Explicit provenance across the full agentic AI lifecycle is the necessary condition for making responsibility computable and actionable.
arXiv preprint arXiv:1711.01134, 2017
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
A method is presented for calculating a transparency metric for ML model pipelines by analyzing the visibility of contributions from data sources and human developers.
Advanced AI systems are unexplainable in full and produce explanations that humans cannot comprehend.
citing papers explorer
-
Quantifying Transparency of Machine Learning Systems through Analysis of Contributions
A method is presented for calculating a transparency metric for ML model pipelines by analyzing the visibility of contributions from data sources and human developers.
-
Unexplainability and Incomprehensibility of Artificial Intelligence
Advanced AI systems are unexplainable in full and produce explanations that humans cannot comprehend.