CONTRASTIVE EXPLANATIONS IN EVOLUTIONARY BIOLOGY
Abstract
Taxonomists in biology have traditionally been concerned to delimit and classify actual (or previously actual) biological forms or kinds. But not all useful classification schemes are of actualised forms. This paper focuses on the need to delimit and classify non‐actual forms when offering contrastive explanations in evolutionary biology. Such a classification scheme sorts actual and non‐actual forms according to their modal status. Such a sorting has been offered by theoretical morphologists, but these efforts have paid insufficient attention to the metaphysics of modality. Contemporary approaches to the metaphysics and epistemology of modality are also found wanting. The paper ends by arguing that the needed intellectual resources are to be found in the imaginative use of Aristotle.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The proposed metric in Fernández et al.'s framework [80] penalizes the number of feature changes when traversing the tree so that sparsity is promoted.
“The proposed metric penalizes the number of feature changes when traversing the tree so that sparsity is promoted.”
From A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence (2021) · cites this paper as [80]
In Fernández et al.'s framework [80], the relevance of the generated counterfactuals is measured by calculating a variant of the Gower distance.
“The relevance of the generated counterfactuals is then measured by calculating a variant of the Gower distance.”
From A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence (2021) · cites this paper as [80]
Several model-specific frameworks generate counterfactuals to explain the output of decision trees [46], [80], [122], [155].
“Several model-specific frameworks generate counterfactuals to explain the output of decision trees [46], [80], [122], [155].”
From A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence (2021) · cites this paper as [80]
Fernández et al. [80] present a recursive algorithm which extracts counterfactuals in the form of contrast-class decision tree nodes.
“For instance, Fernández et al. [80] present a recursive algorithm which extracts counterfactuals in the form of contrast-class decision tree nodes.”
From A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence (2021) · cites this paper as [80]
Numerical counterfactual explanations can replicate the internals of the classifier's structure, e.g., in the form of decision tree nodes or rules.
“In addition, they can replicate the internals of the classifier's structure, e.g., in the form of decision tree nodes or rules [80], [140], [152].”
From A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence (2021) · cites this paper as [80]
Cited by
Sorted by citations
Stepin, I., Alonso, J. M., Catala, A., & Pereira-Farina, M. (2021) · IEEE Access · doi:10.1109/access.2021.3051315 · Cited by 376 · see citing works
“Finally, Boulter illustrates the use of contrastive explanations to distinguish between actual and non-actual biological forms [70].”
Background
- Authors
- Boulter, S.
- Affiliations
- Oxford Brookes University (GB)
- Corresponding author
- Boulter, Stephen
- ORCID
- Boulter, Stephen
- Venue
- Ratio
- Publisher
- Wiley
- Published
- 2012-11-06
- Volume
- 25
- Issue
- 4
- Pages
- 425-441
- ISSN
- 0034-0006 (ISSN-L)
- 1467-9329
- OpenAlex
- W1597293406
- Cited by
- 1
- References
- 0
- Citations by year
- 2021: 1
- FWCI
- 0.00
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Ratio (publishedVersion)
- Topics
- Social Sciences › Arts and Humanities › History and Philosophy of Science › Philosophy and History of Science
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Philosophy and Theoretical Science
- Social Sciences › Arts and Humanities › Philosophy › Epistemology, Ethics, and Metaphysics
- Keywords
- contrastive explanations, evolutionary biology, metaphysics of modality, epistemology of modality, taxonomy, Aristotle
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
