2021
DOI: 10.1007/978-3-030-81688-9_24
|View full text |Cite
|
Sign up to set email alerts
|

Foundations of Fine-Grained Explainability

Abstract: Explainability is the process of linking part of the inputs given to a calculation to its output, in such a way that the selected inputs somehow “cause” the result. We establish the formal foundations of a notion of explainability for arbitrary abstract functions manipulating nested data structures. We then establish explanation relationships for a set of elementary functions, and for compositions thereof. A fully functional implementation of these concepts is finally presented and experimentally evaluated.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2022
2022
2023
2023

Publication Types

Select...
1
1

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(3 citation statements)
references
References 44 publications
0
3
0
Order By: Relevance
“…Each of the diagrams above corresponds to less than 10 lines of Java code. 4 Figure 2 shows the code for Variation 4.…”
Section: Fundamental Conceptsmentioning
confidence: 99%
See 2 more Smart Citations
“…Each of the diagrams above corresponds to less than 10 lines of Java code. 4 Figure 2 shows the code for Variation 4.…”
Section: Fundamental Conceptsmentioning
confidence: 99%
“…Synthia incorporates functionalities for explaining the values produced by a chain of pickers. It leverages an existing library called Petit Poucet [4], which allows one to point to a part of an output produced by some object, and to retrace it back to parts of the inputs that contributed to the production of that value. In the terminology of Petit Poucet, a designator is an object used to refer to a particular part of the input or output of a given computation.…”
Section: Advanced Featuresmentioning
confidence: 99%
See 1 more Smart Citation