Transparency in Complex Computational Systems
2020/04/30 by Kathleen A. Creel, Kathleen Creel · 186 citations
Computer Science · Mathematics · Social Sciences · #Code (set theory) #Computability, Logic, AI Algorithms #Computer science #Computer security #Ethics and Social Impacts of AI #Explainable Artificial Intelligence (XAI) #Mathematics #Opacity #Programming language #Realization (probability) #Theoretical computer science #Transparency (behavior)
paper · pdf · doi:10.1086/709729
published in Philosophy of Science 87(4), 568-589 (Cambridge University Press)
openalex publication_date 2020/04/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29
Abstract
Scientists depend on complex computational systems that are often ineliminably opaque, to the detriment of our ability to give scientific explanations and detect artifacts. Some philosophers have suggested treating opaque systems instrumentally, but computer scientists developing strategies for increasing transparency are correct in finding this unsatisfying. Instead, I propose an analysis of transparency as having three forms: transparency of the algorithm, the realization of the algorithm in code, and the way that code is run on particular hardware and data. This targets the transparency most useful for a task, avoiding instrumentalism by providing partial transparency when full transparency is impossible.
Citations
Cited by
- No right to an explanation
- We Have No Satisfactory Social Epistemology of AI-Based Science
- On the Opportunities and Risks of Foundation Models
- DNNs, Dataset Statistics, and Correlation Functions
- The Benchmarking Epistemology: Construct Validity for Evaluating Machine Learning Models
- The linguistic dead zone of value-aligned agency, natural and artificial
- The Immortal Science of ML: Machine Learning and the Theory-Free Ideal
- Desde la caja negra a la comprensión: fortaleciendo el vínculo modelo-fenómeno mediante inteligencia artificial explicable
- ‘Be your own boss’? Normative concerns of algorithmic management in the gig economy: reclaiming agency at work through algorithmic counter-tactics
- How can we trust opaque systems? Criteria for robust explanations in XAI
- The Problem of Atypicality in LLM-Powered Psychiatry
- Mechanistic Interpretability Needs Philosophy
- Philosophers ought to develop, theorize about, and use philosophically relevant AI
- Federated learning, ethics, and the double black box problem in medical AI
- Black Boxes in Black Hole Imaging
- Hallucination, reliability, and the role of generative AI in science
- What is Interpretability? [europepmc]
- Can Robots Do Epidemiology? Machine Learning, Causal Inference, and Predicting the Outcomes of Public Health Interventions. [europepmc]
- Putting explainable AI in context: institutional explanations for medical AI. [europepmc]
- Enabling Fairness in Healthcare Through Machine Learning. [europepmc]
- Can Machine Learning Provide Understanding? How Cosmologists Use Machine Learning to Understand Observations of the Universe. [europepmc]
- A Framework for Transparency in Precision Livestock Farming. [europepmc]
- When remediating one artifact results in another: control, confounders, and correction. [europepmc]
- The Importance of Understanding Deep Learning. [europepmc]
- Application of Artificial Intelligence in Otology: Past, Present, and Future. [europepmc]
Related