arXiv Machine Learning
Aug 5
Evaluation Blindness: How Silent Measurement Failures Corrupt AI Systems from Training to Deployment
arXiv:2608. 02786v1 Announce Type: new Abstract: AI systems can fail silently.
Detecting Explanatory Insufficiency in Learned Representations: A Framework for Representational Vigilance
arXiv:2606. 13172v2 Announce Type: replace Abstract: Learned representations are central to modern machine learning and are commonly evaluated through predictive performance, robustness, uncertainty estimation, and generalization.
Related stories
arXiv Machine Learning
Aug 24
Structure is information: structural identifiability mappings for machine learning with partially observed dynamical systems
arXiv:2502.04131v2 Announce Type: replace Abstract: The successful application of modern machine learning for time series classification is often hampered by limitations in quality and quantity of av...
arXiv AI
Jul 2
From Silos to Systems: Process-Oriented Hazard Analysis for AI Systems
arXiv:2410. 22526v2 Announce Type: replace Abstract: To effectively address potential harms from Artificial Intelligence (AI) systems, it is essential to identify and mitigate system-level hazards.
arXiv Machine Learning
Jul 23
Building Fast, Evaluating Slow: Pipeline Choices Dominate Autointerpretability Score Variance
arXiv:2607. 19386v1 Announce Type: new Abstract: Cross-paper comparison of sparse autoencoder (SAE) interpretability often relies on autointerpretability scores.
arXiv AI
Jul 28
Physically Verifiable Evidence and LLM-Based Reporting for Bearing Fault Diagnosis
arXiv:2607. 22797v1 Announce Type: cross Abstract: Trustworthy deployment of AI-based diagnosis in safety-critical mechanical systems hinges on validation: whether a prediction can be checked against physical reality before it is acted upon.
arXiv Machine Learning
Sep 15
Machine Learning under Imperfect Data: Challenges and Methods
arXiv:2609.13914v1 Announce Type: new Abstract: Machine-learning models are commonly developed under an assumption that training and test data are sufficiently complete, balanced, labelled, and drawn...
Hugging Face Trending Papers
Sep 16
Reliable Virtual Sensing: A Multi-Domain Benchmark for Robustness Under Sensor Failures
Virtual sensing, the estimation of hard-to-measure quantities from available sensor measurements, is a critical enabler for control and monitoring in cyber-physical systems. However, when sensors fail...
arXiv AI
Jun 11
Models That Know How Evaluations Are Designed Score Safer
arXiv:2605. 28591v2 Announce Type: replace-cross Abstract: The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings.
arXiv AI
Oct 1
Interpretable but Fragile? Robustness of Concept Bottlenecks under Geometric-Semantic Perturbations
arXiv:2609.38625v1 Announce Type: cross Abstract: Concept Bottleneck Models (CBMs) are designed to provide interpretable intermediate representations, yet how such bottlenecks affect robustness remai...
arXiv AI
Aug 28
The Latent Diagnostic Taxonomy: A Framework for Constructing Classifiers and Diagnosing Their Decisions, Applied to Prompt Injection Detection
The paper introduces the Latent Diagnostic Taxonomy, a framework that builds a dimensionality‑optimized classifier and a diagnostic tool to assess the trustworthiness of its confident predictions. It identifies a small set of influential prompts (latent support vectors) that reveal tokens which can change the classifier’s output, and uses these tokens to create a taxonomy that classifies prompts into safe, heuristic bias, heuristic override, or insufficient context categories. Applied to a prompt‑injection detection model, the framework shows that about 77% of confident decisions are fragile to a single token, distinguishing between calibration failures and exploitable shortcuts, and offers remediation strategies for each taxonomy zone.
arXiv AI
Sep 17
Reliable Virtual Sensing: A Multi-Domain Benchmark for Robustness Under Sensor Failures
The paper introduces MuViS-C, a multi‑domain benchmark that evaluates the robustness of learning‑based virtual sensing models against ten common sensor failure modes, ranging from subtle drifts to catastrophic dropouts. It assesses models using average error, relative degradation, and worst‑case fragility across nine datasets from six domains, comparing six architectures (gradient‑boosted trees, convolution, recurrence, attention, and MLP‑mixing). The study finds that all models degrade under corruption, gradient‑boosted trees are most robust, and targeted robustification can improve attention models at the cost of nominal performance.
arXiv AI
Jun 8
Beyond the Black Box: Interpretability of Agentic AI Tool Use
arXiv:2605. 06890v3 Announce Type: replace Abstract: AI agents are promising for high-stakes enterprise workflows, but dependable deployment remains limited because tool-use failures are difficult to diagnose and control.