From Guidon to Neomycin and Heracles in twenty short lessons

By William J. Clancey. 1986

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI (2019, methodology): “…of the first generation of expert systems gave birth to the first generation of explanation systems, including Mycin and its related systems (see Clancey, 1986a, for a detailed history), the Digitalis Therapy Advisor (Swartout, 1977); BLAH (Wiener, 1980), and other special-purpose explanation…”
Metrics for Explainable AI: Challenges and Prospects (2018, methodology): “User models for AI and expert systems were aimed at emulating human cognition and thereby replicating performance on various tasks (see for instance, Anderson et al., 1990; Clancey, 1984, 1986).”
Bridging the Gap Between Ethics and Practice (2020, background): “Clancey [22] describes their pursuit of explainability by way of step-by-step processes, support for “how” and “why” questions tied to causality, counterfactual query support, and graphical overviews.”
Explainable Artificial Intelligence for Training and Tutoring (2005, background): “Three notable efforts falling into this category are the Program Enhancement Advisor (PEA) for teaching LISP programmers to improve their code [5], the family of successors to MYCIN [1], and another entity-driven explanation system, Debrief [4].”
Handbook of Research on Learning and Instruction (2011, background): “Table 8.1 Features and Cues for Throwing (adopted from Knudson & Morrison, 1996)”