Cover Image

Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demands

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Seth, Pratinav, Sankarapu, Vinay Kumar
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Bridging the Gap in XAI-Why Reliable Metrics Matter for Explainability and Compliance
by: Seth, Pratinav, et al.
Published: (2025)

Interpretability as Alignment: Making Internal Understanding a Design Principle
by: Sengupta, Aadit, et al.
Published: (2025)

Orion-Bix: Bi-Axial Attention for Tabular In-Context Learning
by: Bouadi, Mohamed, et al.
Published: (2025)

Orion-MSP: Multi-Scale Sparse Attention for Tabular In-Context Learning
by: Bouadi, Mohamed, et al.
Published: (2025)

Distilling Tabular Foundation Models for Structured Health Data
by: Tanna, Aditya, et al.
Published: (2026)

TabTune: A Unified Library for Inference and Fine-Tuning Tabular Foundation Models
by: Tanna, Aditya, et al.
Published: (2025)

Pocket Foundation Models: Distilling TFMs into CPU-Ready Gradient-Boosted Trees
by: Tanna, Aditya, et al.
Published: (2026)

DLBacktrace: A Model Agnostic Explainability for any Deep Learning Models
by: Sankarapu, Vinay Kumar, et al.
Published: (2024)

xai_evals : A Framework for Evaluating Post-Hoc Local Explanation Methods
by: Seth, Pratinav, et al.
Published: (2025)

Ensembling Tabular Foundation Models - A Diversity Ceiling And A Calibration Trap
by: Tanna, Aditya, et al.
Published: (2026)

Data Presentation Over Architecture: Resampling Strategies for Credit Risk Prediction with Tabular Foundation Models
by: Tanna, Aditya, et al.
Published: (2026)

Interpretability-Aware Pruning for Efficient Medical Image Analysis
by: Malik, Nikita, et al.
Published: (2025)

Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution
by: Sadhu, Saisab, et al.
Published: (2026)

Exploring Fine-Tuning for Tabular Foundation Models
by: Tanna, Aditya, et al.
Published: (2026)

Beyond KL Divergence: Policy Optimization with Flexible Bregman Divergences for LLM Reasoning
by: Yuan, Rui, et al.
Published: (2026)

Beyond Uniform Credit: Causal Credit Assignment for Policy Optimization
by: Khandoga, Mykola, et al.
Published: (2026)

Shaping the Prior: How Synthetic Task Distributions Determine Tabular Foundation Model Quality
by: Bouadi, Mohamed, et al.
Published: (2026)

$C$-$ΔΘ$: Circuit-Restricted Weight Arithmetic for Selective Refusal
by: Kasliwal, Aditya, et al.
Published: (2026)

Position: State-of-the-Art Claims Require State-of-the-Art Evidence
by: Oh, YongKyung
Published: (2026)

Breaking the Safety-Capability Tradeoff: Reinforcement Learning with Verifiable Rewards Maintains Safety Guardrails in LLMs
by: Cho, Dongkyu Derek, et al.
Published: (2025)

Semantic Anchors in In-Context Learning: Why Small LLMs Cannot Flip Their Labels
by: Kumar, Anantha Padmanaban Krishna
Published: (2025)

Towards Developing Safety Assurance Cases for Learning-Enabled Medical Cyber-Physical Systems
by: Bagheri, Maryam, et al.
Published: (2022)

Relational GNNs Cannot Learn $C_2$ Features for Planning
by: Chen, Dillon Z.
Published: (2025)

ART: Adaptive Reasoning Trees for Explainable Claim Verification
by: Wadhwa, Sahil, et al.
Published: (2026)

Verified Neural Compressed Sensing
by: Bunel, Rudy, et al.
Published: (2024)

Co-Activation Graph Analysis of Safety-Verified and Explainable Deep Reinforcement Learning Policies
by: Gross, Dennis, et al.
Published: (2025)

xAI-Drop: Don't Use What You Cannot Explain
by: De Luca, Vincenzo Marco, et al.
Published: (2024)

From High-Dimensional Spaces to Verifiable ODD Coverage for Safety-Critical AI-based Systems
by: Stefani, Thomas, et al.
Published: (2026)

AlignTune: Modular Toolkit for Post-Training Alignment of Large Language Models
by: Lyngkhoi, R E Zera Marveen, et al.
Published: (2026)

Text-to-Image Diffusion Models Cannot Count, and Prompt Refinement Cannot Help
by: Guo, Xuyang, et al.
Published: (2025)

vAttention: Verified Sparse Attention
by: Desai, Aditya, et al.
Published: (2025)

Operationalising Artificial Intelligence Bills of Materials (AIBOMs) for Verifiable AI Provenance and Lifecycle Assurance
by: Radanliev, Petar, et al.
Published: (2026)

OpenKedge: Governing Agentic Mutation with Execution-Bound Safety and Evidence Chains
by: He, Jun, et al.
Published: (2026)

Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes
by: Qiao, Dan, et al.
Published: (2024)

Perplexity Cannot Always Tell Right from Wrong
by: Veličković, Petar, et al.
Published: (2026)

Edge-FIT: Federated Instruction Tuning of Quantized LLMs for Privacy-Preserving Smart Home Environments
by: Venkatesh, Vinay, et al.
Published: (2025)

Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers
by: Cai, Xin-Qiang, et al.
Published: (2025)

Behaviour Distillation
by: Lupu, Andrei, et al.
Published: (2024)

Curriculum Learning for Safety Alignment
by: Kumar, Sandeep, et al.
Published: (2026)

NeurIPS Should Require Reproducibility Standards for Frontier AI Safety Claims
by: Vishwarupe, Varad, et al.
Published: (2026)