---
_id: '61156'
abstract:
- lang: eng
text: Explainability has become an important topic in computer science and artificial
intelligence, leading to a subfield called Explainable Artificial Intelligence
(XAI). The goal of providing or seeking explanations is to achieve (better) ‘understanding’
on the part of the explainee. However, what it means to ‘understand’ is still
not clearly defined, and the concept itself is rarely the subject of scientific
investigation. This conceptual article aims to present a model of forms of understanding
for XAI-explanations and beyond. From an interdisciplinary perspective bringing
together computer science, linguistics, sociology, philosophy and psychology,
a definition of understanding and its forms, assessment, and dynamics during the
process of giving everyday explanations are explored. Two types of understanding
are considered as possible outcomes of explanations, namely enabledness, ‘knowing
how’ to do or decide something, and comprehension, ‘knowing that’ – both in different
degrees (from shallow to deep). Explanations regularly start with shallow understanding
in a specific domain and can lead to deep comprehension and enabledness of the
explanandum, which we see as a prerequisite for human users to gain agency. In
this process, the increase of comprehension and enabledness are highly interdependent.
Against the background of this systematization, special challenges of understanding
in XAI are discussed.
article_number: '101419'
article_type: original
author:
- first_name: Hendrik
full_name: Buschmeier, Hendrik
id: '76456'
last_name: Buschmeier
orcid: 0000-0002-9613-5713
- first_name: Heike M.
full_name: Buhl, Heike M.
id: '27152'
last_name: Buhl
- first_name: Friederike
full_name: Kern, Friederike
last_name: Kern
- first_name: Angela
full_name: Grimminger, Angela
id: '57578'
last_name: Grimminger
- first_name: Helen
full_name: Beierling, Helen
id: '50995'
last_name: Beierling
- first_name: Josephine Beryl
full_name: Fisher, Josephine Beryl
id: '56345'
last_name: Fisher
orcid: 0000-0002-9997-9241
- first_name: André
full_name: Groß, André
id: '93405'
last_name: Groß
orcid: 0000-0002-9593-7220
- first_name: Ilona
full_name: Horwath, Ilona
id: '68836'
last_name: Horwath
- first_name: Nils
full_name: Klowait, Nils
id: '98454'
last_name: Klowait
orcid: 0000-0002-7347-099X
- first_name: Stefan Teodorov
full_name: Lazarov, Stefan Teodorov
id: '90345'
last_name: Lazarov
orcid: 0009-0009-0892-9483
- first_name: Michael
full_name: Lenke, Michael
last_name: Lenke
- first_name: Vivien
full_name: Lohmer, Vivien
last_name: Lohmer
- first_name: Katharina
full_name: Rohlfing, Katharina
id: '50352'
last_name: Rohlfing
orcid: 0000-0002-5676-8233
- first_name: Ingrid
full_name: Scharlau, Ingrid
id: '451'
last_name: Scharlau
orcid: 0000-0003-2364-9489
- first_name: Amit
full_name: Singh, Amit
id: '91018'
last_name: Singh
orcid: 0000-0002-7789-1521
- first_name: Lutz
full_name: Terfloth, Lutz
id: '37320'
last_name: Terfloth
- first_name: Anna-Lisa
full_name: Vollmer, Anna-Lisa
id: '86589'
last_name: Vollmer
- first_name: Yu
full_name: Wang, Yu
last_name: Wang
- first_name: Annedore
full_name: Wilmes, Annedore
last_name: Wilmes
- first_name: Britta
full_name: Wrede, Britta
last_name: Wrede
citation:
ama: Buschmeier H, Buhl HM, Kern F, et al. Forms of Understanding for XAI-Explanations.
Cognitive Systems Research. 2025;94. doi:10.1016/j.cogsys.2025.101419
apa: Buschmeier, H., Buhl, H. M., Kern, F., Grimminger, A., Beierling, H., Fisher,
J. B., Groß, A., Horwath, I., Klowait, N., Lazarov, S. T., Lenke, M., Lohmer,
V., Rohlfing, K., Scharlau, I., Singh, A., Terfloth, L., Vollmer, A.-L., Wang,
Y., Wilmes, A., & Wrede, B. (2025). Forms of Understanding for XAI-Explanations.
