Gap Taxonomy
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
What Molecular Structure Cannot Tell Us: A Taxonomy of Explainability Gaps in GNN-Based Drug Toxicity Prediction
arXiv:2605.26183v2 Announce Type: replace-cross Abstract: Not all clinically relevant adverse effects are structurally inferable from molecular graphs - regardless of model quality or architectural complexity. This study introduces an operational taxonomy of the structural information limits that prevent structure-based toxicity prediction, independent of the learning algorithm employed. Graph Neural Networks (GNNs) have emerged as a natural approach for molecular toxicity prediction,...
AI Loss of Control Incident Management: Response & Resilience
Announce Type: new Abstract: Recent research demonstrating AI systems exhibiting deception and shutdown resistance suggests that AI loss of control (LOC) is an urgent policy concern , yet current literature focuses almost exclusively on alignment and prevention. To address this gap, this paper introduces a foundational framework and taxonomy for managing catastrophic AI LOC incidents.
What Benchmarks Don't Measure: The Case for Evaluating Abstention Competence in Autonomous Agents
arXiv:2606.02965v1 Announce Type: new Abstract: Benchmarks for autonomous agents measure whether agents complete tasks, yet this framing is systematically blind to whether an agent should have proceeded at all. Agents trained under human-feedback objectives develop a structural tendency to proceed even when they lack the inputs, evidence, or authorization to act safely, a disposition we term compliance bias, because both the reward signal and the benchmark scoring regime treat proceeding as...
SoK: Reconstruction Attacks on Synthetic Tabular Data (Insights from Winning the NIST CRC)
Announce Type: new Abstract: Synthetic data is increasingly promoted as a privacy-preserving substitute for releasing sensitive tabular records, yet its central adversarial threat ("reconstruction", the recovery of an individual's hidden attribute values from a synthetic release and a handful of known quasi-identifiers) has been studied only in scattered, hard-to-compare settings. We present the first systematization of reconstruction (equivalently, attribute inference) attacks on...
When LLM Reward Design Fails: Diagnostic-Driven Refinement for Sparse Structured RL
arXiv:2605.28918v1 Announce Type: cross Abstract: For sparse, structured reinforcement-learning tasks with semantic reward-function interfaces, LLM-generated reward shaping is better framed as debugging than one-shot generation. We study PPO-trained agents using MiniGrid as core evaluation and MuJoCo as boundary stress test. Our audit finds two dominant one-shot failure modes -- reward flooding and semantic/API misunderstanding -- plus a rarer weak-shaping case.
When Chatbots Accommodate: What AI Companions Optimize for in Vulnerable Conversations
arXiv:2606.04431v1 Announce Type: new Abstract: Millions turn to AI companion chatbots during loneliness, grief, and personal crises. How these companion platforms respond in such moments can shape the trajectory of a user's vulnerable state. Yet we lack tools to characterize what each platform actually does when users open up.
A Taxonomy of Real-World Asset Tokenization for Blockchain-Based Financial Infrastructure
Announce Type: cross Abstract: Real-world asset (RWA) tokenization has emerged as a prominent application of blockchain technology, enabling off-chain financial and non-financial assets to be represented through blockchain-based instruments. However, deployed RWA systems remain difficult to compare because legal claims, custody arrangements, token mechanics, verification processes, and on-chain integrations are often described separately. This paper develops a systems-level taxonomy of RWA...
Are Large Language Models Suitable for Graph Computation? Progress and Prospects
Announce Type: new Abstract: Large language models (LLMs) have been increasingly explored for graph computation, where tasks require reasoning over structured relationships and algorithmic operations. Yet, it remains unclear when LLMs can reliably support such computation and how they should be incorporated into graph-solving pipelines. Existing surveys at the intersection of LLMs and graphs primarily focus on graph learning, text-attributed graphs, or graph-language modeling.
QBugLM: An Agentic Benchmarking Framework for LLM-based Quantum Software Debugging
Announce Type: new Abstract: Quantum software bugs often yield silent, incorrect outputs rather than explicit errors, making them particularly difficult to detect and repair with conventional techniques. Although large language models (LLMs) have shown strong performance on classical software engineering tasks, their ability to debug quantum code remains largely unexplored. To bridge this gap, we propose QBugLM, a multi-agent framework that automates the quantum software debugging pipeline,...
A Survey of Heterogeneous Graph Neural Networks for Cybersecurity Anomaly Detection
arXiv:2510.26307v3 Announce Type: replace Abstract: Anomaly detection is a critical task in cybersecurity, where identifying insider threats, access violations, and coordinated attacks is essential for ensuring system resilience. Graph-based approaches have become increasingly important for modeling entity interactions, yet most rely on homogeneous and static structures, which limits their ability to capture the heterogeneity and temporal evolution of real-world environments. Heterogeneous...