The DOI matches its Crossref record; the references it cites are not checked yet.
Measuring the Quality of Explanations: The System Causability Scale (SCS): Comparing Human and Machine Explanations
Open accessAbstract
Recent success in Artificial Intelligence (AI) and Machine Learning (ML) allow problem solving automatically without any human intervention. Autonomous approaches can be very convenient. However, in certain domains, e.g., in the medical domain, it is necessary to enable a domain expert to understand, why an algorithm came up with a certain result. Consequently, the field of Explainable AI (xAI) rapidly gained interest worldwide in various domains, particularly in medicine. Explainable AI studies transparency and traceability of opaque AI/ML and there are already a huge variety of methods. For example with layer-wise relevance propagation relevant parts of inputs to, and representations in, a neural network which caused a result, can be highlighted. This is a first important step to ensure that end users, e.g., medical professionals, assume responsibility for decision making with AI/ML and of interest to professionals and regulators. Interactive ML adds the component of human expertise to AI/ML processes by enabling them to re-enact and retrace AI/ML results, e.g. let them check it for plausibility. This requires new human–AI interfaces for explainable AI. In order to build effective and efficient interactive human–AI interfaces we have to deal with the question of how to evaluate the quality of explanations given by an explainable AI system. In this paper we introduce our System Causability Scale to measure the quality of explanations. It is based on our notion of Causability (Holzinger et al. in Wiley Interdiscip Rev Data Min Knowl Discov 9(4), 2019) combined with concepts adapted from a widely-accepted usability scale.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures

Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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 source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Examples include the System Causability Scale [123] or the Muir Trust Scale [124], which are widely adopted in human robot interaction and robotics and rely on predictability ( To what extent the robot behavior [the output of the AI-based system] can be predicted from moment to moment? ), reliability ( To what extent can you count on the system to do its job? ), competence ( What degree of faith”
From Connecting the dots in trustworthy Artificial Intelligence: From AI principles, ethics, and key requirements to responsible AI systems and regulation (2023) · cites this paper as [123]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In terms of auditing procedures, especially when the AI system interacts with users, grading schemes adapted to the use case [123] are in need for validating models.”
From Connecting the dots in trustworthy Artificial Intelligence: From AI principles, ethics, and key requirements to responsible AI systems and regulation (2023) · cites this paper as [123]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Moreover, even well-designed explanations should be evaluated with users to measure their quality (Holzinger et al., 2020).”
From Understanding user mental models in AI-driven code completion tools: Insights from an elicitation study (2025) · cites this paper as Holzinger et al., 2020
The cited source says what the claim attributes to it.
In the citing paper
“The concept of what defines a good explanation is not trivial and is an aspect that is widely studied in the literature (Miller, 2019; Holzinger et al., 2020).”
From Understanding user mental models in AI-driven code completion tools: Insights from an elicitation study (2025) · cites this paper as Holzinger et al., 2020
In the citing paper
“System Causability Scale (SCS) assesses the quality of the interpretability methods which can be utilized in the medical domain [55].”
From Transparency of deep neural networks for medical image analysis: A review of interpretability methods (2022) · cites this paper as [55]
1 more claim about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
The citation lists are queued
They are fetched later and appear here then.
References 40 · Cited by 406
Research works printed but not linked: 1
- Gelman A, Carlin JB, Stern HS, Dunson DB, Rubin DB (2013) Fundamentals of Bayesian data analysis: chapter 5 Hierarchical models. CRC Press, ISBN 978-1-58488-388
Metadata
- Authors
- Holzinger, A., Carrington, A., & Müller, H.
- Affiliations
- Medical University of Graz (AT)
- Ottawa Hospital Research Institute (CA)
- Corresponding author
- Holzinger, Andreas
- Venue
- KI - Künstliche Intelligenz
- Published
- 2020-01-21
- Volume
- 34
- Issue
- 2
- Pages
- 193-198
- ISSN
- 0933-1875 (ISSN-L)
- 1610-1987
- PMC
- PMC7271052
- OpenAlex
- W3000965188
- Cited by
- 406
- References
- 40
- Citations by year
- 2026: 63 · 2025: 61 · 2024: 56 · 2023: 42 · 2022: 84 · 2021: 58 · 2020: 42
- FWCI
- 22.01
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
- Locations
- Künstliche Intell. (publishedVersion, cc-by)
- Funders
- Austrian Science Fund (P-32554)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Human-Computer Interaction › Usability and User Interface Design
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Keywords
- explainable AI, explanation quality, usability evaluation, human-AI interaction, interactive machine learning, clinical decision support, layer-wise relevance propagation, human-AI interface
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Measuring the Quality of Explanations: The System Causability Scale (SCS): Comparing Human and Machine Explanations. https://app.cochat.ai/papers/10.1007/s13218-020-00636-z
- The paper
- Holzinger, A., Carrington, A., & Müller, H. (2020). Measuring the Quality of Explanations: The System Causability Scale (SCS): Comparing Human and Machine Explanations. KI - Künstliche Intelligenz. https://doi.org/10.1007/s13218-020-00636-z
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.