Brief

Researchers have introduced BOHM, a novel method for attributing contributions within compound AI systems that utilize hierarchical routing. Unlike traditional Shapley-based methods, BOHM leverages existing routing weights, offering a zero-cost attribution solution that is particularly effective for systems with opaque components or agentic orchestrators. The method provides multi-resolution attribution across all levels of the hierarchy simultaneously, demonstrating strong correlation with Shapley values on various benchmarks while requiring significantly fewer evaluations. AI

A new research paper published on arXiv demonstrates that no feature ranking method can be simultaneously faithful, stable, and complete when features are collinear. The study proves this impossibility and quantifies it across various model classes, suggesting that ensemble averaging methods like DASH can resolve this issue. The findings have direct implications for fairness auditing, indicating that SHAP-based proxy discrimination audits are unreliable under collinearity. AI

Researchers have developed a machine learning framework for predicting atmospheric visibility in six South Korean cities, addressing challenges like imbalanced data and distribution shifts. The study employed techniques such as SMOTENC and CTGAN to handle data imbalance and an ensemble of machine and deep learning models for prediction. A significant drop in performance on the test set compared to cross-validation highlighted the impact of temporal distribution shifts, quantified using Wasserstein distance. AI