has emerged as an appealing verification methodology, effectively balancing diversity and criticality remains a key challenge for existing methods, particularly due to local optima entrapment in high-dimensional scenario spaces. To address this limitation, we propose a dual-space guided testing framework that coordinates scenario param…

Behavior Driven Development for 3D Games
Fernando Pastor Ric\'os, Beatriz Mar\'in, I. S. W. B. Prasetya, Tanja E. J. Vos, Joseph Davidson, Karel Hovorka
https://arxiv.org/abs/2506.17057

Behavior Driven Development for 3D Games
Computer 3D games are complex software environments that require novel testing processes to ensure high-quality standards. The Intelligent Verification/Validation for Extended Reality Based Systems (iv4XR) framework addresses this need by enabling the implementation of autonomous agents to automate game testing scenarios. This framework facilitates the automation of regression test cases for complex 3D games like Space Engineers. Nevertheless, the technical expertise required to define test scr…

YouTube plans to start testing an age verification system in the US that uses AI to differentiate between adults and minors, first with a small number of users (Michael Liedtke/Associated Press)
https://apnews.com/article/youtube-video-age-ve…

YouTube testing a new age verification system in the U.S.
YouTube is ready to start testing a new age-verification system in the U.S. using artificial intelligence to distinguish between adults and minors based on their viewing habits. The tests, scheduled to being Wednesday, initially affect a small portion of YouTube's U.S. audience. If successful, the system could become more widespread. It works when viewers are logged into their accounts, regardless of the birth date entered. If flagged as under 18, users face restrictions like privacy warnings a…

🌳in eigener Sache 🌲
Meine Website wird anscheinend mit steigender Tendenz von texthungrigen #KIBots heimgesucht.
Sie haben aber keine Lizenz erworben. 🤪
Da ich abgesehen von den KI-Bildern (Absicht) und KI-Dialogen (Untersuchungen oder Anleitungen) Texte noch selbst verfasse, finden die Konzerne bei mir Futter.
Deshalb habe ich fast alle Artikel nur noch für

heise | Pocket verabschiedet sich: Sieben Read-It-Later-Alternativen vorgestellt
Mozilla beendet seinen Read-Later-Dienst Pocket. Wir testen die Alternativen und zeigen, wie Sie Ihre Daten retten und in einen neuen Dienst importieren.

Modulator-free, self-testing quantum random number generator
Ana Bl\'azquez-Co\'ido, Fadri Gr\"unenfelder, Anthony Martin, Raphael Houlmann, Hugo Zbinden, Davide Rusca
https://arxiv.org/abs/2507.12346

Modulator-free, self-testing quantum random number generator
Quantum random number generators (QRNGs) use the inherent unpredictability of quantum mechanics to generate true randomness, as opposed to classical random number generators. However, ensuring the authenticity of this randomness still requires robust verification. Self-testing QRNGs address this need by enabling the validation of the randomness produced based on the observed data from the experiment while requiring few assumptions. In this work, we present a practical, self-testing QRNG designe…

Causal Fuzzing for Verifying Machine Unlearning
Anna Mazhar, Sainyam Galhotra
https://arxiv.org/abs/2509.16525 https://arxiv.org/pdf/2509.16525

Causal Fuzzing for Verifying Machine Unlearning
As machine learning models become increasingly embedded in decision-making systems, the ability to "unlearn" targeted data or features is crucial for enhancing model adaptability, fairness, and privacy in models which involves expensive training. To effectively guide machine unlearning, a thorough testing is essential. Existing methods for verification of machine unlearning provide limited insights, often failing in scenarios where the influence is indirect. In this work, we propose CAFÉ, a ne…

Towards Robust Agentic CUDA Kernel Benchmarking, Verification, and Optimization
Robert Tjarko Lange, Qi Sun, Aaditya Prasad, Maxence Faldor, Yujin Tang, David Ha
https://arxiv.org/abs/2509.14279

Towards Robust Agentic CUDA Kernel Benchmarking, Verification, and Optimization
Recent advances in large language models (LLMs) demonstrate their effectiveness in scaling test-time compute for software engineering tasks. However, these approaches often focus on high-level solutions, with limited attention to optimizing low-level CUDA kernel implementations. Additionally, existing kernel generation benchmarks suffer from exploitable loopholes and insufficient diversity in testing conditions, hindering true generalization assessment. To address these limitations, we introduc…