Cognitive Systems Research, 94, Article 101419. https://doi.org/10.1016/j.cogsys.2025.101419
bibtex: '@article{Buschmeier_Buhl_Kern_Grimminger_Beierling_Fisher_Groß_Horwath_Klowait_Lazarov_et
al._2025, title={Forms of Understanding for XAI-Explanations}, volume={94}, DOI={10.1016/j.cogsys.2025.101419},
number={101419}, journal={Cognitive Systems Research}, author={Buschmeier, Hendrik
and Buhl, Heike M. and Kern, Friederike and Grimminger, Angela and Beierling,
Helen and Fisher, Josephine Beryl and Groß, André and Horwath, Ilona and Klowait,
Nils and Lazarov, Stefan Teodorov and et al.}, year={2025} }'
chicago: Buschmeier, Hendrik, Heike M. Buhl, Friederike Kern, Angela Grimminger,
Helen Beierling, Josephine Beryl Fisher, André Groß, et al. “Forms of Understanding
for XAI-Explanations.” Cognitive Systems Research 94 (2025). https://doi.org/10.1016/j.cogsys.2025.101419.
ieee: 'H. Buschmeier et al., “Forms of Understanding for XAI-Explanations,”
Cognitive Systems Research, vol. 94, Art. no. 101419, 2025, doi: 10.1016/j.cogsys.2025.101419.'
mla: Buschmeier, Hendrik, et al. “Forms of Understanding for XAI-Explanations.”
Cognitive Systems Research, vol. 94, 101419, 2025, doi:10.1016/j.cogsys.2025.101419.
short: H. Buschmeier, H.M. Buhl, F. Kern, A. Grimminger, H. Beierling, J.B. Fisher,
A. Groß, I. Horwath, N. Klowait, S.T. Lazarov, M. Lenke, V. Lohmer, K. Rohlfing,
I. Scharlau, A. Singh, L. Terfloth, A.-L. Vollmer, Y. Wang, A. Wilmes, B. Wrede,
Cognitive Systems Research 94 (2025).
date_created: 2025-09-08T14:24:32Z
date_updated: 2025-12-05T15:32:25Z
ddc:
- '006'
department:
- _id: '660'
doi: 10.1016/j.cogsys.2025.101419
file:
- access_level: closed
content_type: application/pdf
creator: hbuschme
date_created: 2025-12-01T21:02:20Z
date_updated: 2025-12-01T21:02:20Z
file_id: '62730'
file_name: Buschmeier-etal-2025-COGSYS.pdf
file_size: 10114981
relation: main_file
success: 1
file_date_updated: 2025-12-01T21:02:20Z
has_accepted_license: '1'
intvolume: ' 94'
keyword:
- understanding
- explaining
- explanations
- explainable
- AI
- interdisciplinarity
- comprehension
- enabledness
- agency
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://www.sciencedirect.com/science/article/pii/S1389041725000993?via%3Dihub
oa: '1'
project:
- _id: '111'
name: 'TRR 318; TP A01: Adaptives Erklären'
- _id: '112'
name: 'TRR 318; TP A02: Verstehensprozess einer Erklärung beobachten und auswerten'
- _id: '113'
name: TRR 318 - Subproject A3
- _id: '114'
name: 'TRR 318; TP A04: Integration des technischen Modells in das Partnermodell
bei der Erklärung von digitalen Artefakten'
- _id: '115'
name: 'TRR 318; TP A05: Echtzeitmessung der Aufmerksamkeit im Mensch-Roboter-Erklärdialog'
- _id: '122'
name: TRR 318 - Subproject B3
- _id: '123'
name: TRR 318 - Subproject B5
- _id: '119'
name: TRR 318 - Project Area Ö
publication: Cognitive Systems Research
publication_status: published
quality_controlled: '1'
status: public
title: Forms of Understanding for XAI-Explanations
type: journal_article
user_id: '57578'
volume: 94
year: '2025'
...
---
_id: '36522'
abstract:
- lang: eng
text: "Jupyter notebooks enable developers to interleave code snippets with rich-text
and in-line visualizations. Data scientists use Jupyter notebook as the de-facto
standard for creating and sharing machine-learning based solutions, primarily
written in Python. Recent studies have demonstrated, however, that a large portion
of Jupyter notebooks available on public platforms are undocumented and lacks
a narrative structure. This reduces the readability of these notebooks. To address
this shortcoming, this paper presents HeaderGen, a novel tool-based approach that
automatically annotates code cells with categorical markdown headers based on
a taxonomy of machine-learning operations, and classifies and displays function
calls according to this taxonomy. For this functionality to be realized, HeaderGen
enhances an existing call graph analysis in PyCG. To improve precision, HeaderGen
extends PyCG's analysis with support for handling external library code and flow-sensitivity.
The former is realized by facilitating the resolution of function return-types.
