Scientific Theory of a Black-Box: A Life Cycle-Scale XAI Framework Based on Constructive Empiricism
Sebastian M\"uller, Vanessa Toborek, Eike Stadtl\"ander, Tam\'as Horv\'ath, Brendan Balcerak Jackson, Christian Bauckhage

TL;DR
This paper introduces a scientific theory framework for explainable AI that maintains an auditable, adaptable, and empirically adequate record of a black-box model's behavior throughout its lifecycle, enhancing transparency and trust.
Contribution
It proposes the concept of a scientific theory of a black-box (SToBB) grounded in Constructive Empiricism, operationalizing it as a comprehensive, updateable, and auditable framework for black-box explanation.
Findings
Implemented a complete SToBB for a neural network classifier
Developed the CoBoT algorithm for online rule-based surrogate construction
Demonstrated systematic external scrutiny and reusability of explanations
Abstract
Explainable AI (XAI) offers a growing number of algorithms that aim to answer specific questions about black-box models. What is missing is a principled way to consolidate explanatory information about a fixed black-box model into a persistent, auditable artefact, that accompanies the black-box throughout its life cycle. We address this gap by introducing the notion of a scientific theory of a black (SToBB). Grounded in Constructive Empiricism, a SToBB fulfils three obligations: (i) empirical adequacy with respect to all available observations of black-box behaviour, (ii) adaptability via explicit update commitments that restore adequacy when new observations arrive, and (iii) auditability through transparent documentation of assumptions, construction choices, and update behaviour. We operationalise these obligations as a general framework that specifies an extensible observation base,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsExplainable Artificial Intelligence (XAI) · Machine Learning in Materials Science · Generative Adversarial Networks and Image Synthesis