Furthermore, HeaderGen uses type information to perform pattern matching on code
syntax to annotate code cells.\r\nThe evaluation on 15 real-world Jupyter notebooks
from Kaggle shows that HeaderGen's underlying call graph analysis yields high
accuracy (96.4% precision and 95.9% recall). This is because HeaderGen can resolve
return-types of external libraries where existing type inference tools such as
pytype (by Google), pyright (by Microsoft), and Jedi fall short. The header generation
has a precision of 82.2% and a recall rate of 96.8% with regard to headers created
manually by experts. In a user study, HeaderGen helps participants finish comprehension
and navigation tasks faster. All participants clearly perceive HeaderGen as useful
to their task."
author:
- first_name: Ashwin Prasad
full_name: Shivarpatna Venkatesh, Ashwin Prasad
id: '66637'
last_name: Shivarpatna Venkatesh
- first_name: Jiawei
full_name: Wang, Jiawei
last_name: Wang
- first_name: Li
full_name: Li, Li
last_name: Li
- first_name: Eric
full_name: Bodden, Eric
id: '59256'
last_name: Bodden
orcid: 0000-0003-3470-3647
citation:
ama: 'Shivarpatna Venkatesh AP, Wang J, Li L, Bodden E. Enhancing Comprehension
and Navigation in Jupyter Notebooks with Static Analysis. In: IEEE SANER 2023
(International Conference on Software Analysis, Evolution and Reengineering);
2023. doi:10.48550/ARXIV.2301.04419'
apa: Shivarpatna Venkatesh, A. P., Wang, J., Li, L., & Bodden, E. (2023). Enhancing
Comprehension and Navigation in Jupyter Notebooks with Static Analysis. IEEE
SANER 2023 (International Conference on Software Analysis, Evolution and Reengineering).
https://doi.org/10.48550/ARXIV.2301.04419
bibtex: '@inproceedings{Shivarpatna Venkatesh_Wang_Li_Bodden_2023, title={Enhancing
Comprehension and Navigation in Jupyter Notebooks with Static Analysis}, DOI={10.48550/ARXIV.2301.04419},
publisher={IEEE SANER 2023 (International Conference on Software Analysis, Evolution
and Reengineering)}, author={Shivarpatna Venkatesh, Ashwin Prasad and Wang, Jiawei
and Li, Li and Bodden, Eric}, year={2023} }'
chicago: Shivarpatna Venkatesh, Ashwin Prasad, Jiawei Wang, Li Li, and Eric Bodden.
“Enhancing Comprehension and Navigation in Jupyter Notebooks with Static Analysis.”
IEEE SANER 2023 (International Conference on Software Analysis, Evolution and
Reengineering), 2023. https://doi.org/10.48550/ARXIV.2301.04419.
ieee: 'A. P. Shivarpatna Venkatesh, J. Wang, L. Li, and E. Bodden, “Enhancing Comprehension
and Navigation in Jupyter Notebooks with Static Analysis,” presented at the IEEE
SANER 2023 (International Conference on Software Analysis, Evolution and Reengineering),
2023, doi: 10.48550/ARXIV.2301.04419.'
mla: Shivarpatna Venkatesh, Ashwin Prasad, et al. Enhancing Comprehension and
Navigation in Jupyter Notebooks with Static Analysis. IEEE SANER 2023 (International
Conference on Software Analysis, Evolution and Reengineering), 2023, doi:10.48550/ARXIV.2301.04419.
short: 'A.P. Shivarpatna Venkatesh, J. Wang, L. Li, E. Bodden, in: IEEE SANER 2023
(International Conference on Software Analysis, Evolution and Reengineering),
2023.'
conference:
name: IEEE SANER 2023 (International Conference on Software Analysis, Evolution
and Reengineering)
date_created: 2023-01-13T08:03:26Z
date_updated: 2025-04-07T10:18:03Z
ddc:
- '000'
doi: 10.48550/ARXIV.2301.04419
file:
- access_level: open_access
content_type: application/pdf
creator: ashwin
date_created: 2023-01-26T10:48:40Z
date_updated: 2023-01-26T10:48:40Z
file_id: '40304'
file_name: 2301.04419.pdf
file_size: 1862440
relation: main_file
file_date_updated: 2023-01-26T10:48:40Z
has_accepted_license: '1'
keyword:
- static analysis
- python
- code comprehension
- annotation
- literate programming
- jupyter notebook
language:
- iso: eng
oa: '1'
publisher: IEEE SANER 2023 (International Conference on Software Analysis, Evolution
and Reengineering)
status: public
title: Enhancing Comprehension and Navigation in Jupyter Notebooks with Static Analysis
type: conference
user_id: '15249'
year: '2023'
...